While processing polymetallic ores at the non-ferrous metallurgy problems arises connecting with the excellence of production and the efficient applying the technological devices-firing furnace and crusher machine. In earlier time, similar questions were solved due to the big practice experiences and using a mathematical modeling method. The mathematical model for optimizing those operating mode is a very complex and hard to calculation. Performing computations is needed too much time and many resources. Because the control of the agglomeration furnaces and other machines are including complex multiparameter processes. The method of the math modeling for optimization the operating mode to the firing furnace is replaced with modeling based on the neural network that is here a new method. The results obtained have shown that proposed methods based on the neural network modeling of metallurgical processes allow determining more accurate and adequate results of calculations than mathematical modeling by the traditional program. The use of new approaches for modeling the technological processes at the non-ferrous metallurgy gives opportunity to enhance an effectiveness of production excellence and to enhance an efficient applying the heat-energy equipment while a firing the sulfide polymetallic ores of non-ferrous metallurgy.
This document proposes using Markov chains to model and analyze industrial electronic repair processes. Markov chains are well-suited for this application because repair processes are stochastic in nature, with many possible paths and outcomes. The document introduces two Markov chain models - an absorbing Markov chain model and an acyclic absorbing Markov chain model - to represent repair processes and determine important operational parameters. The models can help identify improvement opportunities, support quality control efforts, and inform resource allocation decisions. An example application to a real electronic repair process is also discussed.
Algorithm for Modeling Unconventional Machine Tool Machining Parameters using...IDES Editor
Unconventional machining process finds a lot of
application in aerospace and precision industries. It is
preferred over other conventional methods because of the
advent of composite and high strength to weight ratio
materials, complex parts and also because of its high accuracy
and precision. Usually in unconventional machine tools, trial
and error method is used to fix the values of process
parameters. In the proposed work an algorithm which is
developed using Artificial Neural Network (ANN) is proposed
to create mathematical model functionally relating process
parameters and operating parameters of any unconventional
machine tool. This is accomplished by training a feed forward
network with back propagation learning algorithm. The
required data which are used for training and testing the ANN
in the case study is obtained by conducting trial runs in EBW
machine. By adopting the proposed algorithm there will be a
reduction in production time and set-up time along with
reduction in manufacturing cost in unconventional machining
processes. This in general increases the overall productivity.
The programs for training and testing the neural network are
developed, using MATLAB package
IRJET-Finite Element Analysis of CFRP Composite Material Machining: A ReviewIRJET Journal
This document provides a review of finite element analysis techniques used to model machining of carbon fiber reinforced polymer (CFRP) composite materials. It discusses that finite element analysis can be used to simulate the machining process and evaluate factors that affect machining of CFRP laminates. The document reviews different finite element modeling techniques used in previous studies, including equivalent homogeneous material models and micromechanical models. It also discusses modeling considerations like meshing, material properties definitions, and boundary conditions. The key findings from several previous finite element studies on drilling and milling of CFRP composites are summarized. Overall, the document aims to provide an overview of current trends in finite element modeling of CFRP composite machining.
CFD SIMULATION OF SOLDER PASTE FLOW AND DEFORMATION BEHAVIOURS DURING STENCIL...ijmech
In 20th century, Electronics elements have become most significant part of the regular life. The main heart
of electronic element is PCB which supports and manages mostly machines and equipments these days.
Therefore manufacturing of board and assembly of electronic elements is one of the crucial and significant
objectives for most of the companies. Better life of PCB’s depends on electronic elements and its assembly
with board. Solder paste is used as adhesive material for assembly purpose. It is deposited on board using
stencil and electronic elements are mounted on it and heated for strong bond.
This study investigates on factors affecting stencil printing process due to variation in squeegee speed and
density of solder paste. This study is based on computational fluid dynamics virtual simulation. Prototype is
developed for modelling purpose and simulation software is used to simulate the flow behaviour of solder
paste during stencil printing process.
Computational Nano Technology and Simulation Techniques Applied to Study Silv...IRJET Journal
This document discusses computational nanotechnology methods for simulating silver nano dots. It describes three types of nanotechnologies: wet, dry, and computational. Computational nanotechnology uses computer algorithms and simulations to model nanostructures and devices. The document focuses on using software tools like Quantum Dot Lab and molecular dynamics simulations to model the structure, properties, and dynamics of silver quantum dots at the nanoscale. These computational methods allow for faster, more accurate analysis compared to experimental techniques alone. The simulations provide insights into the charged states, light emission, and movement of atoms in silver nano dots over time.
A review of soft computing techniques in materials engineeringIAEME Publication
This document provides a review of soft computing techniques that have been applied in materials engineering, with a focus on sheet metals. It discusses that soft computing methods like artificial neural networks, genetic algorithms, and other evolutionary algorithms have shown promising results when applied to problems in materials design, modeling properties, process optimization and control. The document reviews several studies that have used these techniques for materials proportion prediction, properties modeling, optimization and other applications. However, it also notes that the interface between materials engineering and intelligent systems techniques is still unclear and more work needs to be done to formalize the methodology.
J4.pdf additive manufacturing papers to studyendarapuarun
This document presents a conceptual framework for combining finite element modeling and machine learning techniques to optimize process parameters for powder bed fusion additive manufacturing. Finite element modeling is useful for numerically simulating the manufacturing process but requires detailed knowledge of material properties. Machine learning can predict process parameters from large datasets but requires significant data. The framework aims to leverage the strengths of both approaches by using finite element modeling to simulate the process based on machine learning predictions of parameters, and test those predictions through additional modeling.
performance study of electrochemical machining on metal matrix compositeNEERAJKUMAR1898
The document discusses performance studies of electrochemical machining (ECM) on metal matrix composites. It describes fabricating five different aluminum matrix composites using stir casting, including an Al 6061 alloy reinforced with 6% graphite and an Al 6061 alloy reinforced with 5% silicon carbide and 5% graphite. Experiments were conducted using Taguchi's design of experiments to determine the optimal ECM process parameters of voltage, electrolyte concentration, and frequency for maximizing material removal rate and minimizing overcut of the composites.
This document proposes using Markov chains to model and analyze industrial electronic repair processes. Markov chains are well-suited for this application because repair processes are stochastic in nature, with many possible paths and outcomes. The document introduces two Markov chain models - an absorbing Markov chain model and an acyclic absorbing Markov chain model - to represent repair processes and determine important operational parameters. The models can help identify improvement opportunities, support quality control efforts, and inform resource allocation decisions. An example application to a real electronic repair process is also discussed.
Algorithm for Modeling Unconventional Machine Tool Machining Parameters using...IDES Editor
Unconventional machining process finds a lot of
application in aerospace and precision industries. It is
preferred over other conventional methods because of the
advent of composite and high strength to weight ratio
materials, complex parts and also because of its high accuracy
and precision. Usually in unconventional machine tools, trial
and error method is used to fix the values of process
parameters. In the proposed work an algorithm which is
developed using Artificial Neural Network (ANN) is proposed
to create mathematical model functionally relating process
parameters and operating parameters of any unconventional
machine tool. This is accomplished by training a feed forward
network with back propagation learning algorithm. The
required data which are used for training and testing the ANN
in the case study is obtained by conducting trial runs in EBW
machine. By adopting the proposed algorithm there will be a
reduction in production time and set-up time along with
reduction in manufacturing cost in unconventional machining
processes. This in general increases the overall productivity.
The programs for training and testing the neural network are
developed, using MATLAB package
IRJET-Finite Element Analysis of CFRP Composite Material Machining: A ReviewIRJET Journal
This document provides a review of finite element analysis techniques used to model machining of carbon fiber reinforced polymer (CFRP) composite materials. It discusses that finite element analysis can be used to simulate the machining process and evaluate factors that affect machining of CFRP laminates. The document reviews different finite element modeling techniques used in previous studies, including equivalent homogeneous material models and micromechanical models. It also discusses modeling considerations like meshing, material properties definitions, and boundary conditions. The key findings from several previous finite element studies on drilling and milling of CFRP composites are summarized. Overall, the document aims to provide an overview of current trends in finite element modeling of CFRP composite machining.
CFD SIMULATION OF SOLDER PASTE FLOW AND DEFORMATION BEHAVIOURS DURING STENCIL...ijmech
In 20th century, Electronics elements have become most significant part of the regular life. The main heart
of electronic element is PCB which supports and manages mostly machines and equipments these days.
Therefore manufacturing of board and assembly of electronic elements is one of the crucial and significant
objectives for most of the companies. Better life of PCB’s depends on electronic elements and its assembly
with board. Solder paste is used as adhesive material for assembly purpose. It is deposited on board using
stencil and electronic elements are mounted on it and heated for strong bond.
This study investigates on factors affecting stencil printing process due to variation in squeegee speed and
density of solder paste. This study is based on computational fluid dynamics virtual simulation. Prototype is
developed for modelling purpose and simulation software is used to simulate the flow behaviour of solder
paste during stencil printing process.
Computational Nano Technology and Simulation Techniques Applied to Study Silv...IRJET Journal
This document discusses computational nanotechnology methods for simulating silver nano dots. It describes three types of nanotechnologies: wet, dry, and computational. Computational nanotechnology uses computer algorithms and simulations to model nanostructures and devices. The document focuses on using software tools like Quantum Dot Lab and molecular dynamics simulations to model the structure, properties, and dynamics of silver quantum dots at the nanoscale. These computational methods allow for faster, more accurate analysis compared to experimental techniques alone. The simulations provide insights into the charged states, light emission, and movement of atoms in silver nano dots over time.
A review of soft computing techniques in materials engineeringIAEME Publication
This document provides a review of soft computing techniques that have been applied in materials engineering, with a focus on sheet metals. It discusses that soft computing methods like artificial neural networks, genetic algorithms, and other evolutionary algorithms have shown promising results when applied to problems in materials design, modeling properties, process optimization and control. The document reviews several studies that have used these techniques for materials proportion prediction, properties modeling, optimization and other applications. However, it also notes that the interface between materials engineering and intelligent systems techniques is still unclear and more work needs to be done to formalize the methodology.
J4.pdf additive manufacturing papers to studyendarapuarun
This document presents a conceptual framework for combining finite element modeling and machine learning techniques to optimize process parameters for powder bed fusion additive manufacturing. Finite element modeling is useful for numerically simulating the manufacturing process but requires detailed knowledge of material properties. Machine learning can predict process parameters from large datasets but requires significant data. The framework aims to leverage the strengths of both approaches by using finite element modeling to simulate the process based on machine learning predictions of parameters, and test those predictions through additional modeling.
performance study of electrochemical machining on metal matrix compositeNEERAJKUMAR1898
The document discusses performance studies of electrochemical machining (ECM) on metal matrix composites. It describes fabricating five different aluminum matrix composites using stir casting, including an Al 6061 alloy reinforced with 6% graphite and an Al 6061 alloy reinforced with 5% silicon carbide and 5% graphite. Experiments were conducted using Taguchi's design of experiments to determine the optimal ECM process parameters of voltage, electrolyte concentration, and frequency for maximizing material removal rate and minimizing overcut of the composites.
IRJET- Electric Discharge Machine: Review on Increase an Efficiency of Me...IRJET Journal
This document reviews research on improving the efficiency of electric discharge machining (EDM). EDM is a non-traditional machining process that uses electric sparks to machine hard conductive materials. Researchers have studied coating copper on tools to improve heat transfer and thus increase material removal rate and tool life. The document also summarizes several past studies that used techniques like Taguchi methods and fuzzy logic to optimize EDM process parameters like pulse on/off times and increase surface finish quality and reduce electrode wear. Overall, the review finds that modeling process parameters and using coatings on tools can improve the efficiency of EDM for precision machining of difficult materials.
1. The document presents research on using artificial neural networks to model and predict the mechanical properties of structural steels after heat treatment.
2. Over 125 types of non-alloy and alloy structural steels were examined, including properties like strength, impact resistance, and hardness.
3. Neural networks were trained using input parameters like chemical composition, heat treatment type and parameters, and geometry to predict mechanical properties. Results showed the neural networks could accurately predict properties within the given input ranges.
Application of artificial neural networksveghalexxx19
This document describes the application of artificial neural networks to model the mechanical properties of structural steels after heat treatment. Specifically:
1. Artificial neural networks were used to predict mechanical properties like strength, impact resistance, and hardness based on input parameters like chemical composition, heat treatment type and parameters, and element geometry.
2. The neural networks were trained on a data set of over 14,212 samples of different structural steel compositions and heat treatments.
3. The results showed that the neural networks were able to accurately predict the mechanical properties for steels within the ranges of the input parameters, with correlation coefficients over 90% and low standard deviation, indicating good ability to generalize to new data.
Coal-Fired Boiler Fault Prediction using Artificial Neural Networks IJECEIAES
Boiler fault is a critical issue in a coal-fired power plant due to its high temperature and high pressure characteristics. The complexity of boiler design increases the difficulty of fault investigation in a quick moment to avoid long duration shut-down. In this paper, a boiler fault prediction model is proposed using artificial neural network. The key influential parameters analysis is carried out to identify its correlation with the performance of the boiler. The prediction model is developed to achieve the least misclassification rate and mean squared error. Artificial neural network is trained using a set of boiler operational parameters. Subsequenlty, the trained model is used to validate its prediction accuracy against actual fault value from a collected real plant data. With reference to the study and test results, two set of initial weights have been tested to verify the repeatability of the correct prediction. The results show that the artificial neural network implemented is able to provide an average of above 92% prediction rate of accuracy.
Effect of the welding process parameter in mmaw for joining of dissimilar metalsIAEME Publication
This document discusses optimizing welding parameters for joining dissimilar metals using manual metal arc welding and an artificial neural fuzzy interface system. Experimental results were analyzed using regression analysis to develop mathematical models relating welding current, voltage, speed, and electrode angle to weld strength and metal deposition rate. An artificial neural network was trained on the experimental data and used to predict the optimal parameters to achieve the highest weld strength. Validation experiments showed the artificial neural fuzzy interface system successfully optimized the welding parameters.
IRJET - Optimal Parameters of Electro-Chemical MachiningIRJET Journal
This document discusses optimizing the parameters of electrochemical machining (ECM) using genetic algorithms. The optimization problem aims to maximize the material removal rate by selecting optimal values for the design variables of electrolyte concentration, flow rate, applied voltage, and feed rate. Genetic algorithms from MATLAB are applied to solve the optimization problem and determine the optimal parameter values for ECM. The results found the maximum material removal rate was achieved with electrolyte concentration of 18.3, flow rate of 5, applied voltage of 15 volts, and feed rate of 0.9.
A Unified Approach for Performance Degradation Analysis from Transistor to Gat...IJECEIAES
In this paper, we present an extensive analysis of the performance degradation in MOS- FET based circuits. The physical effects that we consider are the random dopant fluctuation (RDF), the oxide thickness fluctuation (OTF) and the Hot-carrier-Instability (HCI). The work that we propose is based on two main key points: First, the performance degradation is studied considering BULK, Silicon-On-Insulator (SOI) and Double Gate (DG) MOSFET technologies. The analysis considers technology nodes from 45nm to 11nm. For the HCI effect we consider also the time-dependent evolution of the parameters of the circuit. Second, the analysis is performed from transistor level to gate level. Models are used to evaluate the variation of transistors key parameters, and how these variation affects performance at gate level as well.The work here presented was obtained using TAMTAMS Web, an open and publicly available framework for analysis of circuits based on transistors. The use of TAMTAMS Web greatly increases the value of this work, given that the analysis can be easily extended and improved in both complexity and depth.
Investigation of Material Removal Rate, Surface Roughness and Surface Morphol...IRJET Journal
This document summarizes a study that investigated the effect of wire-electro discharge machining (WEDM) process parameters on material removal rate and surface roughness when machining die steel D3. The study used a Taguchi design of experiments approach with three parameters (peak current, pulse-on time, and wire tension) each at three levels. The results showed that peak current had the greatest influence on both material removal rate and surface roughness, followed by pulse-on time, while wire tension had the least influence. Material removal rate and surface roughness both generally increased with increasing levels of the three parameters. The optimal combination of parameters was determined to maximize material removal rate while minimizing surface roughness.
Development of an Explainable Model for a Gluconic Acid Bioreactor and Profit...IRJET Journal
This document discusses developing an explainable artificial neural network model for optimizing a gluconic acid bioreactor process. It aims to 1) use a grey wolf optimizer trained ANN approach to model the complex bioreactor system, 2) convert the ANN model into an explainable closed-form equation to provide insight into the underlying reactor physics, and 3) optimize the model to maximize gluconic acid yield and profitability using an evolutionary algorithm. Artificial intelligence techniques like ANNs are effective for modeling complicated bioprocesses but provide "black box" solutions that lack explainability. This study develops a general methodology to increase the explainability and acceptability of an ANN model for engineering applications like bioreactor optimization
Technology industries have a very important direct and indirect impact on Finnish business life now and also in the future. A remarkable potential lies particularly in the small- and medium-sized enterprises. To develop and maintain industrial competitiveness we develop technological solutions which can widely be exploited by the Finnish manufacturing industries.
This presentation gives an overview of the VTT’s experience and offering for industry and is focused to computational material development, robotics, additive manufacturing, and concept design.
An overview on application of machine learning techniques in optical networksKhaleda Ali
This document provides an overview of machine learning techniques applied to optical networks. It discusses how optical networks have become more complex with the introduction of technologies like coherent transmission and elastic optical networks. This increased complexity motivates the use of machine learning to analyze network data and make decisions. The document surveys existing work on machine learning applications in optical communications and networking. It aims to introduce researchers to this field and propose new research directions to further the application of machine learning to optical networks.
Study of brass wire and cryogenic treated brass wire on titanium alloy using ...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
The document discusses using a genetic algorithm approach to optimize process parameters in laser beam welding of Inconel. Experiments were conducted varying pulse duration, pulse frequency, welding speed, and pulse energy. Response surface methodology was used to develop mathematical models relating the weld bead geometry (penetration, width, volume) to the process parameters. The models are then used with a genetic algorithm to optimize the total bead volume while keeping the other geometry parameters within constraints, in order to produce high quality welds efficiently. In summary, the proposed methodology enables determining optimal process settings for different production needs and potentially automating the welding process.
This document discusses hierarchical design models for use in the mechatronic product development process, specifically for synchronous machines. It proposes a hierarchical design process where domain-specific design tasks are not fully integrated at the mechatronic level, but instead models cover different views and levels of detail of a system. Models represent structural, behavioral, and functional knowledge and views of a system. The approach is demonstrated through the design process of synchronous machines.
IRJET- Enhancement of Thermal Properties of Dielectric by Adding NanoparticleIRJET Journal
This document discusses enhancing the thermal properties of dielectric fluids used in electric discharge machining (EDM) by adding copper nanoparticles. Experiments were conducted adding copper nanoparticles to the dielectric fluid in EDM to investigate the impact on material removal rate, surface roughness, and thermal conductivity. It was found that adding nanoparticles increased the thermal conductivity of the dielectric fluid, which led to increases in material removal rate of 18-36% compared to conventional EDM without nanoparticles. The document provides background on EDM processes, nanoparticle production methods, and thermal conductivity of dielectric fluids.
Investigation of mrr in wedm for wc co sintered compositeIAEME Publication
The document investigates the influence of wire electrical discharge machining (WEDM) parameters on material removal rate when machining tungsten carbide-cobalt (WC-Co) sintered composite. Experiments were conducted using a response surface methodology with five control factors (pulse on-time, pulse off-time, peak current, servo voltage, and wire tension). The results were used to derive a mathematical model to predict material removal rate and optimize the WEDM process for machining WC-Co composite.
Development of intelligent protection and automation control systems using fu...IJECEIAES
In this article, the causes of technological disturbances in electrical systems are considered, and several characteristic disadvantages of the protection and automation of elements of electrical systems are highlighted. The tendency to decrease the reliability of relay protection associated with the transition from analog to digital types of protection is substantiated. Based on the studied examples, the use of fuzzy logic in protections, the expediency of using fuzzy logic elements in protection devices, and the automation of electrical systems to identify types of short circuits are justified. This article analyzes the most common damages and presents the results of modeling an electrical system with transformer coupling, where all types of asymmetric short circuits were initiated. The dynamics of changes in the symmetrical components of short-circuit currents of the forward, reverse, and zero sequences are determined. Rules have been created for the identification of asymmetric types of short circuits. An algorithm of protection and automation operation using fuzzy logic elements has been developed. The proposed algorithm of protection and automation will reduce the time to determine the type of damage and trigger protections.
IRJET- Investigation on Electrochemical Machining of Inconel 718 AlloyIRJET Journal
This document summarizes an investigation into electrochemical machining (ECM) of Inconel 718 alloy. It provides background on ECM and Inconel 718, including chemical composition and properties. The study examined the effect of input parameters like voltage, electrolyte concentration, and feed rate on the material removal rate when ECM Inconel 718. Results showed that material removal rate initially increases and then further increases with higher voltage and electrolyte concentration. Current was found to be the most influential parameter on removing material from the workpiece. In conclusion, controlling input parameters like voltage, electrolyte concentration, and current can improve the efficiency of ECM for machining difficult alloys like Inconel 718.
Presentation of a fault tolerance algorithm for design of quantum-dot cellul...IJECEIAES
A novel algorithm for working out the Kink energy of quantum-dot cellular automata (QCA) circuits and their fault tolerability is introduced. In this algorithm at first with determining the input values on a specified design, the calculation between cells makes use of Kink physical relations will be managed. Therefore, the polarization of any cell and consequently output cell will be set. Then by determining missed cell(s) on the discussed circuit, the polarization of output cell will be obtained and by comparing it with safe state or software simulation, its fault tolerability will be proved. The proposed algorithm was implemented on a novel and advance fault tolerance full adder whose performance has been demonstrated. This algorithm could be implemented on any QCA circuit. Noticeably higher speed of the algorithm than simulation and traditional manual methods, expandability of this algorithm for variable circuits, beyond of four-dot square of QCA circuits, and the investigation of several damaged cells instead just one and special cell are the advantages of algorithmic action.
A review study of mechanical fatigue testing methods for small scale metal ma...Alexander Decker
This document reviews mechanical fatigue testing techniques for small-scale metal materials. It begins by discussing the increased focus on materials behavior at the micro and nano scales due to growing MEMS/NEMS applications. It then classifies fatigue testing techniques for small-scale materials, including uniaxial tension-tension, dynamic bending, and uniaxial tension-compression. Specific techniques are described in more detail, such as using piezoelectric actuators to enable load-controlled uniaxial cyclic loading of thin films. The document also examines fatigue properties of materials tested with these techniques, like studying crack growth rates in nickel alloy cantilever beams under dynamic bending.
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
More Related Content
Similar to Neural network modeling of agglomeration firing process for polymetallic ores
IRJET- Electric Discharge Machine: Review on Increase an Efficiency of Me...IRJET Journal
This document reviews research on improving the efficiency of electric discharge machining (EDM). EDM is a non-traditional machining process that uses electric sparks to machine hard conductive materials. Researchers have studied coating copper on tools to improve heat transfer and thus increase material removal rate and tool life. The document also summarizes several past studies that used techniques like Taguchi methods and fuzzy logic to optimize EDM process parameters like pulse on/off times and increase surface finish quality and reduce electrode wear. Overall, the review finds that modeling process parameters and using coatings on tools can improve the efficiency of EDM for precision machining of difficult materials.
1. The document presents research on using artificial neural networks to model and predict the mechanical properties of structural steels after heat treatment.
2. Over 125 types of non-alloy and alloy structural steels were examined, including properties like strength, impact resistance, and hardness.
3. Neural networks were trained using input parameters like chemical composition, heat treatment type and parameters, and geometry to predict mechanical properties. Results showed the neural networks could accurately predict properties within the given input ranges.
Application of artificial neural networksveghalexxx19
This document describes the application of artificial neural networks to model the mechanical properties of structural steels after heat treatment. Specifically:
1. Artificial neural networks were used to predict mechanical properties like strength, impact resistance, and hardness based on input parameters like chemical composition, heat treatment type and parameters, and element geometry.
2. The neural networks were trained on a data set of over 14,212 samples of different structural steel compositions and heat treatments.
3. The results showed that the neural networks were able to accurately predict the mechanical properties for steels within the ranges of the input parameters, with correlation coefficients over 90% and low standard deviation, indicating good ability to generalize to new data.
Coal-Fired Boiler Fault Prediction using Artificial Neural Networks IJECEIAES
Boiler fault is a critical issue in a coal-fired power plant due to its high temperature and high pressure characteristics. The complexity of boiler design increases the difficulty of fault investigation in a quick moment to avoid long duration shut-down. In this paper, a boiler fault prediction model is proposed using artificial neural network. The key influential parameters analysis is carried out to identify its correlation with the performance of the boiler. The prediction model is developed to achieve the least misclassification rate and mean squared error. Artificial neural network is trained using a set of boiler operational parameters. Subsequenlty, the trained model is used to validate its prediction accuracy against actual fault value from a collected real plant data. With reference to the study and test results, two set of initial weights have been tested to verify the repeatability of the correct prediction. The results show that the artificial neural network implemented is able to provide an average of above 92% prediction rate of accuracy.
Effect of the welding process parameter in mmaw for joining of dissimilar metalsIAEME Publication
This document discusses optimizing welding parameters for joining dissimilar metals using manual metal arc welding and an artificial neural fuzzy interface system. Experimental results were analyzed using regression analysis to develop mathematical models relating welding current, voltage, speed, and electrode angle to weld strength and metal deposition rate. An artificial neural network was trained on the experimental data and used to predict the optimal parameters to achieve the highest weld strength. Validation experiments showed the artificial neural fuzzy interface system successfully optimized the welding parameters.
IRJET - Optimal Parameters of Electro-Chemical MachiningIRJET Journal
This document discusses optimizing the parameters of electrochemical machining (ECM) using genetic algorithms. The optimization problem aims to maximize the material removal rate by selecting optimal values for the design variables of electrolyte concentration, flow rate, applied voltage, and feed rate. Genetic algorithms from MATLAB are applied to solve the optimization problem and determine the optimal parameter values for ECM. The results found the maximum material removal rate was achieved with electrolyte concentration of 18.3, flow rate of 5, applied voltage of 15 volts, and feed rate of 0.9.
A Unified Approach for Performance Degradation Analysis from Transistor to Gat...IJECEIAES
In this paper, we present an extensive analysis of the performance degradation in MOS- FET based circuits. The physical effects that we consider are the random dopant fluctuation (RDF), the oxide thickness fluctuation (OTF) and the Hot-carrier-Instability (HCI). The work that we propose is based on two main key points: First, the performance degradation is studied considering BULK, Silicon-On-Insulator (SOI) and Double Gate (DG) MOSFET technologies. The analysis considers technology nodes from 45nm to 11nm. For the HCI effect we consider also the time-dependent evolution of the parameters of the circuit. Second, the analysis is performed from transistor level to gate level. Models are used to evaluate the variation of transistors key parameters, and how these variation affects performance at gate level as well.The work here presented was obtained using TAMTAMS Web, an open and publicly available framework for analysis of circuits based on transistors. The use of TAMTAMS Web greatly increases the value of this work, given that the analysis can be easily extended and improved in both complexity and depth.
Investigation of Material Removal Rate, Surface Roughness and Surface Morphol...IRJET Journal
This document summarizes a study that investigated the effect of wire-electro discharge machining (WEDM) process parameters on material removal rate and surface roughness when machining die steel D3. The study used a Taguchi design of experiments approach with three parameters (peak current, pulse-on time, and wire tension) each at three levels. The results showed that peak current had the greatest influence on both material removal rate and surface roughness, followed by pulse-on time, while wire tension had the least influence. Material removal rate and surface roughness both generally increased with increasing levels of the three parameters. The optimal combination of parameters was determined to maximize material removal rate while minimizing surface roughness.
Development of an Explainable Model for a Gluconic Acid Bioreactor and Profit...IRJET Journal
This document discusses developing an explainable artificial neural network model for optimizing a gluconic acid bioreactor process. It aims to 1) use a grey wolf optimizer trained ANN approach to model the complex bioreactor system, 2) convert the ANN model into an explainable closed-form equation to provide insight into the underlying reactor physics, and 3) optimize the model to maximize gluconic acid yield and profitability using an evolutionary algorithm. Artificial intelligence techniques like ANNs are effective for modeling complicated bioprocesses but provide "black box" solutions that lack explainability. This study develops a general methodology to increase the explainability and acceptability of an ANN model for engineering applications like bioreactor optimization
Technology industries have a very important direct and indirect impact on Finnish business life now and also in the future. A remarkable potential lies particularly in the small- and medium-sized enterprises. To develop and maintain industrial competitiveness we develop technological solutions which can widely be exploited by the Finnish manufacturing industries.
This presentation gives an overview of the VTT’s experience and offering for industry and is focused to computational material development, robotics, additive manufacturing, and concept design.
An overview on application of machine learning techniques in optical networksKhaleda Ali
This document provides an overview of machine learning techniques applied to optical networks. It discusses how optical networks have become more complex with the introduction of technologies like coherent transmission and elastic optical networks. This increased complexity motivates the use of machine learning to analyze network data and make decisions. The document surveys existing work on machine learning applications in optical communications and networking. It aims to introduce researchers to this field and propose new research directions to further the application of machine learning to optical networks.
Study of brass wire and cryogenic treated brass wire on titanium alloy using ...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
The document discusses using a genetic algorithm approach to optimize process parameters in laser beam welding of Inconel. Experiments were conducted varying pulse duration, pulse frequency, welding speed, and pulse energy. Response surface methodology was used to develop mathematical models relating the weld bead geometry (penetration, width, volume) to the process parameters. The models are then used with a genetic algorithm to optimize the total bead volume while keeping the other geometry parameters within constraints, in order to produce high quality welds efficiently. In summary, the proposed methodology enables determining optimal process settings for different production needs and potentially automating the welding process.
This document discusses hierarchical design models for use in the mechatronic product development process, specifically for synchronous machines. It proposes a hierarchical design process where domain-specific design tasks are not fully integrated at the mechatronic level, but instead models cover different views and levels of detail of a system. Models represent structural, behavioral, and functional knowledge and views of a system. The approach is demonstrated through the design process of synchronous machines.
IRJET- Enhancement of Thermal Properties of Dielectric by Adding NanoparticleIRJET Journal
This document discusses enhancing the thermal properties of dielectric fluids used in electric discharge machining (EDM) by adding copper nanoparticles. Experiments were conducted adding copper nanoparticles to the dielectric fluid in EDM to investigate the impact on material removal rate, surface roughness, and thermal conductivity. It was found that adding nanoparticles increased the thermal conductivity of the dielectric fluid, which led to increases in material removal rate of 18-36% compared to conventional EDM without nanoparticles. The document provides background on EDM processes, nanoparticle production methods, and thermal conductivity of dielectric fluids.
Investigation of mrr in wedm for wc co sintered compositeIAEME Publication
The document investigates the influence of wire electrical discharge machining (WEDM) parameters on material removal rate when machining tungsten carbide-cobalt (WC-Co) sintered composite. Experiments were conducted using a response surface methodology with five control factors (pulse on-time, pulse off-time, peak current, servo voltage, and wire tension). The results were used to derive a mathematical model to predict material removal rate and optimize the WEDM process for machining WC-Co composite.
Development of intelligent protection and automation control systems using fu...IJECEIAES
In this article, the causes of technological disturbances in electrical systems are considered, and several characteristic disadvantages of the protection and automation of elements of electrical systems are highlighted. The tendency to decrease the reliability of relay protection associated with the transition from analog to digital types of protection is substantiated. Based on the studied examples, the use of fuzzy logic in protections, the expediency of using fuzzy logic elements in protection devices, and the automation of electrical systems to identify types of short circuits are justified. This article analyzes the most common damages and presents the results of modeling an electrical system with transformer coupling, where all types of asymmetric short circuits were initiated. The dynamics of changes in the symmetrical components of short-circuit currents of the forward, reverse, and zero sequences are determined. Rules have been created for the identification of asymmetric types of short circuits. An algorithm of protection and automation operation using fuzzy logic elements has been developed. The proposed algorithm of protection and automation will reduce the time to determine the type of damage and trigger protections.
IRJET- Investigation on Electrochemical Machining of Inconel 718 AlloyIRJET Journal
This document summarizes an investigation into electrochemical machining (ECM) of Inconel 718 alloy. It provides background on ECM and Inconel 718, including chemical composition and properties. The study examined the effect of input parameters like voltage, electrolyte concentration, and feed rate on the material removal rate when ECM Inconel 718. Results showed that material removal rate initially increases and then further increases with higher voltage and electrolyte concentration. Current was found to be the most influential parameter on removing material from the workpiece. In conclusion, controlling input parameters like voltage, electrolyte concentration, and current can improve the efficiency of ECM for machining difficult alloys like Inconel 718.
Presentation of a fault tolerance algorithm for design of quantum-dot cellul...IJECEIAES
A novel algorithm for working out the Kink energy of quantum-dot cellular automata (QCA) circuits and their fault tolerability is introduced. In this algorithm at first with determining the input values on a specified design, the calculation between cells makes use of Kink physical relations will be managed. Therefore, the polarization of any cell and consequently output cell will be set. Then by determining missed cell(s) on the discussed circuit, the polarization of output cell will be obtained and by comparing it with safe state or software simulation, its fault tolerability will be proved. The proposed algorithm was implemented on a novel and advance fault tolerance full adder whose performance has been demonstrated. This algorithm could be implemented on any QCA circuit. Noticeably higher speed of the algorithm than simulation and traditional manual methods, expandability of this algorithm for variable circuits, beyond of four-dot square of QCA circuits, and the investigation of several damaged cells instead just one and special cell are the advantages of algorithmic action.
A review study of mechanical fatigue testing methods for small scale metal ma...Alexander Decker
This document reviews mechanical fatigue testing techniques for small-scale metal materials. It begins by discussing the increased focus on materials behavior at the micro and nano scales due to growing MEMS/NEMS applications. It then classifies fatigue testing techniques for small-scale materials, including uniaxial tension-tension, dynamic bending, and uniaxial tension-compression. Specific techniques are described in more detail, such as using piezoelectric actuators to enable load-controlled uniaxial cyclic loading of thin films. The document also examines fatigue properties of materials tested with these techniques, like studying crack growth rates in nickel alloy cantilever beams under dynamic bending.
Similar to Neural network modeling of agglomeration firing process for polymetallic ores (20)
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
Neural network optimizer of proportional-integral-differential controller par...IJECEIAES
Wide application of proportional-integral-differential (PID)-regulator in industry requires constant improvement of methods of its parameters adjustment. The paper deals with the issues of optimization of PID-regulator parameters with the use of neural network technology methods. A methodology for choosing the architecture (structure) of neural network optimizer is proposed, which consists in determining the number of layers, the number of neurons in each layer, as well as the form and type of activation function. Algorithms of neural network training based on the application of the method of minimizing the mismatch between the regulated value and the target value are developed. The method of back propagation of gradients is proposed to select the optimal training rate of neurons of the neural network. The neural network optimizer, which is a superstructure of the linear PID controller, allows increasing the regulation accuracy from 0.23 to 0.09, thus reducing the power consumption from 65% to 53%. The results of the conducted experiments allow us to conclude that the created neural superstructure may well become a prototype of an automatic voltage regulator (AVR)-type industrial controller for tuning the parameters of the PID controller.
An improved modulation technique suitable for a three level flying capacitor ...IJECEIAES
This research paper introduces an innovative modulation technique for controlling a 3-level flying capacitor multilevel inverter (FCMLI), aiming to streamline the modulation process in contrast to conventional methods. The proposed
simplified modulation technique paves the way for more straightforward and
efficient control of multilevel inverters, enabling their widespread adoption and
integration into modern power electronic systems. Through the amalgamation of
sinusoidal pulse width modulation (SPWM) with a high-frequency square wave
pulse, this controlling technique attains energy equilibrium across the coupling
capacitor. The modulation scheme incorporates a simplified switching pattern
and a decreased count of voltage references, thereby simplifying the control
algorithm.
A review on features and methods of potential fishing zoneIJECEIAES
This review focuses on the importance of identifying potential fishing zones in seawater for sustainable fishing practices. It explores features like sea surface temperature (SST) and sea surface height (SSH), along with classification methods such as classifiers. The features like SST, SSH, and different classifiers used to classify the data, have been figured out in this review study. This study underscores the importance of examining potential fishing zones using advanced analytical techniques. It thoroughly explores the methodologies employed by researchers, covering both past and current approaches. The examination centers on data characteristics and the application of classification algorithms for classification of potential fishing zones. Furthermore, the prediction of potential fishing zones relies significantly on the effectiveness of classification algorithms. Previous research has assessed the performance of models like support vector machines, naïve Bayes, and artificial neural networks (ANN). In the previous result, the results of support vector machine (SVM) were 97.6% more accurate than naive Bayes's 94.2% to classify test data for fisheries classification. By considering the recent works in this area, several recommendations for future works are presented to further improve the performance of the potential fishing zone models, which is important to the fisheries community.
Electrical signal interference minimization using appropriate core material f...IJECEIAES
As demand for smaller, quicker, and more powerful devices rises, Moore's law is strictly followed. The industry has worked hard to make little devices that boost productivity. The goal is to optimize device density. Scientists are reducing connection delays to improve circuit performance. This helped them understand three-dimensional integrated circuit (3D IC) concepts, which stack active devices and create vertical connections to diminish latency and lower interconnects. Electrical involvement is a big worry with 3D integrates circuits. Researchers have developed and tested through silicon via (TSV) and substrates to decrease electrical wave involvement. This study illustrates a novel noise coupling reduction method using several electrical involvement models. A 22% drop in electrical involvement from wave-carrying to victim TSVs introduces this new paradigm and improves system performance even at higher THz frequencies.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
Bibliometric analysis highlighting the role of women in addressing climate ch...IJECEIAES
Fossil fuel consumption increased quickly, contributing to climate change
that is evident in unusual flooding and draughts, and global warming. Over
the past ten years, women's involvement in society has grown dramatically,
and they succeeded in playing a noticeable role in reducing climate change.
A bibliometric analysis of data from the last ten years has been carried out to
examine the role of women in addressing the climate change. The analysis's
findings discussed the relevant to the sustainable development goals (SDGs),
particularly SDG 7 and SDG 13. The results considered contributions made
by women in the various sectors while taking geographic dispersion into
account. The bibliometric analysis delves into topics including women's
leadership in environmental groups, their involvement in policymaking, their
contributions to sustainable development projects, and the influence of
gender diversity on attempts to mitigate climate change. This study's results
highlight how women have influenced policies and actions related to climate
change, point out areas of research deficiency and recommendations on how
to increase role of the women in addressing the climate change and
achieving sustainability. To achieve more successful results, this initiative
aims to highlight the significance of gender equality and encourage
inclusivity in climate change decision-making processes.
Voltage and frequency control of microgrid in presence of micro-turbine inter...IJECEIAES
The active and reactive load changes have a significant impact on voltage
and frequency. In this paper, in order to stabilize the microgrid (MG) against
load variations in islanding mode, the active and reactive power of all
distributed generators (DGs), including energy storage (battery), diesel
generator, and micro-turbine, are controlled. The micro-turbine generator is
connected to MG through a three-phase to three-phase matrix converter, and
the droop control method is applied for controlling the voltage and
frequency of MG. In addition, a method is introduced for voltage and
frequency control of micro-turbines in the transition state from gridconnected mode to islanding mode. A novel switching strategy of the matrix
converter is used for converting the high-frequency output voltage of the
micro-turbine to the grid-side frequency of the utility system. Moreover,
using the switching strategy, the low-order harmonics in the output current
and voltage are not produced, and consequently, the size of the output filter
would be reduced. In fact, the suggested control strategy is load-independent
and has no frequency conversion restrictions. The proposed approach for
voltage and frequency regulation demonstrates exceptional performance and
favorable response across various load alteration scenarios. The suggested
strategy is examined in several scenarios in the MG test systems, and the
simulation results are addressed.
Enhancing battery system identification: nonlinear autoregressive modeling fo...IJECEIAES
Precisely characterizing Li-ion batteries is essential for optimizing their
performance, enhancing safety, and prolonging their lifespan across various
applications, such as electric vehicles and renewable energy systems. This
article introduces an innovative nonlinear methodology for system
identification of a Li-ion battery, employing a nonlinear autoregressive with
exogenous inputs (NARX) model. The proposed approach integrates the
benefits of nonlinear modeling with the adaptability of the NARX structure,
facilitating a more comprehensive representation of the intricate
electrochemical processes within the battery. Experimental data collected
from a Li-ion battery operating under diverse scenarios are employed to
validate the effectiveness of the proposed methodology. The identified
NARX model exhibits superior accuracy in predicting the battery's behavior
compared to traditional linear models. This study underscores the
importance of accounting for nonlinearities in battery modeling, providing
insights into the intricate relationships between state-of-charge, voltage, and
current under dynamic conditions.
Smart grid deployment: from a bibliometric analysis to a surveyIJECEIAES
Smart grids are one of the last decades' innovations in electrical energy.
They bring relevant advantages compared to the traditional grid and
significant interest from the research community. Assessing the field's
evolution is essential to propose guidelines for facing new and future smart
grid challenges. In addition, knowing the main technologies involved in the
deployment of smart grids (SGs) is important to highlight possible
shortcomings that can be mitigated by developing new tools. This paper
contributes to the research trends mentioned above by focusing on two
objectives. First, a bibliometric analysis is presented to give an overview of
the current research level about smart grid deployment. Second, a survey of
the main technological approaches used for smart grid implementation and
their contributions are highlighted. To that effect, we searched the Web of
Science (WoS), and the Scopus databases. We obtained 5,663 documents
from WoS and 7,215 from Scopus on smart grid implementation or
deployment. With the extraction limitation in the Scopus database, 5,872 of
the 7,215 documents were extracted using a multi-step process. These two
datasets have been analyzed using a bibliometric tool called bibliometrix.
The main outputs are presented with some recommendations for future
research.
Use of analytical hierarchy process for selecting and prioritizing islanding ...IJECEIAES
One of the problems that are associated to power systems is islanding
condition, which must be rapidly and properly detected to prevent any
negative consequences on the system's protection, stability, and security.
This paper offers a thorough overview of several islanding detection
strategies, which are divided into two categories: classic approaches,
including local and remote approaches, and modern techniques, including
techniques based on signal processing and computational intelligence.
Additionally, each approach is compared and assessed based on several
factors, including implementation costs, non-detected zones, declining
power quality, and response times using the analytical hierarchy process
(AHP). The multi-criteria decision-making analysis shows that the overall
weight of passive methods (24.7%), active methods (7.8%), hybrid methods
(5.6%), remote methods (14.5%), signal processing-based methods (26.6%),
and computational intelligent-based methods (20.8%) based on the
comparison of all criteria together. Thus, it can be seen from the total weight
that hybrid approaches are the least suitable to be chosen, while signal
processing-based methods are the most appropriate islanding detection
method to be selected and implemented in power system with respect to the
aforementioned factors. Using Expert Choice software, the proposed
hierarchy model is studied and examined.
Enhancing of single-stage grid-connected photovoltaic system using fuzzy logi...IJECEIAES
The power generated by photovoltaic (PV) systems is influenced by
environmental factors. This variability hampers the control and utilization of
solar cells' peak output. In this study, a single-stage grid-connected PV
system is designed to enhance power quality. Our approach employs fuzzy
logic in the direct power control (DPC) of a three-phase voltage source
inverter (VSI), enabling seamless integration of the PV connected to the
grid. Additionally, a fuzzy logic-based maximum power point tracking
(MPPT) controller is adopted, which outperforms traditional methods like
incremental conductance (INC) in enhancing solar cell efficiency and
minimizing the response time. Moreover, the inverter's real-time active and
reactive power is directly managed to achieve a unity power factor (UPF).
The system's performance is assessed through MATLAB/Simulink
implementation, showing marked improvement over conventional methods,
particularly in steady-state and varying weather conditions. For solar
irradiances of 500 and 1,000 W/m2
, the results show that the proposed
method reduces the total harmonic distortion (THD) of the injected current
to the grid by approximately 46% and 38% compared to conventional
methods, respectively. Furthermore, we compare the simulation results with
IEEE standards to evaluate the system's grid compatibility.
Enhancing photovoltaic system maximum power point tracking with fuzzy logic-b...IJECEIAES
Photovoltaic systems have emerged as a promising energy resource that
caters to the future needs of society, owing to their renewable, inexhaustible,
and cost-free nature. The power output of these systems relies on solar cell
radiation and temperature. In order to mitigate the dependence on
atmospheric conditions and enhance power tracking, a conventional
approach has been improved by integrating various methods. To optimize
the generation of electricity from solar systems, the maximum power point
tracking (MPPT) technique is employed. To overcome limitations such as
steady-state voltage oscillations and improve transient response, two
traditional MPPT methods, namely fuzzy logic controller (FLC) and perturb
and observe (P&O), have been modified. This research paper aims to
simulate and validate the step size of the proposed modified P&O and FLC
techniques within the MPPT algorithm using MATLAB/Simulink for
efficient power tracking in photovoltaic systems.
Adaptive synchronous sliding control for a robot manipulator based on neural ...IJECEIAES
Robot manipulators have become important equipment in production lines, medical fields, and transportation. Improving the quality of trajectory tracking for
robot hands is always an attractive topic in the research community. This is a
challenging problem because robot manipulators are complex nonlinear systems
and are often subject to fluctuations in loads and external disturbances. This
article proposes an adaptive synchronous sliding control scheme to improve trajectory tracking performance for a robot manipulator. The proposed controller
ensures that the positions of the joints track the desired trajectory, synchronize
the errors, and significantly reduces chattering. First, the synchronous tracking
errors and synchronous sliding surfaces are presented. Second, the synchronous
tracking error dynamics are determined. Third, a robust adaptive control law is
designed,the unknown components of the model are estimated online by the neural network, and the parameters of the switching elements are selected by fuzzy
logic. The built algorithm ensures that the tracking and approximation errors
are ultimately uniformly bounded (UUB). Finally, the effectiveness of the constructed algorithm is demonstrated through simulation and experimental results.
Simulation and experimental results show that the proposed controller is effective with small synchronous tracking errors, and the chattering phenomenon is
significantly reduced.
Remote field-programmable gate array laboratory for signal acquisition and de...IJECEIAES
A remote laboratory utilizing field-programmable gate array (FPGA) technologies enhances students’ learning experience anywhere and anytime in embedded system design. Existing remote laboratories prioritize hardware access and visual feedback for observing board behavior after programming, neglecting comprehensive debugging tools to resolve errors that require internal signal acquisition. This paper proposes a novel remote embeddedsystem design approach targeting FPGA technologies that are fully interactive via a web-based platform. Our solution provides FPGA board access and debugging capabilities beyond the visual feedback provided by existing remote laboratories. We implemented a lab module that allows users to seamlessly incorporate into their FPGA design. The module minimizes hardware resource utilization while enabling the acquisition of a large number of data samples from the signal during the experiments by adaptively compressing the signal prior to data transmission. The results demonstrate an average compression ratio of 2.90 across three benchmark signals, indicating efficient signal acquisition and effective debugging and analysis. This method allows users to acquire more data samples than conventional methods. The proposed lab allows students to remotely test and debug their designs, bridging the gap between theory and practice in embedded system design.
Detecting and resolving feature envy through automated machine learning and m...IJECEIAES
Efficiently identifying and resolving code smells enhances software project quality. This paper presents a novel solution, utilizing automated machine learning (AutoML) techniques, to detect code smells and apply move method refactoring. By evaluating code metrics before and after refactoring, we assessed its impact on coupling, complexity, and cohesion. Key contributions of this research include a unique dataset for code smell classification and the development of models using AutoGluon for optimal performance. Furthermore, the study identifies the top 20 influential features in classifying feature envy, a well-known code smell, stemming from excessive reliance on external classes. We also explored how move method refactoring addresses feature envy, revealing reduced coupling and complexity, and improved cohesion, ultimately enhancing code quality. In summary, this research offers an empirical, data-driven approach, integrating AutoML and move method refactoring to optimize software project quality. Insights gained shed light on the benefits of refactoring on code quality and the significance of specific features in detecting feature envy. Future research can expand to explore additional refactoring techniques and a broader range of code metrics, advancing software engineering practices and standards.
Smart monitoring technique for solar cell systems using internet of things ba...IJECEIAES
Rapidly and remotely monitoring and receiving the solar cell systems status parameters, solar irradiance, temperature, and humidity, are critical issues in enhancement their efficiency. Hence, in the present article an improved smart prototype of internet of things (IoT) technique based on embedded system through NodeMCU ESP8266 (ESP-12E) was carried out experimentally. Three different regions at Egypt; Luxor, Cairo, and El-Beheira cities were chosen to study their solar irradiance profile, temperature, and humidity by the proposed IoT system. The monitoring data of solar irradiance, temperature, and humidity were live visualized directly by Ubidots through hypertext transfer protocol (HTTP) protocol. The measured solar power radiation in Luxor, Cairo, and El-Beheira ranged between 216-1000, 245-958, and 187-692 W/m 2 respectively during the solar day. The accuracy and rapidity of obtaining monitoring results using the proposed IoT system made it a strong candidate for application in monitoring solar cell systems. On the other hand, the obtained solar power radiation results of the three considered regions strongly candidate Luxor and Cairo as suitable places to build up a solar cells system station rather than El-Beheira.
An efficient security framework for intrusion detection and prevention in int...IJECEIAES
Over the past few years, the internet of things (IoT) has advanced to connect billions of smart devices to improve quality of life. However, anomalies or malicious intrusions pose several security loopholes, leading to performance degradation and threat to data security in IoT operations. Thereby, IoT security systems must keep an eye on and restrict unwanted events from occurring in the IoT network. Recently, various technical solutions based on machine learning (ML) models have been derived towards identifying and restricting unwanted events in IoT. However, most ML-based approaches are prone to miss-classification due to inappropriate feature selection. Additionally, most ML approaches applied to intrusion detection and prevention consider supervised learning, which requires a large amount of labeled data to be trained. Consequently, such complex datasets are impossible to source in a large network like IoT. To address this problem, this proposed study introduces an efficient learning mechanism to strengthen the IoT security aspects. The proposed algorithm incorporates supervised and unsupervised approaches to improve the learning models for intrusion detection and mitigation. Compared with the related works, the experimental outcome shows that the model performs well in a benchmark dataset. It accomplishes an improved detection accuracy of approximately 99.21%.
Low power architecture of logic gates using adiabatic techniquesnooriasukmaningtyas
The growing significance of portable systems to limit power consumption in ultra-large-scale-integration chips of very high density, has recently led to rapid and inventive progresses in low-power design. The most effective technique is adiabatic logic circuit design in energy-efficient hardware. This paper presents two adiabatic approaches for the design of low power circuits, modified positive feedback adiabatic logic (modified PFAL) and the other is direct current diode based positive feedback adiabatic logic (DC-DB PFAL). Logic gates are the preliminary components in any digital circuit design. By improving the performance of basic gates, one can improvise the whole system performance. In this paper proposed circuit design of the low power architecture of OR/NOR, AND/NAND, and XOR/XNOR gates are presented using the said approaches and their results are analyzed for powerdissipation, delay, power-delay-product and rise time and compared with the other adiabatic techniques along with the conventional complementary metal oxide semiconductor (CMOS) designs reported in the literature. It has been found that the designs with DC-DB PFAL technique outperform with the percentage improvement of 65% for NOR gate and 7% for NAND gate and 34% for XNOR gate over the modified PFAL techniques at 10 MHz respectively.
Hierarchical Digital Twin of a Naval Power SystemKerry Sado
A hierarchical digital twin of a Naval DC power system has been developed and experimentally verified. Similar to other state-of-the-art digital twins, this technology creates a digital replica of the physical system executed in real-time or faster, which can modify hardware controls. However, its advantage stems from distributing computational efforts by utilizing a hierarchical structure composed of lower-level digital twin blocks and a higher-level system digital twin. Each digital twin block is associated with a physical subsystem of the hardware and communicates with a singular system digital twin, which creates a system-level response. By extracting information from each level of the hierarchy, power system controls of the hardware were reconfigured autonomously. This hierarchical digital twin development offers several advantages over other digital twins, particularly in the field of naval power systems. The hierarchical structure allows for greater computational efficiency and scalability while the ability to autonomously reconfigure hardware controls offers increased flexibility and responsiveness. The hierarchical decomposition and models utilized were well aligned with the physical twin, as indicated by the maximum deviations between the developed digital twin hierarchy and the hardware.
Literature Review Basics and Understanding Reference Management.pptxDr Ramhari Poudyal
Three-day training on academic research focuses on analytical tools at United Technical College, supported by the University Grant Commission, Nepal. 24-26 May 2024
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELgerogepatton
As digital technology becomes more deeply embedded in power systems, protecting the communication
networks of Smart Grids (SG) has emerged as a critical concern. Distributed Network Protocol 3 (DNP3)
represents a multi-tiered application layer protocol extensively utilized in Supervisory Control and Data
Acquisition (SCADA)-based smart grids to facilitate real-time data gathering and control functionalities.
Robust Intrusion Detection Systems (IDS) are necessary for early threat detection and mitigation because
of the interconnection of these networks, which makes them vulnerable to a variety of cyberattacks. To
solve this issue, this paper develops a hybrid Deep Learning (DL) model specifically designed for intrusion
detection in smart grids. The proposed approach is a combination of the Convolutional Neural Network
(CNN) and the Long-Short-Term Memory algorithms (LSTM). We employed a recent intrusion detection
dataset (DNP3), which focuses on unauthorized commands and Denial of Service (DoS) cyberattacks, to
train and test our model. The results of our experiments show that our CNN-LSTM method is much better
at finding smart grid intrusions than other deep learning algorithms used for classification. In addition,
our proposed approach improves accuracy, precision, recall, and F1 score, achieving a high detection
accuracy rate of 99.50%.
HEAP SORT ILLUSTRATED WITH HEAPIFY, BUILD HEAP FOR DYNAMIC ARRAYS.
Heap sort is a comparison-based sorting technique based on Binary Heap data structure. It is similar to the selection sort where we first find the minimum element and place the minimum element at the beginning. Repeat the same process for the remaining elements.
Neural network modeling of agglomeration firing process for polymetallic ores
1. International Journal of Electrical and Computer Engineering (IJECE)
Vol. 12, No. 4, August 2022, pp. 4352~4363
ISSN: 2088-8708, DOI: 10.11591/ijece.v12i4.pp4352-4363 4352
Journal homepage: http://ijece.iaescore.com
Neural network modeling of agglomeration firing process for
polymetallic ores
Gulnara Abitova1
, Vladimir Nikulin2
, Leila Rzayeva3
, Tansuly Zadenova3
, Ali Myrzatay3
1
Department of Intelligent Systems and Cybersecurity, Astana IT University, Nur-Sultan, Kazakhstan
2
Department of Electrical Engineering and Computer Sciences, Binghamton University, Binghamton, USA
3
Department of Systems Analysis and Control, L.N. Gumilyov Eurasian National University, Nur-Sultan, Kazakhstan
Article Info ABSTRACT
Article history:
Received Jun 29, 2021
Revised Dec 30, 2021
Accepted Jan 10, 2022
While processing polymetallic ores at the non-ferrous metallurgy problems
arises connecting with the excellence of production and the efficient
applying the technological devices-firing furnace and crusher machine. In
earlier time, similar questions were solved due to the big practice
experiences and using a mathematical modeling method. The mathematical
model for optimizing those operating mode is a very complex and hard to
calculation. Performing computations is needed too much time and many
resources. Because the control of the agglomeration furnaces and other
machines are including complex multiparameter processes. The method of
the math modeling for optimization the operating mode to the firing furnace
is replaced with modeling based on the neural network that is here a new
method. The results obtained have shown that proposed methods based on
the neural network modeling of metallurgical processes allow determining
more accurate and adequate results of calculations than mathematical
modeling by the traditional program. The use of new approaches for
modeling the technological processes at the non-ferrous metallurgy gives
opportunity to enhance an effectiveness of production excellence and to
enhance an efficient applying the heat-energy equipment while a firing the
sulfide polymetallic ores of non-ferrous metallurgy.
Keywords:
Automatic control
Industry production
Mathematical modeling
Neural network
Optimization mode
This is an open access article under the CC BY-SA license.
Corresponding Author:
Gulnara Abitova
Department of Intelligent Systems and Cybersecurity, Astana IT University
Nur-Sultan, 010000-Kazakhstan
Email: gulnara.abitova@astanait.edu.kz, abitova.gul@gmail.com
1. INTRODUCTION
Background of research is presented to us the actuality of this study that demonstrated in the
following works and investigations. As known the neural networks are the present trends for designing of
automation with using artificial intelligence (AI) systems, in particularly in the fields of effective operating,
optimizing control for manufactory production and business. Within transferring to Industry 4.0 and
implementation of the digital technologies in the whole spheres of economics and society the use of neural
network technologies is promising ways to optimize the operating modes of technological equipment as well
as the innovative development methods of the effective automation control systems for the complex
technological processes.
One of the promising areas of application of artificial neural networks tools is the modeling of
complex technological processes in the metallurgical manufactories of the mining and metallurgical complex.
For this industry and scientific field of research, the use of methods of mathematical modeling is a widely
applied approach for control optimization and making high-quality decisions for decreasing the maintenance
2. Int J Elec & Comp Eng ISSN: 2088-8708
Neural network modeling of agglomeration firing process for … (Gulnara Abitova)
4353
cost of the technological equipment and self-cost of the production. At the same time, the use of the
mathematical models of technological processes is an important tool and an effective method for studying the
influence of technology on the final product properties with the appropriate quality.
Nowadays, in the non-ferrous metallurgy while the processing of the sulfide polymetallic ores there
are often problems connecting with the quality of the decisions made in the operation and control of the
equipment as well as connecting with adequate modeling of technological processes. Because, the decision-
making of operation work is mainly dependent on an understanding of the complex chemical-physical
processes and multicomponent reactions occurring inside agglomeration equipment, as well as of complexity
of calculation and accuracy of results of mathematical modeling.
The problem of statements of the research is given below. Usually, mathematical models of
metallurgical processes are often simplified and limited to certain assumptions. As a rule, those models are
created on the basis of differential equations and integrating-differential equations, and several
approximations. Actually, these simplicities are dependent on many factors, in particular, multi-component
ness and high-temperature chemical reactions while the agglomeration firing of the sulfide polymetallic ores.
Therefore, the problem of statements of the research is to study and to find a new methods and approaches to
the mathematical modeling and optimization of complex technological processes while the processing of
polymetallic ores in the non-ferrous production.
The effectiveness of the applied tools for controlling a production technology and a product quality,
first, is determined by the accuracy and adequacy of the synthesized models of the technological process. The
approximated mathematical models that are linearized in control parameters are not always sufficient and
suitable to adequately reproduce the features of continuous technological processes in the lead-zinc
production while the processing of polymetallic ores [1]. The practical developments in the use of neural
networks for modeling the various kinds of engineering systems in the other economic areas show that they
can be used for the metallurgy plants too. Because, they are devoid of several shortcomings which
mathematical models have and allow to solve industry optimization problems of any complexity [2], [3].
It is important that while modeling the technological process of agglomeration firing of the sulfide
polymetallic ores it is necessary to pay attention to the multiple information and functional dependencies
between the production technology and the properties (quality indicators) of the resulting final product.
Existing research and practical works are not given good examples of developing and using a neural network
to simulation and designing a manufactory process at the metallurgical non-ferrous productions. But a
flexibility of neural network models supposes to apply them to simulate a processing and firing the sulfide
polymetallic ores in the non-ferrous metallurgy [4]–[6]. Applying an artificial intelligent system for modeling
the manufactory production at non-ferrous metallurgy will provide the efficiency enhancing of the production
excellence, as well as the efficiency of an automation system to the agglomeration firing of sulfide
polymetallic ores.
In this manner this study is proposed the new approach to the modeling of continuous technological
processes in the lead-zinc production based on the neural networks. Using this approach there were created a
neural network-based models for the processing of polymetallic ores that had provided more accurate results
and adequate calculations than mathematical programs. In the same time, it provided to decrease the self-cost
of the final products, and also increase the energy effectiveness of the heat-energy equipment operation by
optimizing the operating mode.
The relevant literature review is shows us the following situation. The considering study questions
and relevant problems presented in this work are investigated and by many modern researchers and practices
of industry nowadays. Because artificial neural networks are a convenient and effective tool for representing
the information models and their functional defending [7]. In the metallurgical industry, the problem of
implementing a novel approaches and techniques is interesting, which can speed up investigations to get a
coming metal product, to refine an excellence of the final production, as well as to reduce self-cost [8].
Traditional methods of searching for the composition of new alloys with the required properties are
include repeated smelting of prototypes and complex mathematical processing of the results. However, with
different content of impurities in the concentrate, the number of necessary industry experiments also is
increased. The complex physical-chemical compound of metals while the processing is very strong influence
on the changing of the material properties. Therefore, there are complex dependencies between the
concentration of metals in the ores, the operating modes of firing, and test conditions in the firing process. In
this manner, the opportunity to select the strict mathematical relationship between the compound and
characteristics may become impossible and hard. Because of this, the ability to obtain the most promising
alloys and metal quality can be complex and difficult to manage [3].
The creation of neural network expert systems is applied to solve a direct problem-predicting the
properties of non-ferrous metal alloys by their chemical composition. To solve the inverse problem, the
issuance of recommendations on the chemical composition is used, depending on the set of required
parameters (taking into account the cost). All this makes it possible to drastically simplify scientific research
3. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 12, No. 4, August 2022: 4352-4363
4354
and come up with the creation of new complex materials based on innovative technologies necessary for the
development of modern technologies of the 21st century [2].
A plethora of latest research are aimed to investigation of neural network algorithms, and it is
applying to the manufactory equipment. At the same time, there are many studies on the modeling a thermal
operation of industrial furnaces in industrial production to ensure the tasks of optimization of control,
forecasting, as well as for automated control of energy consumption. Therefore, the work [4] is to consider
the problems of designing, training the artificial intelligent systems which design a heat-energy operating to
the firing process at the industry manufactory. The artificial intelligent systems can be used both in solving
optimization problems and designing automatic control systems.
Neurocomputers are also actively used in energy systems. Last time, the neural network approach
has been actively integrated in the tasks of predicting the load of energy and gas consumption [9]. In another
study is given a group approach. Here are considering a learning fundamental of the statistical model. This
way is helping to forecast the short-term energy expense of a multi house living building [10]. Other
approaches are proposed in the work [11], where the investigators proposed a class deep opinion network to
forecast energy expense. Here is considered a method that based on the various data and time sets.
In [12], researchers suggested the new learning structure to increase a forecast correctness of
short-term energy load. Similarly, in [13], [14], investigators given another forecasting ways. The
considering structure is a group of forecasting models called sisters. They have the alike structures but a
picking process of data here is various. In [15], [16] have studied a novel approach based on an evolutionary
algorithm to forecast small capacity. The developed mixed circuit allows optimum indicators regulation for
neural networks, that increasing training and forecasting. Similarly, in [17], [18] are considered factors and
initial data used in forecasting the loads on power systems and predict peak electricity consumption.
At the same time, extensive experience has been accumulated in the field of use in quality control in
the industry. For example, the neural network used at Intel enterprises to detect defects in the manufacture of
chips is a way of rejecting a defective chip with an accuracy of 99.5% [5]. The neural network developed by
Mark Waller of Shanghai University specializes in the development of synthetic molecules [19]. Yandex data
factory tools help in steel smelting: the scrap metal used for steel production is often heterogeneous in
composition. According to Yandex, the introduction of neural networks can reduce the cost of expensive
ferroalloys by 5% [20]. A neural network can help for lane detection is proposed using a convolutional neural
network (CNN). Proposed approach provides it to use in assistive robotic systems. The use of machine
learning technologies in this field will significantly reduce costs [21].
This work showes that a deep transfer learning is feasible to detect coronavirus disease (COVID-19)
disease automatically from chest X-ray. This approach is sudgessed a training the learning model with chest
X-ray images that is presented mixed with COVID-19 patients, other pneumonia affected patients and people
with healthy lungs. [22]. Currently, leading oil and gas companies in various fields are already actively using
neural networks. For example, the authors of paper [23] analyzed the global trends of digital technologies’
introduction into the oil and gas mining industry. Gazprom Neft, in its project, implemented the concept of
“artificial intelligence” -a digital geological model. Processing and interpretation of seismic and exploration
drilling data are six times faster and three times more accurate. Nest lab is one of the developers of a digital
robotic complex capable of training and optimizing production processes. The combination of simplified
physical models and neural network algorithms made it possible to present on the market a product capable
not only of automating processes but also of providing operational solutions for managing well regimes. The
testing of the “robot program” at the fields of LUKOIL and Gazprom Neft allowed us to achieve significant
results [24].
An example of the development and implementation of neural networks in the oil industry is the
silicon valley company Tachyus, which combined classical physics and machine learning. The efficiency of
field operations, according to the reports of the company’s representatives, is up to 20% in mature fields. One
of the most striking examples of testing neural network modeling technology developed by Tachyus is one of
the large deposits in the Gulf of San Jorge (Argentina). The use of machine learning algorithms allows you to
choose the optimal distribution of injection wells corresponding to a limited number of injection distribution
options to achieve maximum oil production. So, on the example of the Zapadno-Malobalykskoye field in
Kazakhstan, most solutions to the optimization problem provide the current daily production. Simply put,
most randomly selected options for the distribution of infectivity of injection wells will allow achieving the
current performance of production wells. Neural network algorithms reveal the possibility of creating the
necessary conditions that will allow you to realize the full potential of the development system [25].
A review of the other economic and production areas shows that there is a wide range of neural
networks applications and artificial intelligence used for the control, automation, and optimization of the
processes and plants in the different areas of control. For example, in the work [26] an encode-decode
Seg-Net system via deep learning network incorporated with VGG16 has been proposed in order to identify
4. Int J Elec & Comp Eng ISSN: 2088-8708
Neural network modeling of agglomeration firing process for … (Gulnara Abitova)
4355
the lane markings on distinct environmental effects. Also, there is a recent work on the development of
COVID-19 detection system by a transfer deep learning approach where the state-of-the-art CNN models
have been used. The related to coronavirus studies were in the work [27] where a new CNN model has been
proposed in order to detect COVID-19 based on X-ray images.
Other work [28] investigates the method for an accurate estimation of solar radiation in Indonesia
via a new two-step artificial neural network (ANN). Another paper [6] is demonstated a comparative
framework where a suite of long short-term memory (LSTM) recurrent neural networks (RNN) models are
implemented to address the existing gaps and limitations of reported wind power forecasting methodologies.
Similarly, Salam et al. [29] proposed in his research the hybrid SVM-ANN net model. The performance of
support vector machine (SVM), ANN, SVM with reduced features, and hybrid SVM-ANN model in the
detection of breast cancer have been compared.
Recently published papers of other authors have proposed the use ANNs as an intelligent control
strategy for a microgrid energy management system [30]. Similarly, another paper gives the analysis of the
performance of the multilayer neural networks with respect to the different activation functions for the
purposes of prediction of the production and consumption of electric power [31]. In the other work is
investigated the method for the short-term wind speed forecasting system via a deep learning algorithm with
applications to wind turbines [32], [33].
Thus, there are many methods for determining the accuracy of mathematical models associated with
the energy performance of industrial plants and other industrial production. However, in the non-ferrous
production the indicated above methods are not applied. Because there are not found a general-purpose
method yet for their application for modeling complex processes for processing and agglomeration firing of
multicomponent polymetallic sulfide ores. This analysis supports the relevance of our study within the
development of Industry 4.0.
The new value of Research is shown by the next outcomes. The recent development of neural
network technologies can provide the creation of an appropriate technologies and approaches to getting the
correctness of mathematical systems for automating manufactory equipment. They can be used to make an
optimization of the energy expenses of the firing equipment in the lead-zinc production. In this paper, it is
proposed the use of neural network technologies for calculating and modeling an agglomeration furnace and
crusher machine to increase their efficiency and to reduce production cost. So, this research is proposed the
new method is based on the process modeling based on neural networks. In the same time, here is provides a
new approach to the optimization of the operation mode and of the control systems for complex
multi-component processes in the lead-zinc production, which proves the new value of research. Nowadays
there are no proposed methods and approaches in the existing works that are applicable to the technological
processes in the metallurgical manufactory for the processing of polymetallic ores.
2. RESEARCH METHOD
This part considers the applying research methods. In the first section, it is given explanation of the
proposed methodology of the research problem. The second section is presented a description of the
mathematical model and algorithm for calculating the firing process. The third section is demonstrated a
description of optimization model of the operation mode for the technological equipment.
2.1. Methodology of the research problem
The research technique of this work involves the use of modern approaches on process optimization
such as neural network modeling and mathematical modeling as well as numerical methods and analytical
calculations of the obtained results. Also, a method of statistical analysis for decision making and using it
while the learning process of neural network models is used in this research work. It is very important to take
appropriate mathematical models that reflect the operation of the agglomeration furnace and associated
technological equipment. It is given opportunity to make an acceptable choice of the firing equipment. In this
matter, the mathematical models used for these goals in the form of computer programs have a complex
structure, large volumes, and take a significant amount of time for calculations process.
In this case, using the neural networks technologies for determine an accuracy result obtained when
solving heat and energy transfer problems using multi-purpose computing systems is the one best way to
solve these kinds of problems. In this work, the methods of modeling are used to solve the optimization of
the operating modes of the agglomeration furnace and crusher machine on a firing expense to the burner,
energy to a grinder process. In order to define the dependence between the working mode of the firing
equipment and grinder machine, a method of determining the dependencies of studied parameters is used. For
example, the determination of the dependencies of the influence of changing of the generalized size of
polymetallic ores and the parameters of the heating on the time of agglomerating firing.
5. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 12, No. 4, August 2022: 4352-4363
4356
2.2. Description of the mathematical model and algorithm for calculating the firing process
The sample is designed for a firing furnace working in a fixed mode. The stationary heating flow in
the loaded furnace charge should be propose equal to the quantity of heat energy transmitted from the gases
to the loaded charge under the convection. Let us assume that the gas volume in the working space of the
furnace is isothermal. As far as, the process of loading and unloading the metal charge is continuous, the
temperature over all hot area of the metal charge is currently invariable [28].
The math sample is based on the solving of the conjugate question of heat transfer in the
gas-charge-agglomerate system. The method of discrete performance of border conditions was taken as a
mathematical method of modeling [28], [29]. In Figure 1 is presented the algorithm for solving the studied
optimization problem which includes 9 stages. This algorithm provides the calculating the specific
consumption of air supplied for the firing and the lowest heat combustion of the fuel for the process. It is
given the opportunity to determine the specific outputs and the percentage of combustion products. The
realization of this algorithm is made by a set of special computer programs [29], [30].
Figure 1. Algorithm of solving the optimization problems and calculating
2.3. Description of optimization model of the operation mode for the technological equipment
Choosing the objective function and operating parameters of the model. For designing an
optimization model, it is needed to choose the objective function and parameters of variating for this model.
The general-purpose economic argument (the production cost) is one of the appropriate as an objective
function to optimize the operating mode of firing furnace. The production cost consists of two types of costs:
direct and indirect. Direct costs are divided into basic materials and semi-finished products costs, basic and
additional wages. Indirect costs are divided into conditionally variable (proportional) and conditionally fixed
expenses [30], [31].
The production costs (𝑆𝑝.𝑐.) (tg/y) are set for a year and relate mainly to conditionally fixed costs and
are determined by the following (1), where 𝑆𝑐.𝑚.𝑚.-costs of manufactory management, tg/y; 𝑆𝑐.𝑜.𝑝.-costs of
other personal, tg/y; 𝑆𝑎.𝑐.𝑏.-costs of buildings and construction, tg/y; 𝑆𝑐.𝑏.𝑐.-costs of maintaining buildings and
construction, tg/y; 𝑆𝑒𝑥.𝑟.𝑏.-expenses for current repairs of buildings, tg/y; 𝑆𝑐.𝑡.𝑒.𝑟.-costs for testing,
experiments, and research, tg/y; 𝑆𝑐.𝑙𝑝.𝑠.𝑜. -costs of labor protection, and safety, tg/y; 𝑆𝑐.𝑙𝑣.𝑡.-the cost of
low-value tools, tg/y.
𝑆𝑝.𝑐. = 𝑆𝑐.𝑚.𝑚. + 𝑆𝑐.𝑜.𝑝. + 𝑆𝑎.𝑐.𝑏. + 𝑆𝑐.𝑚.𝑏. + 𝑆𝑐.𝑏.𝑐. + 𝑆𝑒𝑥.𝑟.𝑏. + 𝑆𝑐.𝑡.𝑏.𝑟. + 𝑆𝑐.𝑙𝑝.𝑠.𝑜. + 𝑆𝑐.𝑙𝑣.𝑡. (1)
Here the production cost (or self-cost of the product) is the main function of the optimization model for the
operating mode.
6. Int J Elec & Comp Eng ISSN: 2088-8708
Neural network modeling of agglomeration firing process for … (Gulnara Abitova)
4357
The costs of maintaining and operating equipment (𝑆𝑐.𝑚.𝑜.𝑒𝑞.) related to conditionally variable costs
are determined by the formula (2), tg/y, where 𝑆𝑐.𝑎.𝑒𝑞.-the cost of amortization of equipment, transport, and
tools, tg/y; 𝑆𝑐.𝑎𝑑.𝑚.-costs for additional materials, oils, and etc., tg/y; 𝑆𝑒.𝑐.𝑒𝑞.-energy costs spent to equipment
operation, tg/y; 𝑆𝑠.𝑠.𝑝.-salary of personal servicing the equipment, tg/y; 𝑆𝑒𝑥.𝑚.𝑟.-expenses for maintenance and
repair of equipment, tg/y; 𝑆𝑐.𝑡.𝑠.-costs for transportation services, tg/y; 𝑆𝑐.𝑤.𝑒𝑞.-the cost of wear low-value
equipment, tg/y; 𝑆𝑜.𝑐.𝑜.𝑚.-other costs associated with the operation and maintenance of equipment, tg/y.
𝑆𝑐.𝑚.𝑜.𝑒𝑞. = 𝑆𝑐.𝑎.𝑒𝑞. + 𝑆𝑐.𝑎𝑑.𝑚. + 𝑆𝑒.𝑐..𝑒𝑞. + 𝑆𝑠.𝑠.𝑝. + 𝑆𝑒𝑥.𝑚.𝑟. + 𝑆𝑐.𝑡.𝑠. + 𝑆𝑐.𝑤.𝑒𝑞. + 𝑆𝑜.𝑐.𝑜.𝑚. (2)
Thus, the self-cost of the manufactory production is determined by the (3), where 𝑆𝑠.𝑚.𝑝. is the salary of the
main workers for processing of 1 kg of the i-th type of product, tg/kg.
𝑆𝑠𝑐.𝑚.𝑝. = 𝑆𝑠𝑐.𝑖𝑑.𝑒𝑥.+𝑆𝑠.𝑚.𝑝. (3)
Therefore, the optimization parameter while selecting the operating mode of the equipment for the
agglomeration firing process is the minimum of the production self-cost. The parameters of operating mode
(parameters of the quality of agglomeration) are taken as variable parameters in the model: a temperature on
the surface T (1, FoK) and a temperature difference at the end of firing T1−0 (FoK), as well as the parameter
associated with the placement of pallets in the agglomeration furnace (Rm).
Selecting restrictions of the mathematical model and facilitation a number experiment. It is hard to
apply the above algorithm to define the optimal working data based on a recitation of versions because the
quantity of such calculations is huge. In this manner, the technique is applied, that is presented a set up a
computational experiment. This algorithm provides information where an objective function will be changing
depending on the various working data sets [1], [32].
To define those a dependency, it is needed to well install the intervals of modification of the
operating data. The limits of the various intervals are defined using the following requirements: i) the range
of variation of the last firing temperature on the surface, is in the range at which firing cannot be executed
and to the melting point of the metal and ii) the acceptable temperature difference at the end of the metal
firing is 5-10 С (the range of variation). In practice, it is advisable to reduce this range somewhat by setting
it in the range from 35 to 170 С. The required dependency and equation of mathematical modeling y = f (x1,
x2, x3) is presented in the next form (4), where y is an optimization parameter; x1, x2, x3 -variable parameters;
bi,-coefficients.
𝑦 = 𝑏1 + 𝑏2 ∗ 𝑥1 + 𝑏3 ∗ 𝑥2 + 𝑏4 ∗ 𝑥3 + 𝑏5 ∗ 𝑥1 ∗ 𝑥2 + 𝑏6 ∗ 𝑥1 ∗ 𝑥3
+𝑏7 ∗ 𝑥2 ∗ 𝑥3 + 𝑏8 ∗ 𝑥1
2
+ 𝑏9 ∗ 𝑥2
2
+ 𝑏10 ∗ 𝑥3
2
(4)
In order to find the coefficients bi, a second-order orthogonal planning matrix for a computational
experiment is constructed for three factors x1, x2, x3. On the basis of a computational experiment using the
planning matrix, the coefficients bi are found for the dependence. The optimization problem is solved taking
into account 8 constraints as shown in Table 1. Using these data presented in Table 1, we can determine the
differences between existing and valid values that are presented in the form of dependencies between
constraints and temperature of the firing process.
Table 1. The eight constraints for optimization
Number of constraints Type of constraints
1 is the temperature of the gases in the working space of the firing furnace
2 is the rate of delivery of agglomeration pallets from the furnace
3 is the allowable temperature difference during the initial firing period
4 are the maximum temperatures of the using furnace materials
5 are the maximum temperatures of the using furnace materials
6 are the maximum temperatures of the using furnace materials
7 is the maximum possible gas flow rate for the agglomeration furnace
8 is the productivity of the agglomeration furnace
The differences between the valid and existing values are determined by the following formula (5), where i-
current constraint number; yi-the difference between the valid and calculated values of i constraints; x1, x2, x3-
variable parameters.
7. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 12, No. 4, August 2022: 4352-4363
4358
∆𝑦1 = 𝑏1,𝑖 + 𝑏2,𝑖 ∗ 𝑥1 + 𝑏3,𝑖 ∗ 𝑥2 + 𝑏4,𝑖 ∗ 𝑥3 + 𝑏5,𝑖 ∗ 𝑥1 ∗ 𝑥2 + 𝑏6,𝑖 ∗ 𝑥1 ∗ 𝑥3
+𝑏7,𝑖 ∗ 𝑥2 ∗ 𝑥3 + 𝑏8,𝑖 ∗ 𝑥1
2
+ 𝑏9,𝑖 ∗ 𝑥2
2
+ 𝑏10,𝑖 ∗ 𝑥3
2
(5)
The time for choosing the objective function depends on the adopted step of changing the varied
parameters. As the step decreases, the computation time is decreased, and the accuracy is increased. In the
optimization model, a technique is used that makes it possible to estimate the accuracy of obtaining the
objective function with the adopted step of changing the varied parameters. The entire area of variation of the
varied parameters was divided into 1,000 volumes or 10 steps. Then the volume with the minimum cost was
determined. Then the calculation was repeated, but already with division by 3,350 volumes or 25 steps. If the
results coincided with the specified accuracy, then the calculation was terminated. In other cases, the self-cost
of the production was refined for variable parameters with minimization of the objective function.
The value of the optimal self-cost of the product obtained using the model was substituted into the
initial data in the computational experiment, which was repeated anew. The dependencies were refining
again. Further, the calculation of the objective function optimization was repeated. Refinements were
repeated until the specified accuracy was obtained. After that, the calculation was completed. Since
additional computational experiments are in the area of the desired values of the objective function, the
accuracy of the optimization results increases significantly with a small amount of computer time.
For calculation of these optimization tasks, during the study, it was used several modern computer
tools and technics. For example, for analytical solutions were used the programs were designed using the
Mathcad packet. The numerical methods were used to solve research questions using the PHOENICS packet.
At the same time, for the processing and analysis of the research results, it was used modeling methods based
on the neural networks using the Nonresolution’s packet.
3. RESULTS AND DISCUSSION
This part of the research is presented the obtained results of program calculations and modeling as
well as the experimental data for the agglomeration firing of sulfide ores of non-ferrous metallurgy. In first
section is shown the operation results of the mathematical model of agglomeration furnace and crusher
machine. In the second section is given the application of neural network technology to simulate a
furnace-crushing agglomeration plant. In the third section are presented the algorithm of training of the
neural network model.
3.1. Operation results of the mathematical model of agglomeration furnace and crusher Machine
The last part of the study is demonstrated the research outcomes. These outcomes are given for the
process of processing polymetallic ores in the Kazakh industry plant. For this purpose, data from real
installations of lead-zinc production JSC “Kazzinc” were taken as a basis.
The firing furnace is a chamber lined with refractory bricks and enclosed in a metal frame. The
agglomeration furnace is loaded and unloaded manually through a working window framed by a
water-cooled frame and closed by a water-cooled steel damper lined with lightweight chamotte. The results
of calculating the optimal modes of the real industry plant of Kazakhstan are given in Table 2. Table 2
demonstrates only the main results which are important for optimization of the processing mode in the lead-
zinc production. Because they mainly are influencing to the quality and accuracy of modeling results while
the processing of polymetallic ores.
Table 2. The calculating results the optimal modes for the firing furnace and the crusher machine
Title of the controlled parameter 1 2 3 4 5 6 7
The temperature of agglomeration furnace (0
С) 870 903 815 868 810 780 751
The volume of pallets in the furnace (kg) 560 870 630 660 730 1200 1500
The firing process temperature (0
С) 1470 1980 1320 1670 1850 1950 1535
The temperature difference of firing (0
С) 99 87 76 68 54 82 79
Gas consumption (m3
/hour) 25 28 22 21 20 19 25
Agglomeration time of firing (sec) 1312 1418 1138 1248 1176 1096 1147
Self-cost of production (tenge/kg) 37,2 38,3 46,9 52,5 50,2 48,3 44,0
3.2. Application of neural network technology to simulate a furnace-crushing agglomeration plant
Neural network modeling approach for optimization of the agglomeration plant. The mathematical
model for optimizing the operating mode of an agglomeration plant: agglomeration furnace and crusher
machine for processing polymetallic sulfide ores is a rather difficult program that includes several dozen
8. Int J Elec & Comp Eng ISSN: 2088-8708
Neural network modeling of agglomeration firing process for … (Gulnara Abitova)
4359
calculation modules. Performing a calculation in the program and obtaining a map of the technological
process of agglomeration firing of a metal charge requires a rather large investment of time, and sometimes a
decision must be made immediately. Therefore, in this work, the numerical calculation has replaced the
program of the mathematical modeling for optimizing the operating mode of the agglomeration plant for
firing based on the neural network.
As a result, the designed approach by implementing the process of the so-called network learning
that is based on the learning process on the outcomes of computations using the math samples. The neural
network has combined up the info received as a functional relationship inside. At the other cases, the math
model of the agglomeration firing equipment and crusher machine was changed to model of taking solutions
for an optimization of manufacturing plants.
Generation of input and output data for neural network model of the agglomeration plant. For
programming using neural networks, it was necessary to solve the problem by collecting data for training
using a neural network. A training dataset is a collection of observations for which the values of the input and
output variables are specified. The choice of variables (at the initial stage) is intuitive. Initially, training a
neural network includes all the variables that can affect the result, and at subsequent stages, they reduce their
set. This approach to a neural network program assumes the possibility of flexible and convenient work with
a data set. In this manner, the following main data were used as input variables: i) diameter of agglomerating
pallets, ii) size of pallets, iii) the estimated size of the agglomeration after the firing operation and
iv) permissible temperature difference at the end of agglomeration. The training data set was the database
presented by the Microsoft Excel spreadsheet. Each row in table is one supervision that involves the different
senses of seven main input variables and a one output quantity.
3.3. Algorithm of training of the neural network model
Training neural network models for the agglomeration process. For the training of the artificial
network model in the work, it was resolved the issue of choosing a specific network architecture (the number
of “levels” and the amount of “neuro cells” in every of them) when creating a neural network. Since the
nature of the phenomenon is not well known at the outset of the analysis, the choice of architecture is
difficult and often involves a lengthy process of “trial and error”. Therefore, to solve such questions it was
created the algorithm that provided the training of the neural network model for the optimization task of the
operation mode as shown in Figure 2. Figure 2 is presented the proposed algorithm of training of the neural
network models to determine the number of polymetallic ores pallets in the agglomeration furnace.
Figure 2. The algorithm of training of the neural network model of agglomeration
Verification of the results of neural network modeling. The training was performed using the data
received from the computation on the program for optimizing the operating mode of the firing furnace and
9. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 12, No. 4, August 2022: 4352-4363
4360
crushing plant. Then, the neural network was ready for operation. It was used to make forecasts and make
instant decisions. In sum, the better training outputs of neural networks were the training outputs indicated
below in the spreadsheet 3 and Figure 3. For example, the Table 3 shows a relative study of the training
outcomes and computation according to the computer program to define a number of the metal ores in the
firing furnace. Table 3 is demonstrated that the final root-mean-square error is small: MSE=0.0128.
(a) (b)
Figure 3. The Learning outcomes of the neural network according to the proposed algorithm: calculation
outcomes of the time for (a) and calculation outcomes of the outside temperature and (b) for firing process
Table 3. The relative study of the training outcomes and computation
Calculation outcomes and learning outcomes Number of ores pallets
The total number of pallets obtained from the program calculation 1 955
The total number of pallets obtained as a result of training the neural network 1 943
The relative study of the training outcomes of the learning and computation by the computer that
provides the defining of the outside temperature for firing process are shown in Figures 3(a) and 3(b).
Figure 3(a) has “Time[sec.]” as the vertical axis, and “Number of pallets [pcs.]” as horizontal axis.
Figure 3(b) has “Temperature [°С]” as the vertical axis, and “Number of pallets [pcs.]” as horizonta axis.
These graphics is showed some of the learning outcomes of the designed neural network according to the
proposed algorithm. Thus, according to the numerical experiments and the applying the trained neural
network, the little deviations were obtained that are presented in Table 4. As the result, we have obtained the
following outcomes of the training and of the little deviations: the neural networks calculation errors in the
ore’s pallets number in the agglomeration furnace ranged from 11% to 24%; the neural networks calculation
errors in the time of agglomeration of ores pallet blanks ranged from 0.2% to 7%; the neural networks
calculation errors in the surface temperature of the ore’s pallet blanks were from 0.09% to 3%.
Table 4. Comparative results of numerical calculations and calculations using neural networks
Deviations on the
number of pallets, pcs.
Deviation on the time
of agglomeration, sec.
Deviations in temperature at the
end of agglomeration, °С
Maximum deviation 15 302 37
Mean deviation 12 254 25
Minimum deviation 7 9 1
4. CONCLUSION
Within the presented study it was considered the research problems connect with controlling the
quality of the final product and optimization of the processing mode for agglomeration firing of the
polymetallic ores in the lead-zinc production. Also, this work was paid attention to determining the accuracy
and adequacy of the calculation results that are obtained by the numerical methods and mathematical
0
1000
2000
3000
4000
5000
6000
7000
8000
1 3 5 7 9 11 13 15 17 19 21 23 25
Time
[sec.]
Number of pallets [pcs.]
Time according to the results of…
Time according to the results of the…
1091
1087
1089
1095
1092
1090
1088
1088
1093
1089
1088
1082
1084
1086
1088
1090
1092
1094
1096
1 2 3 4 5 6 7 8 9 10 11
Temperatue
[°С]
Number of pallets [pcs.]
Results of calculating the program of temperature
Results of calculating the neural network of temperature
10. Int J Elec & Comp Eng ISSN: 2088-8708
Neural network modeling of agglomeration firing process for … (Gulnara Abitova)
4361
modeling of the processes. Actively used in the study mathematical calculations and programs usually are
very complex and required to use more resources and time. At the same time, these approaches as a rule have
several constraints and approximations in the models. But for the industry productions and manufactories, it
is very important to control all parameters in the required modes and to reduce the self-cost of the production.
Therefore, in the work, it was studied the new approaches and innovative methods for solving the
optimization questions of the metallurgical plant using neural network technologies. The obtained results of
the study are proved our proposed ways and new approaches for solving the problem of the research. The use
of neural networks to modeling a technological process of firing of polymetallic sulfide ores at the non-
ferrous metallurgy provided to enhance the efficiency of production quality control systems and automation
systems for firing of sulfide metals, decreasing a manufacturing cost by 3%. In addition, it increased the
effectiveness of energy reproduction. Operation of heating equipment by optimizing the operating mode of
equipment is provided the increasing of effectiveness 10%.
Thus, from the above results, it is obvious that a getting neural models correctly describe the real
processes while the processing t and the firing of polymetallic ores in the furnace. And this is proving that the
research goals of this work are obtained. Future, it can be recommended to use for study the process of the
firing of the other ores on the metallurgy plant and for calculating the design features of a heating and power
plant. This way also could be applied to forecast and take good solutions to design any other heating tools as
well as for its optimal regulation. Finally, these results in this work are adding the new value of research to
the existing scientific results and knowledge in particular to problems of the modeling and optimizing the
technological processes in the metallurgical manufactories. The novelty of this research lies is presented in
the following. The new technique has been developed to determine the accuracy of calculation results and the
adequate of modeling the modes of continuous technological processes of the loading and unloading
concentrates into agglomeration furnaces and firing of the sulfide polymetallic ores. It was created the neural
network model of the agglomeration furnace and crusher machine solving the problem of calculating the
needed parameters of the furnace and crusher machine. It was proposed the new approach to optimizing the
operating mode of energy equipment in lead-zinc production that provided a decrease in the production cost.
REFERENCES
[1] D. Yu, T. A. Utigard, and M. Barati, “Fluidized bed selective oxidation-sulfation roasting of nickel sulfide concentrate: part ii.
Sulfation roasting,” Metallurgical and Materials Transactions B, vol. 45, no. 2, pp. 662–674, Apr. 2014, doi: 10.1007/s11663-
013-9959-9.
[2] P. V. Saraev, “Numerical methods of interval analysis in learning neural network,” Automation and Remote Control, vol. 73, no.
11, pp. 1865–1876, Nov. 2012, doi: 10.1134/S0005117912110082.
[3] G. Abitova, E. Abdrakhmanova, Z. Bekish, T. Zadenova, L. Rzayeva, and K. Kulniyazova, “Study and simulation of control
system of the process of roasting in fluidized bed furnaces of polymetallic sulfide ores under uncertainty,” in 2021 IEEE
International Conference on Smart Information Systems and Technologies (SIST), Apr. 2021, pp. 1–6, doi:
10.1109/SIST50301.2021.9465976.
[4] V. A. Vekhnik, “Thermal neural network modeling continuous furnace operation metallurgical heat engineering,” The
Proceedings of the National Metallurgical Academy of Ukraine, 2002.
[5] V. A. Kastornova and M. G. Mozhaeva, “Artificial neural networks as modern means of informatization,” Information
environment of education and science, no. 7, pp. 1–17, 2012.
[6] E. Mora, J. Cifuentes, and G. Marulanda, “Short-term forecasting of wind energy: a comparison of deep learning frameworks,”
Energies, vol. 14, no. 23, Nov. 2021, doi: 10.3390/en14237943.
[7] P. D. Wasserman, Neural computing: theory and practice. Coriolis Group; First Edition, 1989.
[8] А. N. Gorban and D. A. Rossiev, Neural networks on personal computer. Novosibirsk: Nauka, 1996.
[9] A. Y. Andreeva and V. A. Romanchuk, “The use of neurocomputer technologies in methods of managing complex objects,”
Modern technology and technology, 2015. .
[10] A. N. Khan, N. Iqbal, R. Ahmad, and D.-H. Kim, “Ensemble prediction approach based on learning to statistical model for
efficient building energy consumption management,” Symmetry, vol. 13, no. 3, Mar. 2021, doi: 10.3390/sym13030405.
[11] X. Qiu, L. Zhang, Y. Ren, P. Suganthan, and G. Amaratunga, “Ensemble deep learning for regression and time series
forecasting,” in 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL), Dec. 2014, pp. 1–6, doi:
10.1109/CIEL.2014.7015739.
[12] C. Tian, J. Ma, C. Zhang, and P. Zhan, “A deep neural network model for short-term load forecast based on long short-term
memory network and convolutional neural network,” Energies, vol. 11, no. 12, Dec. 2018, doi: 10.3390/en11123493.
[13] P. Singh and P. Dwivedi, “Integration of new evolutionary approach with artificial neural network for solving short term load
forecast problem,” Applied Energy, vol. 217, pp. 537–549, May 2018, doi: 10.1016/j.apenergy.2018.02.131.
[14] F. Jamil, N. Iqbal, Imran, S. Ahmad, and D. Kim, “Peer-to-peer energy trading mechanism based on blockchain and machine
learning for sustainable electrical power supply in smart grid,” IEEE Access, vol. 9, pp. 39193–39217, 2021, doi:
10.1109/ACCESS.2021.3060457.
[15] D. L. Marino, K. Amarasinghe, and M. Manic, “Building energy load forecasting using deep neural networks,” in IECON 2016-
42nd Annual Conference of the IEEE Industrial Electronics Society, Oct. 2016, pp. 7046–7051, doi:
10.1109/IECON.2016.7793413.
[16] Q. Zhang and J. Zhang, “Short-term load forecasting method based on EWT and IDBSCAN,” Journal of Electrical Engineering
and Technology, vol. 15, no. 2, pp. 635–644, Mar. 2020, doi: 10.1007/s42835-020-00358-0.
[17] N. Ulakhanov and U. Mishigdorzhiyn, “The neural networks application in predicting the geometrical parameters of coatings
formed on a steel substrate by laser alloying,” IOP Conference Series: Materials Science and Engineering, vol. 684, no. 1, Nov.
11. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 12, No. 4, August 2022: 4352-4363
4362
2019, doi: 10.1088/1757-899X/684/1/012003.
[18] Ö. F. Ertugrul, “Forecasting electricity load by a novel recurrent extreme learning machines approach,” International Journal of
Electrical Power and Energy Systems, vol. 78, pp. 429–435, Jun. 2016, doi: 10.1016/j.ijepes.2015.12.006.
[19] M. H. S. Segler, T. Kogej, C. Tyrchan, and M. P. Waller, “Generating focused molecule libraries for drug discovery with
recurrent neural networks,” ACS Central Science, vol. 4, no. 1, pp. 120–131, Jan. 2018, doi: 10.1021/acscentsci.7b00512.
[20] V. N. E. Kalinin, “Automation in oil production. The project of creating a system for electronic development of assets,” Siberian
oil, 2013. .
[21] R. S. Mamidala, U. Uthkota, M. B. Shankar, A. J. Antony, and A. V Narasimhadhan, “Dynamic approach for lane detection using
google street view and CNN,” in TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), Oct. 2019, vol. 2019, pp. 2454–
2459, doi: 10.1109/TENCON.2019.8929655.
[22] S. Albahli and W. Albattah, “Detection of coronavirus disease from X-ray images using deep learning and transfer learning
algorithms,” Journal of X-Ray Science and Technology, vol. 28, no. 5, pp. 841–850, Sep. 2020, doi: 10.3233/XST-200720.
[23] E. Samylovskaya, A. Makhovikov, A. Lutonin, D. Medvedev, and R.-E. Kudryavtseva, “Digital technologies in arctic oil and gas
resources extraction: global trends and Russian experience,” Resources, vol. 11, no. 3, Mar. 2022, doi:
10.3390/resources11030029.
[24] H. Tcharo, A. E. Vorobyev, and K. A. Vorobyev, “Digitalization of the oil industry: basic approaches and rationale for ‘smart’
technologies (in Russian),” The Eurasian Scientific Journal, 2018. .
[25] G. Tassey, “Competing in advanced manufacturing: The need for improved growth models and policies,” Journal of Economic
Perspectives, vol. 28, no. 1, 2014.
[26] V. Fernandez, J. Chavez, and G. Kemper, “Device to evaluate cleanliness of fiber optic connectors using image processing and
neural networks,” International Journal of Electrical and Computer Engineering (IJECE), vol. 11, no. 4, pp. 3093–3105, Aug.
2021, doi: 10.11591/ijece.v11i4.pp3093-3105.
[27] T. S. Lim, K. G. Tay, A. Huong, and X. Y. Lim, “Breast cancer diagnosis system using hybrid support vector machine-artificial
neural network,” International Journal of Electrical and Computer Engineering (IJECE), vol. 11, no. 4, pp. 3059–3069, Aug.
2021, doi: 10.11591/ijece.v11i4.pp3059-3069.
[28] Y. Boujoudar, M. Azeroual, H. Elmoussaoui, and T. Lamhamdi, “Intelligent control of battery energy storage for microgrid
energy management using ANN,” International Journal of Electrical and Computer Engineering (IJECE), vol. 11, no. 4, pp.
2760–2767, Aug. 2021, doi: 10.11591/ijece.v11i4.pp2760-2767.
[29] A. Salam, A. El Hibaoui, and A. Saif, “A comparison of activation functions in multilayer neural network for predicting the
production and consumption of electricity power,” International Journal of Electrical and Computer Engineering (IJECE), vol.
11, no. 1, pp. 163–170, Feb. 2021, doi: 10.11591/ijece.v11i1.pp163-170.
[30] Z. Hu, J. Ma, L. Yang, L. Yao, and M. Pang, “Monthly electricity demand forecasting using empirical mode decomposition-based
state space model,” Energy and Environment, vol. 30, no. 7, pp. 1236–1254, Nov. 2019, doi: 10.1177/0958305X19842061.
[31] V. A. Gorbunov, “Using neural network technologies to improve energy efficiency heat technology installations,” in Ivanovo,
2011.
[32] A. K. Sokolov, “Optimization of operating and design parameters and improvement of calculation methods for gas heating
furnaces,” in Diss. work, 2002.
[33] D. Yu, T. A. Utigard, and M. Barati, “Fluidized bed selective oxidation-sulfation roasting of nickel sulfide concentrate: Part I.
Oxidation roasting,” Metallurgical and Materials Transactions B, vol. 45, no. 2, pp. 653–661, Apr. 2014, doi: 10.1007/s11663-
013-9958-x.
BIOGRAPHIES OF AUTHORS
Gulnara Abitova received her M.S. degree in Cybernetics in 1988 from Moscow
Institute of Allows and Steel at Moscow, Russia, and her Ph.D. in Automation and Control in
2013 from the State University of New York (SUNY) at Binghamton and L.N. Eurasian
National University, Kazakhstan. She graduated from the Postdoctoral Program in Control
Systems in 2012 from Binghamton University, USA. Dr. Abitova worked as a Visiting
Professor and Researcher at the Department of Electrical and Computer Engineering at
Binghamton University, USA, in 2010-2012. In 2017, she was an Invited Professor at the
Savonia University of Applied Sciences and Technology in Savonia, Finland. She published
more than 100 research articles, 6 monographs and books, and 3 theses. Her current research
interest includes control systems and industrial automation, simulation and modeling, neural
networks technology. She can be contacted at e-mail: abitova.gul@gmail.com.
Vladimir Nikulin received his B.S. degree in Electrical Engineering in 1996 from
Karaganda Polytechnic Institute, and his M.S. and Ph.D. both in Electrical Engineering in 1998
and 2002, respectively, from the State University of New York (SUNY) at Binghamton
University (SUNY), USA. In 2002, he joined the Department of Electrical and Computer
Engineering at Binghamton where he is currently an Associate Professor. In 2006, he was a
Visiting Scholar in the Department of Cybernetics at the Czech Technical University in Prague
and also worked as a Visiting Professor. Dr. Nikulin published more than 250 papers on the
control system and automation, as well as on optics and quantic electronics. His interests are
control systems, industrial automation, optics, quantic electronics, electrical engineering, and
simulation. He can be contacted at email: vnikulin@binghamton.edu.
12. Int J Elec & Comp Eng ISSN: 2088-8708
Neural network modeling of agglomeration firing process for … (Gulnara Abitova)
4363
Leila Rzayeva received her B.S, M.S., and Ph.D. from L.N. Gumilyov Eurasian
National University, Astana, Kazakhstan, in 2015. She works as an Associate Professor,
Advisor, and Researcher at L.N. Gumilyov Eurasian National University, Information
Technology Faculty (Nur-Sultan, Kazakhstan). She is having a total teaching experience of
more than 10 years. Leila Rzayeva has published more than 30 national/international research
articles. Her interests are control systems and industrial automation, simulation, and design of
control information systems, as well as the design of neural networks and artificial intelligent
systems. E-mail: leilarza2@gmail.com.
Tansuly Zadenova received her BEng and MSc in Information Systems from the
L.N. Gumilyov Eurasian National University, Nur-Sultan, Kazakhstan, in 2014 and 2017
respectively. She is a Doctoral student in Automation and Control of Information Technology
Faculty at L.N. Gumilyov Eurasian National University (Nur-Sultan, Kazakhstan), from 2018.
She has presented several research papers in international journals and conferences. Her
scientific interest is in the field of automation and control, neural networks, and industrial
optimization. E-mail: tan.zadenova21@gmail.com.
Ali Myrzatay received his B.S, and M.S. in Telecommunication Systems from the
L.N. Gumilyov Eurasian National University, Astana, Kazakhstan, in 2014 and 2016
respectively. He is a Doctoral student in Automation and Control of Information Technology
Faculty at L.N. Gumilyov Eurasian National University (Nur-Sultan, Kazakhstan), from 2018.
He has presented several research papers in international and republican journals and
conferences. His scientific interests are automation and control, machine learning, neural
networks, and industrial optimization. E-mail: mirzataitegiali@gmail.com.