This document discusses the use of neural network controllers for nonlinear systems based on nonlinear autoregressive moving average (NARMA) models. It specifically examines using a NARMA-L2 model to design three different neural network controllers for a nerves system based arm position sensor device: 1) a neural network controller with NARMA-L2 system identification, 2) a neural network controller with NARMA-L2 model predictive control, and 3) a neural network controller with NARMA-L2 model reference adaptive control. Simulation results show the neural network controller with NARMA-L2 model reference adaptive control had the best performance for controlling the arm position under different input signals.
This document summarizes a research article that proposes using a novel clustering-based fuzzy controller for speed control of DC motors. The controller uses a hybrid kernel-based clustering algorithm called KPFCM to identify fuzzy rules and membership functions from motor data. This approach provides an efficient way to model the nonlinear dynamics of DC motors for control purposes. Simulation results show the proposed fuzzy controller achieves better performance than a conventional fuzzy logic controller in terms of rise time, overshoot, settling time, and error metrics. The clustering-based approach reduces computational time compared to traditional fuzzy design methods.
High - Performance using Neural Networks in Direct Torque Control for Asynchr...IJECEIAES
This article investigates solution for the biggest problem of the Direct Torque Control on the asynchronous machine to have the high dynamic performance with very simple hysteresis control scheme. The Conventional Direct Torque Control (CDTC) suffers from some drawbacks such as high current, flux and torque ripple, as well as flux control at very low speed. In this paper, we propose an intelligent approach to improve the direct torque control of induction machine which is an artificial neural networks control. The principle, the numerical procedure and the performances of this method are presented. Simulations results show that the proposed ANN-DTC strategy effectively reduces the torque and flux ripples at low switching frequency, compared with Fuzzy Logic DTC and The Conventional DTC.
This document presents research on an adaptive vague controller based power system stabilizer (AVCPSS). It begins with an abstract that describes using an Adaptive Network Based Vague Inference System (ANVIS) to develop an Adaptive Vague Set Based Controller Power System Stabilizer (AVCPSS) capable of providing stabilization signals over a wide range of operating conditions and disturbances. Section I provides further introduction and background. Section II describes vague set theory and vague controllers, while Section III details the development of a Vague Set Based Controller Power System Stabilizer (VCPSS). Section IV introduces ANVIS for implementing learning and adaptation. Section V discusses the AVCPSS developed using ANVIS. Results in Section VI show the
Review: “Implementation of Feedforward and Feedback Neural Network for Signal...IJERA Editor
Main focus of project is on implementation of Neural Network Architecture (NNA) with on chip learning on
Analog VLSI Technology for signal processing application. In the proposed paper the analog components like
Gilbert Cell Multiplier (GCM), Neuron Activation Function (NAF) are used to implement artificial NNA.
Analog components used comprises of multiplier, adder and tan sigmoidal function circuit using MOS transistor.
This Neural Architecture is trained using Back Propagation (BP) Algorithm in analog domain with new
techniques of weight storage. Layout design and verification of above design is carried out using VLSI Backend
Microwind 3.1 software Tool. The technology used to design layout is 32 nm CMOS Technology.
Digital Implementation of Artificial Neural Network for Function Approximatio...IOSR Journals
: The soft computing algorithms are being nowadays used for various multi input multi output
complicated non linear control applications. This paper presented the development and implementation of back
propagation of multilayer perceptron architecture developed in FPGA using VHDL. The usage of the FPGA
(Field Programmable Gate Array) for neural network implementation provides flexibility in programmable
systems. For the neural network based instrument prototype in real time application. The conventional specific
VLSI neural chip design suffers the limitation in time and cost. With low precision artificial neural network
design, FPGA have higher speed and smaller size for real time application than the VLSI design. The
challenges are finding an architecture that minimizes the hardware cost, maximizing the performance,
accuracy. The goal of this work is to realize the hardware implementation of neural network using FPGA.
Digital system architecture is presented using Very High Speed Integrated Circuits Hardware Description
Language (VHDL)and is implemented in FPGA chip. MATLAB ANN programming and tools are used for
training the ANN. The trained weights are stored in different RAM, and is implemented in FPGA. The design
was tested on a FPGA demo board
Introduction to Adaptive Resonance Theory (ART) neural networks including:
Introduction (Stability-Plasticity Dilemma)
ART Network
ART Types
Basic ART network Architecture
ART Algorithm and Learning
ART Computational Example
ART Application
Conclusion
Main References
Implementation of an arithmetic logic using area efficient carry lookahead adderVLSICS Design
An arithmetic logic unit acts as the basic building blocks or cell of a central processing unit of a computer.
And it is a digital circuit comprised of the basic electronics components, which is used to perform various
function of arithmetic and logic and integral operations further the purpose of this work is to propose the
design of an 8-bit ALU which supports 4-bit multiplication. Thus, the functionalities of the ALU in this
study consist of following main functions like addition also subtraction, increment, decrement, AND, OR,
NOT, XOR, NOR also two complement generation Multiplication. And the functions with the adder in the
airthemetic logic unit are implemented using a Carry Look Ahead adder joined by a ripple carry approach.
The design of the following multiplier is achieved using the Booths Algorithm therefore the proposed ALU
can be designed by using verilog or VHDL and can also be designed on Cadence Virtuoso platform.
This document summarizes a research paper that proposes a microcontroller-based cryptosystem using the Tiny Encryption Algorithm (TEA) combined with a Key Generation Unit (KGU). The KGU uses timers in the microcontroller to generate random bits for encryption keys. The cryptosystem can operate in serial or wireless transmission modes. Performance analysis shows the cryptosystem has improved throughput and decreased execution time compared to TEA alone. Randomness testing of the generated keys indicates distinct random bits. In conclusion, the system provides moderate security and simplicity for applications requiring secured data transfer with low cost and memory constraints.
This document summarizes a research article that proposes using a novel clustering-based fuzzy controller for speed control of DC motors. The controller uses a hybrid kernel-based clustering algorithm called KPFCM to identify fuzzy rules and membership functions from motor data. This approach provides an efficient way to model the nonlinear dynamics of DC motors for control purposes. Simulation results show the proposed fuzzy controller achieves better performance than a conventional fuzzy logic controller in terms of rise time, overshoot, settling time, and error metrics. The clustering-based approach reduces computational time compared to traditional fuzzy design methods.
High - Performance using Neural Networks in Direct Torque Control for Asynchr...IJECEIAES
This article investigates solution for the biggest problem of the Direct Torque Control on the asynchronous machine to have the high dynamic performance with very simple hysteresis control scheme. The Conventional Direct Torque Control (CDTC) suffers from some drawbacks such as high current, flux and torque ripple, as well as flux control at very low speed. In this paper, we propose an intelligent approach to improve the direct torque control of induction machine which is an artificial neural networks control. The principle, the numerical procedure and the performances of this method are presented. Simulations results show that the proposed ANN-DTC strategy effectively reduces the torque and flux ripples at low switching frequency, compared with Fuzzy Logic DTC and The Conventional DTC.
This document presents research on an adaptive vague controller based power system stabilizer (AVCPSS). It begins with an abstract that describes using an Adaptive Network Based Vague Inference System (ANVIS) to develop an Adaptive Vague Set Based Controller Power System Stabilizer (AVCPSS) capable of providing stabilization signals over a wide range of operating conditions and disturbances. Section I provides further introduction and background. Section II describes vague set theory and vague controllers, while Section III details the development of a Vague Set Based Controller Power System Stabilizer (VCPSS). Section IV introduces ANVIS for implementing learning and adaptation. Section V discusses the AVCPSS developed using ANVIS. Results in Section VI show the
Review: “Implementation of Feedforward and Feedback Neural Network for Signal...IJERA Editor
Main focus of project is on implementation of Neural Network Architecture (NNA) with on chip learning on
Analog VLSI Technology for signal processing application. In the proposed paper the analog components like
Gilbert Cell Multiplier (GCM), Neuron Activation Function (NAF) are used to implement artificial NNA.
Analog components used comprises of multiplier, adder and tan sigmoidal function circuit using MOS transistor.
This Neural Architecture is trained using Back Propagation (BP) Algorithm in analog domain with new
techniques of weight storage. Layout design and verification of above design is carried out using VLSI Backend
Microwind 3.1 software Tool. The technology used to design layout is 32 nm CMOS Technology.
Digital Implementation of Artificial Neural Network for Function Approximatio...IOSR Journals
: The soft computing algorithms are being nowadays used for various multi input multi output
complicated non linear control applications. This paper presented the development and implementation of back
propagation of multilayer perceptron architecture developed in FPGA using VHDL. The usage of the FPGA
(Field Programmable Gate Array) for neural network implementation provides flexibility in programmable
systems. For the neural network based instrument prototype in real time application. The conventional specific
VLSI neural chip design suffers the limitation in time and cost. With low precision artificial neural network
design, FPGA have higher speed and smaller size for real time application than the VLSI design. The
challenges are finding an architecture that minimizes the hardware cost, maximizing the performance,
accuracy. The goal of this work is to realize the hardware implementation of neural network using FPGA.
Digital system architecture is presented using Very High Speed Integrated Circuits Hardware Description
Language (VHDL)and is implemented in FPGA chip. MATLAB ANN programming and tools are used for
training the ANN. The trained weights are stored in different RAM, and is implemented in FPGA. The design
was tested on a FPGA demo board
Introduction to Adaptive Resonance Theory (ART) neural networks including:
Introduction (Stability-Plasticity Dilemma)
ART Network
ART Types
Basic ART network Architecture
ART Algorithm and Learning
ART Computational Example
ART Application
Conclusion
Main References
Implementation of an arithmetic logic using area efficient carry lookahead adderVLSICS Design
An arithmetic logic unit acts as the basic building blocks or cell of a central processing unit of a computer.
And it is a digital circuit comprised of the basic electronics components, which is used to perform various
function of arithmetic and logic and integral operations further the purpose of this work is to propose the
design of an 8-bit ALU which supports 4-bit multiplication. Thus, the functionalities of the ALU in this
study consist of following main functions like addition also subtraction, increment, decrement, AND, OR,
NOT, XOR, NOR also two complement generation Multiplication. And the functions with the adder in the
airthemetic logic unit are implemented using a Carry Look Ahead adder joined by a ripple carry approach.
The design of the following multiplier is achieved using the Booths Algorithm therefore the proposed ALU
can be designed by using verilog or VHDL and can also be designed on Cadence Virtuoso platform.
This document summarizes a research paper that proposes a microcontroller-based cryptosystem using the Tiny Encryption Algorithm (TEA) combined with a Key Generation Unit (KGU). The KGU uses timers in the microcontroller to generate random bits for encryption keys. The cryptosystem can operate in serial or wireless transmission modes. Performance analysis shows the cryptosystem has improved throughput and decreased execution time compared to TEA alone. Randomness testing of the generated keys indicates distinct random bits. In conclusion, the system provides moderate security and simplicity for applications requiring secured data transfer with low cost and memory constraints.
This document provides an overview of artificial neural networks. It defines ANNs as highly interconnected networks of neurons inspired by the human brain. The document then discusses key aspects of ANNs like biological neurons, network architecture, learning rules, activation functions, and specific ANN models including perceptrons, backpropagation networks, associative memories, and Hopfield networks. It provides details on the basic building blocks and functioning of various ANN concepts.
Simulation of Single and Multilayer of Artificial Neural Network using Verilogijsrd.com
This document discusses the simulation of single layer and multilayer artificial neural networks using Verilog. It begins with an introduction to artificial neural networks and their application in VLSI circuit fault diagnosis. It then provides details on the algorithm and design methodology for simulating a single layer neural network to model an AND gate, showing the calculation of error over iterations in Matlab and time taken using Verilog code. For a multilayer network modeling an XOR gate, it similarly discusses the backpropagation algorithm, showing error reduction over iterations in Matlab and time taken using Verilog. It concludes that neural networks can help minimize time to find faults in digital circuits.
This document discusses neural networks and multilayer feedforward neural network architectures. It describes how multilayer networks can solve nonlinear classification problems using hidden layers. The backpropagation algorithm is introduced as a way to train these networks by propagating error backwards from the output to adjust weights. The architecture of a neural network is explained, including input, hidden, and output nodes. Backpropagation is then described in more detail through its training process of forward passing input, calculating error at the output, and propagating this error backwards to update weights. Examples of backpropagation and its applications are also provided.
Identification and Control of Three-Links Electrically Driven Robot Arm Using...Waqas Tariq
This paper uses a fuzzy neural network (FNN) structure for identifying and controlling nonlinear dynamic systems such three links robot arm. The equation of motion for three links robot arm derived using Lagrange’s equation. This equation then combined with the equations of motion for dc. servo motors which actuated the robot. For the control problem, we present the forward and inverse adaptive control approaches using the FNN. Computer simulation is performed to view the results for identification and control
Implementation of Back-Propagation Neural Network using Scilab and its Conver...IJEEE
Artificial neural network has been widely used for solving non-linear complex tasks. With the development of computer technology, machine learning techniques are becoming good choice. The selection of the machine learning technique depends upon the viability for particular application. Most of the non-linear problems have been solved using back propagation based neural network. The training time of neural network is directly affected by convergence speed. Several efforts are done to improve the convergence speed of back propagation algorithm. This paper focuses on the implementation of back-propagation algorithm and an effort to improve its convergence speed. The algorithm is written in SCILAB. UCI standard data set is used for analysis purposes. Proposed modification in standard backpropagation algorithm provides substantial improvement in the convergence speed.
Deep Learning for Natural Language ProcessingIRJET Journal
This document discusses the use of deep learning techniques in natural language processing. It begins by defining deep learning as a set of machine learning algorithms that use multiple layered models like neural networks to learn inputs. Deep learning aims to process complex data like text in a way that mimics the human brain. The document then discusses several deep learning methods that have been applied to natural language processing tasks, including stacked autoencoders, deep Boltzmann machines, and transfer learning. It provides examples of how these techniques are used to perform tasks like object recognition from text and speech recognition.
Implementation Of Back-Propagation Neural Network For Isolated Bangla Speech ...ijistjournal
This document describes the implementation of a back-propagation neural network for isolated Bangla speech recognition. The network was trained on Mel Frequency Cepstral Coefficient (MFCC) features extracted from recordings of 10 Bangla digits spoken by 10 speakers. The network architecture included an input layer of 250 neurons, a hidden layer of 16 neurons, and an output layer of 10 neurons. The network was trained using backpropagation and achieved a recognition rate of 96.3% for known speakers and 92% for unknown speakers. The system demonstrates the potential for developing speaker-independent isolated digit speech recognition in Bangla.
Application of Artificial Neural Networking for Determining the Plane of Vibr...IOSRJMCE
In this paper a new approach for Artificial Neural Networking using Feed Forward Back Propagation Method and Levenberg-Marquardt backpropagation training function has been developed using Java Programming, where by directly feeding the RMS and Phase values of vibration, the unbalance plane can be detected with minimum error. In a Machine Fault Simulator RMS value and phase values of vibrations are collected from the four accelerometers placed in X and Y direction of Left and Right Bearings .Further these data are fed into the neural network for training purpose. In the testing phase of the neural network, the plane of vibration has been determined using different training algorithms available in MATLAB. Their prediction values have been compared with the actual value, errors for different training algorithms are calculated and a conclusion has been drawn for the best training function available for this current research work.
This document discusses various types of neural networks including feedback neural networks, self-organizing feature maps, and Hopfield networks. It provides details on Hopfield networks such as their architecture, training and testing algorithms. It also discusses issues like false minima problem in neural networks and techniques to address it like simulated annealing and stochastic update. Furthermore, it covers associative memory models like bidirectional associative memory and self-organizing maps.
This document summarizes research on neural networks. It discusses the basic structure and components of neural networks, including network topology (feed forward and recurrent), transfer functions, and learning algorithms (supervised, unsupervised, reinforcement). It also overview popular neural network models like multilayer perceptrons, radial basis function networks, Kohonen's self-organizing maps, and Hopfield networks. Finally, it outlines some applications of neural networks such as process control, pattern recognition, and more.
The document outlines Adaptive Resonance Theory (ART), a type of neural network invented by Stephen Grossberg in 1976. ART networks aim to solve the stability-plasticity dilemma by allowing plasticity to learn new patterns while maintaining stability of previously learned patterns. The basic ART system consists of a comparison field, recognition field, vigilance parameter, and reset module. The ART algorithm matches input patterns to stored cluster templates, either joining the closest matching cluster or initializing a new one. [/SUMMARY]
A simplified design of multiplier for multi layer feed forward hardware neura...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 describes IntelliSuite's integrated MEMS design flow, which allows users to model devices from the schematic level through physical layout and verification, as well as simulate multi-physics processes. IntelliSuite combines top-down and bottom-up design approaches for efficient and accurate modeling. Key capabilities include schematic capture, physical layout, process simulation, and system-level modeling extraction for fast behavioral simulation.
A Survey on Secure Alternate Path Selection for Enhanced Network Lifetime in ...IRJET Journal
This document summarizes a research paper that proposes techniques to enhance the lifetime of wireless sensor networks. It discusses how sensor nodes closer to the sink node consume more energy transmitting data, creating hotspots and shortening the network's lifetime. To address this, the paper proposes using alternate shortest paths to route data and relocating the sink node when the energy of alternate paths gets low. It also uses elliptic curve cryptography and a hybrid encryption method using AES and ECC to securely transmit data and further increase the network lifetime. Evaluation results show the proposed energy-aware sink relocation technique effectively enhances the network lifetime of wireless sensor networks.
Back propagation networks are neural networks that use a learning algorithm called backpropagation. The key characteristics are:
1. Neurons in one layer connect to all neurons in the next layer.
2. Each neuron has its own input weights.
3. Training involves passing input values through the network layers to calculate the output, then using backpropagation to adjust the weights to reduce error.
4. The network must have at least an input and output layer, with optional hidden layers.
This summary provides an overview of a document describing a teleoperated robot arm and hand system using shared control:
1. The system uses shared control between autonomous control, teleoperation, and simulation modules to coordinate a robot arm, dexterous hand, sensors, and a teleoperated mechanical arm and data glove.
2. Key aspects of the shared control include sensor data sharing between various sensors, multi-agent based sharing to perform complex tasks using different sensors, and human-machine interactive sharing between high-level planning and low-level autonomous control.
3. Experiments showed the system could perform autonomous operations like pushing buttons and twisting objects using vision and force sensors, and the shared control approach was high-
Mixed approach for scheduling process in wimax for high qoseSAT Journals
Abstract
WiMAX(worldwide interoperability for Microwave Access) networks are the networks which are responsible for providing many services like video, data and voice. The WiMAX technology satisfies the modern need of broadband internet through wireless access. For managing all these services through WiMAX, IEEE802.16 gives QOS (Quality of Service) parameter. In WiMAX, a fundamental challenge is to achieve high QOS so that various parameters like waiting time, end to end delay can be minimized and other parameter like execution time and network utilization etc. To obtain high QOS there is scheduling algorithm which is implemented at the base station and subscriber stations. In this paper we discuss scheduling algorithms and also compare the parameters (waiting time, turnaround time, execution time, packet drop age and packet delivery). We purpose a scheduling algorithm which is combination of greedy latency, distance calculation of user from base station, calculate the burst time and apply SJF on that burst values.
Keywords: WiMAX, QOS, IEEE802.16, Scheduling, FCFS (first come first serve), SJF(Shortest job First), Latency.
Analysis of intelligent system design by neuro adaptive control no restrictioniaemedu
This document discusses using neuro-adaptive control to analyze the design of intelligent systems. It begins by introducing the topic and noting that conventional adaptive control techniques assume explicit system models or dynamic structures based on linear models, which may not be valid for complex nonlinear systems. Neural networks and other intelligent control approaches that do not require explicit mathematical modeling are presented as alternatives. The paper then focuses on using time-delay neural networks for system identification and control of nonlinear dynamic systems. Various neural network architectures and learning algorithms for system modeling and control are described.
Analysis of intelligent system design by neuro adaptive controliaemedu
This document summarizes the analysis of intelligent system design using neuro-adaptive control methods. It discusses using neural networks for system identification through series-parallel and parallel models. It also discusses supervised control using a neural network trained by an expert operator, inverse control using a neural network trained on the inverse system model, and neuro-adaptive control using two neural networks - one for system identification and one for control. Neuro-adaptive control allows handling nonlinear system behavior without linear approximations.
Tuning of Proportional Integral Derivative Controller Using Artificial Neural...IRJET Journal
This document discusses tuning a proportional-integral-derivative (PID) controller using an artificial neural network (ANN). Specifically:
1. A PID controller is used to control various process variables like pressure, temperature, and speed. The PID controller gains (KP, KI, KD) are tuned by training an ANN to optimize the controller response.
2. An ANN is trained using the Levenberg-Marquardt algorithm to determine the optimal PID gains. The tuned PID controller results in reduced overshoot, peak value, and settling time compared to the untuned controller.
3. Simulation results show that with ANN tuning, overshoot is reduced from 27.1% to 7
Neural Network Implementation Control Mobile RobotIRJET Journal
This document describes the design and implementation of a neural network controlled mobile robot. The robot is equipped with IR sensors to detect obstacles and a microcontroller runs a neural network program. The neural network is trained offline using a backpropagation algorithm and sensor input patterns to navigate around obstacles. Experimental results showed the robot could successfully react to new obstacle configurations not in its training set. Potential applications of neural networks discussed include industrial process control, sales forecasting, and target marketing. The design could be improved by adding GPS and speed control to allow the robot to navigate to a target destination avoiding obstacles.
This document provides an overview of artificial neural networks. It defines ANNs as highly interconnected networks of neurons inspired by the human brain. The document then discusses key aspects of ANNs like biological neurons, network architecture, learning rules, activation functions, and specific ANN models including perceptrons, backpropagation networks, associative memories, and Hopfield networks. It provides details on the basic building blocks and functioning of various ANN concepts.
Simulation of Single and Multilayer of Artificial Neural Network using Verilogijsrd.com
This document discusses the simulation of single layer and multilayer artificial neural networks using Verilog. It begins with an introduction to artificial neural networks and their application in VLSI circuit fault diagnosis. It then provides details on the algorithm and design methodology for simulating a single layer neural network to model an AND gate, showing the calculation of error over iterations in Matlab and time taken using Verilog code. For a multilayer network modeling an XOR gate, it similarly discusses the backpropagation algorithm, showing error reduction over iterations in Matlab and time taken using Verilog. It concludes that neural networks can help minimize time to find faults in digital circuits.
This document discusses neural networks and multilayer feedforward neural network architectures. It describes how multilayer networks can solve nonlinear classification problems using hidden layers. The backpropagation algorithm is introduced as a way to train these networks by propagating error backwards from the output to adjust weights. The architecture of a neural network is explained, including input, hidden, and output nodes. Backpropagation is then described in more detail through its training process of forward passing input, calculating error at the output, and propagating this error backwards to update weights. Examples of backpropagation and its applications are also provided.
Identification and Control of Three-Links Electrically Driven Robot Arm Using...Waqas Tariq
This paper uses a fuzzy neural network (FNN) structure for identifying and controlling nonlinear dynamic systems such three links robot arm. The equation of motion for three links robot arm derived using Lagrange’s equation. This equation then combined with the equations of motion for dc. servo motors which actuated the robot. For the control problem, we present the forward and inverse adaptive control approaches using the FNN. Computer simulation is performed to view the results for identification and control
Implementation of Back-Propagation Neural Network using Scilab and its Conver...IJEEE
Artificial neural network has been widely used for solving non-linear complex tasks. With the development of computer technology, machine learning techniques are becoming good choice. The selection of the machine learning technique depends upon the viability for particular application. Most of the non-linear problems have been solved using back propagation based neural network. The training time of neural network is directly affected by convergence speed. Several efforts are done to improve the convergence speed of back propagation algorithm. This paper focuses on the implementation of back-propagation algorithm and an effort to improve its convergence speed. The algorithm is written in SCILAB. UCI standard data set is used for analysis purposes. Proposed modification in standard backpropagation algorithm provides substantial improvement in the convergence speed.
Deep Learning for Natural Language ProcessingIRJET Journal
This document discusses the use of deep learning techniques in natural language processing. It begins by defining deep learning as a set of machine learning algorithms that use multiple layered models like neural networks to learn inputs. Deep learning aims to process complex data like text in a way that mimics the human brain. The document then discusses several deep learning methods that have been applied to natural language processing tasks, including stacked autoencoders, deep Boltzmann machines, and transfer learning. It provides examples of how these techniques are used to perform tasks like object recognition from text and speech recognition.
Implementation Of Back-Propagation Neural Network For Isolated Bangla Speech ...ijistjournal
This document describes the implementation of a back-propagation neural network for isolated Bangla speech recognition. The network was trained on Mel Frequency Cepstral Coefficient (MFCC) features extracted from recordings of 10 Bangla digits spoken by 10 speakers. The network architecture included an input layer of 250 neurons, a hidden layer of 16 neurons, and an output layer of 10 neurons. The network was trained using backpropagation and achieved a recognition rate of 96.3% for known speakers and 92% for unknown speakers. The system demonstrates the potential for developing speaker-independent isolated digit speech recognition in Bangla.
Application of Artificial Neural Networking for Determining the Plane of Vibr...IOSRJMCE
In this paper a new approach for Artificial Neural Networking using Feed Forward Back Propagation Method and Levenberg-Marquardt backpropagation training function has been developed using Java Programming, where by directly feeding the RMS and Phase values of vibration, the unbalance plane can be detected with minimum error. In a Machine Fault Simulator RMS value and phase values of vibrations are collected from the four accelerometers placed in X and Y direction of Left and Right Bearings .Further these data are fed into the neural network for training purpose. In the testing phase of the neural network, the plane of vibration has been determined using different training algorithms available in MATLAB. Their prediction values have been compared with the actual value, errors for different training algorithms are calculated and a conclusion has been drawn for the best training function available for this current research work.
This document discusses various types of neural networks including feedback neural networks, self-organizing feature maps, and Hopfield networks. It provides details on Hopfield networks such as their architecture, training and testing algorithms. It also discusses issues like false minima problem in neural networks and techniques to address it like simulated annealing and stochastic update. Furthermore, it covers associative memory models like bidirectional associative memory and self-organizing maps.
This document summarizes research on neural networks. It discusses the basic structure and components of neural networks, including network topology (feed forward and recurrent), transfer functions, and learning algorithms (supervised, unsupervised, reinforcement). It also overview popular neural network models like multilayer perceptrons, radial basis function networks, Kohonen's self-organizing maps, and Hopfield networks. Finally, it outlines some applications of neural networks such as process control, pattern recognition, and more.
The document outlines Adaptive Resonance Theory (ART), a type of neural network invented by Stephen Grossberg in 1976. ART networks aim to solve the stability-plasticity dilemma by allowing plasticity to learn new patterns while maintaining stability of previously learned patterns. The basic ART system consists of a comparison field, recognition field, vigilance parameter, and reset module. The ART algorithm matches input patterns to stored cluster templates, either joining the closest matching cluster or initializing a new one. [/SUMMARY]
A simplified design of multiplier for multi layer feed forward hardware neura...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 describes IntelliSuite's integrated MEMS design flow, which allows users to model devices from the schematic level through physical layout and verification, as well as simulate multi-physics processes. IntelliSuite combines top-down and bottom-up design approaches for efficient and accurate modeling. Key capabilities include schematic capture, physical layout, process simulation, and system-level modeling extraction for fast behavioral simulation.
A Survey on Secure Alternate Path Selection for Enhanced Network Lifetime in ...IRJET Journal
This document summarizes a research paper that proposes techniques to enhance the lifetime of wireless sensor networks. It discusses how sensor nodes closer to the sink node consume more energy transmitting data, creating hotspots and shortening the network's lifetime. To address this, the paper proposes using alternate shortest paths to route data and relocating the sink node when the energy of alternate paths gets low. It also uses elliptic curve cryptography and a hybrid encryption method using AES and ECC to securely transmit data and further increase the network lifetime. Evaluation results show the proposed energy-aware sink relocation technique effectively enhances the network lifetime of wireless sensor networks.
Back propagation networks are neural networks that use a learning algorithm called backpropagation. The key characteristics are:
1. Neurons in one layer connect to all neurons in the next layer.
2. Each neuron has its own input weights.
3. Training involves passing input values through the network layers to calculate the output, then using backpropagation to adjust the weights to reduce error.
4. The network must have at least an input and output layer, with optional hidden layers.
This summary provides an overview of a document describing a teleoperated robot arm and hand system using shared control:
1. The system uses shared control between autonomous control, teleoperation, and simulation modules to coordinate a robot arm, dexterous hand, sensors, and a teleoperated mechanical arm and data glove.
2. Key aspects of the shared control include sensor data sharing between various sensors, multi-agent based sharing to perform complex tasks using different sensors, and human-machine interactive sharing between high-level planning and low-level autonomous control.
3. Experiments showed the system could perform autonomous operations like pushing buttons and twisting objects using vision and force sensors, and the shared control approach was high-
Mixed approach for scheduling process in wimax for high qoseSAT Journals
Abstract
WiMAX(worldwide interoperability for Microwave Access) networks are the networks which are responsible for providing many services like video, data and voice. The WiMAX technology satisfies the modern need of broadband internet through wireless access. For managing all these services through WiMAX, IEEE802.16 gives QOS (Quality of Service) parameter. In WiMAX, a fundamental challenge is to achieve high QOS so that various parameters like waiting time, end to end delay can be minimized and other parameter like execution time and network utilization etc. To obtain high QOS there is scheduling algorithm which is implemented at the base station and subscriber stations. In this paper we discuss scheduling algorithms and also compare the parameters (waiting time, turnaround time, execution time, packet drop age and packet delivery). We purpose a scheduling algorithm which is combination of greedy latency, distance calculation of user from base station, calculate the burst time and apply SJF on that burst values.
Keywords: WiMAX, QOS, IEEE802.16, Scheduling, FCFS (first come first serve), SJF(Shortest job First), Latency.
Analysis of intelligent system design by neuro adaptive control no restrictioniaemedu
This document discusses using neuro-adaptive control to analyze the design of intelligent systems. It begins by introducing the topic and noting that conventional adaptive control techniques assume explicit system models or dynamic structures based on linear models, which may not be valid for complex nonlinear systems. Neural networks and other intelligent control approaches that do not require explicit mathematical modeling are presented as alternatives. The paper then focuses on using time-delay neural networks for system identification and control of nonlinear dynamic systems. Various neural network architectures and learning algorithms for system modeling and control are described.
Analysis of intelligent system design by neuro adaptive controliaemedu
This document summarizes the analysis of intelligent system design using neuro-adaptive control methods. It discusses using neural networks for system identification through series-parallel and parallel models. It also discusses supervised control using a neural network trained by an expert operator, inverse control using a neural network trained on the inverse system model, and neuro-adaptive control using two neural networks - one for system identification and one for control. Neuro-adaptive control allows handling nonlinear system behavior without linear approximations.
Tuning of Proportional Integral Derivative Controller Using Artificial Neural...IRJET Journal
This document discusses tuning a proportional-integral-derivative (PID) controller using an artificial neural network (ANN). Specifically:
1. A PID controller is used to control various process variables like pressure, temperature, and speed. The PID controller gains (KP, KI, KD) are tuned by training an ANN to optimize the controller response.
2. An ANN is trained using the Levenberg-Marquardt algorithm to determine the optimal PID gains. The tuned PID controller results in reduced overshoot, peak value, and settling time compared to the untuned controller.
3. Simulation results show that with ANN tuning, overshoot is reduced from 27.1% to 7
Neural Network Implementation Control Mobile RobotIRJET Journal
This document describes the design and implementation of a neural network controlled mobile robot. The robot is equipped with IR sensors to detect obstacles and a microcontroller runs a neural network program. The neural network is trained offline using a backpropagation algorithm and sensor input patterns to navigate around obstacles. Experimental results showed the robot could successfully react to new obstacle configurations not in its training set. Potential applications of neural networks discussed include industrial process control, sales forecasting, and target marketing. The design could be improved by adding GPS and speed control to allow the robot to navigate to a target destination avoiding obstacles.
International Journal of Computational Engineering Research(IJCER) ijceronline
nternational Journal of Computational Engineering Research (IJCER) is dedicated to protecting personal information and will make every reasonable effort to handle collected information appropriately. All information collected, as well as related requests, will be handled as carefully and efficiently as possible in accordance with IJCER standards for integrity and objectivity.
Design Nonlinear Model Reference with Fuzzy Controller for Nonlinear SISO Sec...IJECEIAES
The document describes a proposed design for a nonlinear model reference controller combined with type-1 and interval type-2 fuzzy control schemes for nonlinear single-input single-output (SISO) systems. The model reference controller is designed based on an optimal desired model and Lyapunov stability theory. Then a type-1 or interval type-2 fuzzy Takagi-Sugeno controller is combined with the model reference controller to improve its performance by reducing steady state error from the system response. The proposed controller is applied to control an inverted pendulum system. Simulation results show that the model reference controller with interval type-2 fuzzy control has better performance than with type-1 fuzzy control.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
IRJET- Power Theft Detection using Probabilistic Neural Network ClassifierIRJET Journal
This document describes a method for detecting power theft using a probabilistic neural network classifier. It begins with an introduction to the problem of power theft in India's transmission and distribution systems. It then provides details on probabilistic neural networks and how they can be used for classification problems. The proposed method trains a PNN to detect normal vs fraudulent customers using training data. It presents a simulation model built in MATLAB/Simulink to test the theft detection algorithm under different scenarios, such as theft occurring at various distances along the distribution line. The results demonstrate that the PNN is able to accurately detect the location of power theft. In conclusion, probabilistic neural networks are effective for power theft detection and location in power distribution systems.
Study on Adaptive PID Control Algorithm Based on RBF Neural NetworkRadita Apriana
Aim at the limitation of traditional PID controller has certain limitation, the traditionalPID control is
often difficult to obtain satisfactory control performance, and the RBF neural networkis difficult to meet the
requirement ofreal-time control system.To overcome it, an adaptive PID control strategy based on (RBF)
neural network isproposed in this paper. The resultsshow that the proposed controller is practical and
effective, because of the adaptability, strong robustness and satisfactory controlperformance.It is also
revealed from simulation results that the proposed control algorithm is valid for DC motor and also
provides the theoretical and experimental basis.
Prediction of stock market index using neural networks an empirical study of...Alexander Decker
This document discusses using neural networks to predict stock market indexes. Specifically, it describes building an Error Correction Network (ECN) model to predict returns of the BSE stock index in India and two major stocks, using both technical and fundamental data as inputs. Daily predictions are made using a standard ECN structure, while weekly predictions use an extended ECN structure. The results for stock predictions are less convincing than for the index, but the ECN outperforms a naive prediction strategy. The document provides mathematical descriptions of ECN models and how they can be used for time series forecasting.
ANFIS Control of Energy Control Center for Distributed Wind and Solar Generat...IRJET Journal
This document describes a proposed system to control distributed wind and solar generators using an artificial neuro fuzzy interface system (ANFIS) within an energy control center (ECC) architecture based on a multi-agent system. The system would use ANFIS within the ECC to monitor voltages from the distributed generators and control circuit breakers connecting the generators to loads or energy storage like batteries. This would allow the system to optimize energy distribution based on generator output. The multi-agent system would include software agents running on different computers to manage each distributed generator and exchange information through the ECC. MATLAB/Simulink would be used to simulate the system and test ANFIS control of connecting generators to loads.
This document presents a study on using a neural network (NN) controlled dynamic voltage restorer (DVR) to mitigate harmonics and improve power quality. The DVR is used to inject compensating voltages and reduce harmonics caused by sensitive loads. The NN controller is trained using the Levenberg Marquardt algorithm. Simulation results show the NN-controlled DVR significantly reduces total harmonic distortion from around 3-4% to below 0.2%. Hardware testing verifies the simulation results and demonstrates effective harmonic mitigation. The study concludes the proposed NN-controlled DVR provides effective compensation of harmonics from sensitive loads to improve power quality.
Efficiency of Neural Networks Study in the Design of TrussesIRJET Journal
The document examines the efficiency of different types of artificial neural networks (ANNs) in the design of trusses. It analyzes generalized regression, radial basis function, and linear layer neural networks using the MATLAB neural network tool. Various truss models are analyzed using the ANNs and STAAD Pro software. The ANNs are trained and tested for interpolation and extrapolation to calculate percentage errors. Parameters like spread constants, number of trainings, number of input/output variables are varied to study their effect on the ANN performance and efficiency. The study aims to determine the most suitable ANN type for truss design based on the percentage error results.
This document describes a study that developed a neuro-fuzzy system for predicting electricity consumption. The neuro-fuzzy system combines the learning capabilities of neural networks with the linguistic rule interpretation of fuzzy inference systems. It was applied to predict future electricity consumption in Northern Cyprus based on past consumption data. The system was trained using a supervised learning algorithm to determine optimal parameters. Simulation results showed the neuro-fuzzy system achieved more accurate predictions of electricity consumption than a neural network model alone, using fewer training epochs.
The document describes a study that uses a hybrid neuro-fuzzy (HNF) approach for automatic generation control (AGC) of a two-area interconnected power system. The HNF controller is designed using an adaptive neuro-fuzzy inference system to control frequency and tie-line power deviations. Simulation results show the HNF controller provides improved dynamic response and faster control compared to a conventional PI controller. The HNF approach can handle non-linearities in power systems while providing faster control than other conventional controllers.
International Journal of Computational Engineering Research (IJCER) ijceronline
This document describes a system for implementing an artificial neuron using an FPGA. The system first converts analog signals from electrochemical sensors to digital signals using a 12-bit analog-to-digital converter (ADC). It then implements the mathematical operations of a neuron in digital logic on the FPGA, including multiplication, accumulation, and an activation function. Simulation and chipscope results are presented which verify the design and operation of the artificial neuron on the FPGA board. The system provides a modular design that could be expanded to create a complete artificial neural network for processing electrochemical sensor data.
11.simulation of unified power quality conditioner for power quality improvem...Alexander Decker
1) The document discusses the simulation of a Unified Power Quality Conditioner (UPQC) using fuzzy logic and neural networks to improve power quality.
2) A UPQC consists of series and shunt active power filters connected back-to-back to compensate voltage sags and current quality problems affecting sensitive loads.
3) Fuzzy logic and neural network controllers are designed for the UPQC and their performance is compared in mitigating voltage sags using Matlab/Simulink simulations. The neural network controller is shown to compensate a higher percentage of voltage sags compared to the fuzzy logic controller.
Simulation of unified power quality conditioner for power quality improvement...Alexander Decker
1) The document discusses the simulation of a Unified Power Quality Conditioner (UPQC) using fuzzy logic and neural networks to improve power quality.
2) A UPQC configuration is presented that uses a fuzzy logic controller and is compared to an artificial neural network controller.
3) Simulation results in Matlab/Simulink show that the fuzzy logic controller compensates 75% of voltage sags during faults while the neural network controller compensates 95% of voltage sags.
Development of a D.C Circuit Analysis Software Using Microsoft Visual C#.NetIOSR Journals
The document describes the development of a DC circuit analysis software called CiRSiS using Microsoft Visual C#.Net. The software can analyze purely resistive planar circuits using mesh and nodal analysis. It displays the current direction in each component as well as a current-voltage-power table for each component. The software was tested on ladder circuits with up to 4 loops and bridge circuits, showing results that correlate 99.3396% with manual calculations, making it reliable for circuit analysis and simulation.
This document describes the development of a DC circuit analysis software called CiRSiS using Microsoft Visual C#.Net. The software can analyze purely resistive planar circuits by calculating the current through each component, voltage across each component, and power dissipated by each component. It also displays the direction of current flow. The software was developed using equations, pseudocode, algorithms, flowcharts, and C# code. Test calculations on sample circuits showed the software results matched manual calculations with an average error of 0.339%, demonstrating the reliability of the software for circuit analysis and simulation.
Similar to Nonlinear autoregressive moving average l2 model based adaptive control of nonlinear arm nerve simulator system (20)
Design and simulation of a steam turbine generator using observer based and l...Mustefa Jibril
Steam turbine generator is an electromechanical system which converts heat energy to electrical energy.
In this paper, the modeling, design and analysis of a simple steam turbine generator have done using
Matlab/Simulink Toolbox. The open loop system have been analyzed to have an efficiency of 76.92 %. Observer
based & linear quadratic regulator (LQR) controllers have been designed to improve the generating voltage.
Comparison of this two proposed controllers have been done for increasing the performance improvement to
generate a 220 Dc volt. The simulation result shows that the steam turbine generator with observer based controller
has a small percentage overshoot with minimum settling time than the steam turbine generator with LQR controller
and the open loop system. Finally, the steam turbine generator with observer based controller shows better
improvement in performance than the steam turbine generator with LQR controller
Modelling design and control of an electromechanical mass lifting system usin...Mustefa Jibril
In this paper, an electromechanical mass lifter system is designed, analyzed and compare using optimal
and robust control theories. LQR and μ -synthesis controllers are used to improve the lift displacement by
comparison method for tracking the desired step and sinusoidal wave signals input. Finally, the comparison
simulation result prove the effectiveness of the electromechanical mass lifter system with μ -synthesis controller for
improving the rise time, percentage overshoot, settling time and peak value of tracking the desired step displacement
signal and improving the peak value for tracking the desired sinusoidal displacement signal with a good
performance.
Tank liquid level control using narma l2 and mpc controllersMustefa Jibril
This document describes a study comparing NARMA-L2 and MPC controllers for controlling liquid level in a tank. A mathematical model of a simple liquid tank system is presented. NARMA-L2 and MPC controllers are designed and their performance is evaluated in MATLAB/Simulink by having the controllers track step and white noise desired liquid level signals. Simulation results show that the tank controlled by the NARMA-L2 controller has better performance than the MPC controller for tracking a step signal, while for tracking a white noise signal the NARMA-L2 controller performs nearly as well as the noise signal itself. The NARMA-L2 controller is concluded to be effective for this liquid level control
Design and simulation of voltage amplidyne system using robust control techniqueMustefa Jibril
In this paper, modelling designing and simulation of a simple voltage amplidyne system is done using
robust control theory. In order to increase the performance of the voltage amplidyne system with H optimal control
synthesis and H optimal control synthesis via-iteration controllers are used. The open loop response of the voltage
amplidyne system shows that the system can amplify the input 7 times. Comparison of the voltage amplidyne
system with H optimal control synthesis and H optimal control synthesis via-iteration controllers to track a desired
step input have been done. Finally, the comparative simulation results prove the effectiveness of the proposed
voltage amplidyne system with H optimal control synthesis controller in improving the percentage overshoot and the
settling time
Design & control of vehicle boom barrier gate system using augmented h 2 ...Mustefa Jibril
A vehicle boom barrier gate system is one of the recently developed technologies operating at the
entrances to the restricted areas. This paper aims to design and control of vehicle’s boom barrier gate system using
robust augmentation technique. 2 H optimal and H synthesis controllers are used to improve the performance of
the system. The open loop response analysis of the vehicle boom barrier gate system shows that the input of the
system need to be improved. Comparison of the vehicle boom barrier gate system with 2 H optimal and H
synthesis controllers have been done to track a set point desired angular position using a step and operational open
and close input signals and a promising results have been observed.
Mechanically actuated capacitor microphone control using mpc and narma l2 con...Mustefa Jibril
In this paper, a capacitor microphone system is presented to improve the conversion of mechanical energy
to electrical energy using a nonlinear auto regressive moving average-L2 (NARMA-L2) and model predictive
control (MPC) controllers for the analysis of the open loop and closed loop system. The open loop system response
shows that the output voltage signal need to be improved. The comparison of the closed loop system with the
proposed controllers have been analyzed and a promising result have been obtained using Matlab/Simulink.
Modeling and simulation of vehicle windshield wiper system using h infinity l...Mustefa Jibril
Vehicle windshield wiper system increases the driving safety by contributing a clear shot viewing to the
driver. In this paper, modelling, designing and simulation of a vehicle windshield wiper system with robust control
theory is done successfully. H loop shaping and robust pole placement controllers are used to improve the
wiping speed by tracking a reference speed signals. The reference speed signals used in this paper are step and sine
wave signals. Comparison of the H loop shaping and robust pole placement controllers based on the two
reference signals is done and convincing results have been obtained. Finally the comparative results prove the
effectiveness of the proposed H Loop Shaping controller to improve the wiping mechanism for the given two
reference signals.
Design and performance investigation of a low cost portable ventilator for co...Mustefa Jibril
In this paper, the design of a low cost portable ventilator with performance analysis have been done to
solve the scarcity of respiratory ventilators for COVID-19 patients. The materials used to build the system are: DC
motor, rotating disc and pneumatic piston. The system input is the patient heart beat and the output is volume of air
to the patient lung with adjusted breathing rate. This ventilator adjusts the breathing rate to the patient depending on
his heart beat rate. The performance analysis of this system have been done using Proportional Integral Derivative
(PID) and Full State Feedback H2 controllers. Comparison of the system with the proposed controllers have been
done using a step change and a random change of the patient heart beat and a promising result have been analyzed
successfully.
Metal cutting tool position control using static output feedback and full sta...Mustefa Jibril
In this paper, a metal cutting machine position control have been designed and simulated using
Matlab/Simulink Toolbox successfully. The open loop response of the system analysis shows that the system needs
performance improvement. Static output feedback and full state feedback H 2 controllers have been used to increase
the performance of the system. Comparison of the metal cutting machine position using static output feedback and
full state feedback H 2 controllers have been done to track a set point position using step and sine wave input signals
and a promising results have been analyzed.
Design and simulation of a steam turbine generator using observer based and l...Mustefa Jibril
Steam turbine generator is an electromechanical system which converts heat energy to electrical energy.
In this paper, the modeling, design and analysis of a simple steam turbine generator have done using
Matlab/Simulink Toolbox. The open loop system have been analyzed to have an efficiency of 76.92 %. Observer
based & linear quadratic regulator (LQR) controllers have been designed to improve the generating voltage.
Comparison of this two proposed controllers have been done for increasing the performance improvement to
generate a 220 Dc volt. The simulation result shows that the steam turbine generator with observer based controller
has a small percentage overshoot with minimum settling time than the steam turbine generator with LQR controller
and the open loop system. Finally, the steam turbine generator with observer based controller shows better
improvement in performance than the steam turbine generator with LQR controller.
Speed control of ward leonard layout system using h infinity optimal controlMustefa Jibril
In this paper, modelling designing and simulation of a Ward Leonard layout system is done using
robust control theory. In order to increase the performance of the Ward Leonard layout system
with H optimal control synthesis and H optimal control synthesis via -iteration controllers
are used. The open loop response of the Ward Leonard layout system shows that the system needs
to be improved. Comparison of the Ward Leonard layout system with H optimal control
synthesis and H optimal control synthesis via -iteration controllers to track a desired step speed
input have been done. Finally, the comparative simulation results prove the effectiveness of the
proposed Ward Leonard layout system with H optimal control synthesis controller in improving
the percentage overshoot and the settling time.
Tank liquid level control using narma l2 and mpc controllersMustefa Jibril
Liquid level control is highly important in industrial applications such as boilers in nuclear power
plants. In this paper a simple liquid level tank is designed based on NARMA-L2 and Model
Predictive control controllers. The simple water level tank has one input, liquid flow inn and one
output, liquid level. The proposed controllers is compared in MATLAB and then simulated in
Simulink to test how the system actual liquid level track the desired liquid level with two input
desired signals (step and white noise). The response of the NARMA-L2 controller is then
compared with a MPC controller. The results are shown sequentially and the effectiveness of the
controller is illustrated.
Performance investigation of hydraulic actuator based mass lift system using ...Mustefa Jibril
A hydraulic actuator is a system that can provide a large power amplification in industries and
factories. In this paper, mass lifter hydraulic actuator system to a desired displacement is designed
using optimal control theory. MPC and LQR controllers are used to design and improve the
performance of the hydraulic actuator. The hydraulic actuator system is linearized using Taylor
series linearization method and designed using Matlab/Simulink tool. Comparison of the hydraulic
actuator with MPC and LQR controllers using three desired output displacement signals (step, sine
wave and white noise) is done and simulation results have been analyzed successfully. For the
desired step input signal, the hydraulic actuator system with MPC controller lower rise and settling
times with small percentage overshoot as compared to the hydraulic actuator system with LQR
controller and for the desired sine wave signal, the hydraulic actuator system with MPC controller
almost track the desired sine wave input signal correctly as compared to the hydraulic actuator
system with LQR controller. While for the desired white noise input signal, the hydraulic actuator
system with MPC controller have tried to track the desired white noise input signal with small
variation in amplitude as compared to the hydraulic actuator system with LQR controller. Finally
the comparative simulation results prove the effectiveness of the proposed hydraulic actuator
system with MPC controller.
Modelling design and control of an electromechanical mass lifting system usin...Mustefa Jibril
In this paper, an electromechanical mass lifter system is designed, analyzed and compare using
optimal and robust control theories. LQR and μ -synthesis controllers are used to improve the lift
displacement by comparison method for tracking the desired step and sinusoidal wave signals
input. Finally, the comparison simulation result prove the effectiveness of the electromechanical
mass lifter system with μ -synthesis controller for improving the rise time, percentage overshoot,
settling time and peak value of tracking the desired step displacement signal and improving the
peak value for tracking the desired sinusoidal displacement signal with a good performance.
Comparison of a triple inverted pendulum stabilization using optimal control ...Mustefa Jibril
In this paper, modelling design and analysis of a triple inverted pendulum have been done using
Matlab/Script toolbox. Since a triple inverted pendulum is highly nonlinear, strongly unstable
without using feedback control system. In this paper an optimal control method means a linear
quadratic regulator and pole placement controllers are used to stabilize the triple inverted
pendulum upside. The impulse response simulation of the open loop system shows us that the
pendulum is unstable. The comparison of the closed loop impulse response simulation of the
pendulum with LQR and pole placement controllers results that both controllers have stabilized
the system but the pendulum with LQR controllers have a high overshoot with long settling time
than the pendulum with pole placement controller. Finally the comparison results prove that the
pendulum with pole placement controller improve the stability of the system.
Design and simulation of a steam turbine generator using observer based and l...Mustefa Jibril
Steam turbine generator is an electromechanical system which converts heat energy to electrical
energy. In this paper, the modelling, design and analysis of a simple steam turbine generator have
done using Matlab/Simulink Toolbox. The open loop system have been analyzed to have an
efficiency of 76.92 %. Observer based & linear quadratic regulator (LQR) controllers have been
designed to improve the generating voltage. Comparison of this two proposed controllers have
been done for increasing the performance improvement to generate a 220 Dc volt. The simulation
result shows that the steam turbine generator with observer based controller has a small percentage
overshoot with minimum settling time than the steam turbine generator with LQR controller and
the open loop system. Finally, the steam turbine generator with observer based controller shows
better improvement in performance than the steam turbine generator with LQR controller.
Design and control of steam flow in cement production process using neural ne...Mustefa Jibril
In this paper a NARMA L2, model reference and neural network predictive controller is utilized in order to control the output flow rate of the steam in furnace by controlling the steam flow valve. The steam flow control system is basically a feedback control system which is mostly used in cement production industries. The design of the system with the proposed controllers is done with Matlab/Simulink toolbox. The system is designed for the actual steam flow output to track the desired steam that is given to the system as input for two desired steam input signals (step and sine wave). In order to analyze the performance of the system, comparison of the proposed controllers is done by simulating the system for the two reference signals for the system with and without sensor noise disturbance. Finally the comparison results prove the effectiveness of the presented process control system with model reference controller.
Body travel performance improvement of space vehicle electromagnetic suspensi...Mustefa Jibril
Electromagnetic suspension system (EMS) is mostly used in the field of high-speed vehicle. In this paper, a space exploring vehicle quarter electromagnetic suspension system is modelled, designed and simulated using linear quadratic optimal control problem. Linear quadratic Gaussian and linear quadratic integral controllers are designed to improve the body travel of the vehicle using bump road profile. Comparison between the proposed controllers is done and a promising simulation result have been analyzed.
Quarter car active suspension systemdesign using optimal and robust control m...Mustefa Jibril
This document describes the design of optimal and robust controllers for a quarter car active suspension system. It first presents the mathematical model of a quarter car system and describes various road disturbances that could be used as inputs, including bumps, random variations, sine waves, and white noise. Then it details the design of a μ-synthesis controller using robust control methods and an LQR controller using optimal control methods. Various performance metrics are evaluated through simulation against the different road disturbances. The results show that the active suspension system with a μ-synthesis controller provides the best overall performance compared to the LQR controller design.
Comparison of active and semi active suspension systems using robust controllerMustefa Jibril
1. The document compares active and semi-active suspension systems using robust H-infinity controllers. Mathematical models of quarter car active and semi-active suspension systems are developed.
2. Simulation results show that the active suspension system with H-infinity controller decreases body acceleration and maintains suspension deflection and body travel outputs, proving its effectiveness over the semi-active system.
3. Numerical results confirm that the active suspension system provides minimum body travel and acceleration amplitudes, while matching the suspension deflection to the road profile, achieving the control targets.
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Sinan KOZAK
Sinan from the Delivery Hero mobile infrastructure engineering team shares a deep dive into performance acceleration with Gradle build cache optimizations. Sinan shares their journey into solving complex build-cache problems that affect Gradle builds. By understanding the challenges and solutions found in our journey, we aim to demonstrate the possibilities for faster builds. The case study reveals how overlapping outputs and cache misconfigurations led to significant increases in build times, especially as the project scaled up with numerous modules using Paparazzi tests. The journey from diagnosing to defeating cache issues offers invaluable lessons on maintaining cache integrity without sacrificing functionality.
International Conference on NLP, Artificial Intelligence, Machine Learning an...gerogepatton
International Conference on NLP, Artificial Intelligence, Machine Learning and Applications (NLAIM 2024) offers a premier global platform for exchanging insights and findings in the theory, methodology, and applications of NLP, Artificial Intelligence, Machine Learning, and their applications. The conference seeks substantial contributions across all key domains of NLP, Artificial Intelligence, Machine Learning, and their practical applications, aiming to foster both theoretical advancements and real-world implementations. With a focus on facilitating collaboration between researchers and practitioners from academia and industry, the conference serves as a nexus for sharing the latest developments in the field.
UNLOCKING HEALTHCARE 4.0: NAVIGATING CRITICAL SUCCESS FACTORS FOR EFFECTIVE I...amsjournal
The Fourth Industrial Revolution is transforming industries, including healthcare, by integrating digital,
physical, and biological technologies. This study examines the integration of 4.0 technologies into
healthcare, identifying success factors and challenges through interviews with 70 stakeholders from 33
countries. Healthcare is evolving significantly, with varied objectives across nations aiming to improve
population health. The study explores stakeholders' perceptions on critical success factors, identifying
challenges such as insufficiently trained personnel, organizational silos, and structural barriers to data
exchange. Facilitators for integration include cost reduction initiatives and interoperability policies.
Technologies like IoT, Big Data, AI, Machine Learning, and robotics enhance diagnostics, treatment
precision, and real-time monitoring, reducing errors and optimizing resource utilization. Automation
improves employee satisfaction and patient care, while Blockchain and telemedicine drive cost reductions.
Successful integration requires skilled professionals and supportive policies, promising efficient resource
use, lower error rates, and accelerated processes, leading to optimized global healthcare outcomes.
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.
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTjpsjournal1
The rivalry between prominent international actors for dominance over Central Asia's hydrocarbon
reserves and the ancient silk trade route, along with China's diplomatic endeavours in the area, has been
referred to as the "New Great Game." This research centres on the power struggle, considering
geopolitical, geostrategic, and geoeconomic variables. Topics including trade, political hegemony, oil
politics, and conventional and nontraditional security are all explored and explained by the researcher.
Using Mackinder's Heartland, Spykman Rimland, and Hegemonic Stability theories, examines China's role
in Central Asia. This study adheres to the empirical epistemological method and has taken care of
objectivity. This study analyze primary and secondary research documents critically to elaborate role of
china’s geo economic outreach in central Asian countries and its future prospect. China is thriving in trade,
pipeline politics, and winning states, according to this study, thanks to important instruments like the
Shanghai Cooperation Organisation and the Belt and Road Economic Initiative. According to this study,
China is seeing significant success in commerce, pipeline politics, and gaining influence on other
governments. This success may be attributed to the effective utilisation of key tools such as the Shanghai
Cooperation Organisation and the Belt and Road Economic Initiative.
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.
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
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
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
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.
Embedded machine learning-based road conditions and driving behavior monitoring
Nonlinear autoregressive moving average l2 model based adaptive control of nonlinear arm nerve simulator system
1. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[159]
NONLINEAR AUTOREGRESSIVE MOVING AVERAGE-L2
MODEL BASED ADAPTIVE CONTROL OF NONLINEAR ARM NERVE
SIMULATOR SYSTEM
Mustefa Jibril*1
, EliyasAlemayehu Tadese*2
, Abu Fayo*3
*1
Msc, Dept. of Electrical & Computer Engineering, Dire Dawa Institute of Technology, DireDawa, Ethiopia
*2
Msc, Faculty of Electrical & Computer Engineering, Jimma Institute of Technology, Jimma, Ethiopia
*3
Msc, Faculty of Electrical & Computer Engineering, Jimma Institute of Technology, Jimma, Ethiopia
ABSTRACT
This paper considers the trouble of the usage of approximate strategies for realizing the neural controllers for
nonlinear SISO systems. In this paper, we introduce the nonlinear autoregressive moving average (NARMA-L2)
model which might be approximations to the NARMA model. The nonlinear autoregressive moving average
(NARMA-L2) model is an precise illustration of the input–output behavior of finite-dimensional nonlinear discrete
time dynamical systems in a neighborhood of the equilibrium state. However, it isn't always handy for purposes of
neural networks due to its nonlinear dependence on the manipulate input. In this paper, nerves system based arm
position sensor device is used to degree the precise arm function for nerve patients the use of the proposed systems.
In this paper, neural network controller is designed with NARMA-L2 model, neural network controller is designed
with NARMA-L2 model system identification based predictive controller and neural network controller is designed
with NARMA-L2 model based model reference adaptive control system. Hence, quite regularly, approximate
techniques are used for figuring out the neural controllers to conquer computational complexity. Comparison were
made among the neural network controller with NARMA-L2 model, neural network controller with NARMA-L2
model system identification based predictive controller and neural network controller with NARMA-L2 model
reference based adaptive control for the preferred input arm function (step, sine wave and random signals). The
comparative simulation result shows the effectiveness of the system with a neural network controller with NARMA-
L2 model based model reference adaptive control system.
Keywords- Nonlinear autoregressive moving average, neural network, Model reference adaptive control, Predictive
controller
I. INTRODUCTION
The neural network pattern tins be used in dominion strategies that require a global creation of the diagram forward
or inverse dynamics, and these form are available in the example of neural networks, which have been trained using
neural based design discovery techniques. The generalized teaching dresser attempts to crops the inverse of a
fortification over the entire kingdom crack using off-line training while in the specialized configuration the
convention is on-line and uses incorrectness back dispersal through the movement to learn the protocol inverse
liveliness over a small operating region. The global firmness of the closed-loop response design is guaranteed
provided the arrangement of the robot-manipulator action phrase is exact. Generalization of the director over the
desired path breach has been established using an on-line weight education scheme. The advantage of a neuron-
adaptive hybrids mastery scheme is the high accuracy and computationally less intensive proficiency scheme.
II. SYSTEM DISCRIPTION
A. Nerves System Based Arm Position Sensor System Description
Nerves system based arm position sensor is a device which senses the electrical pulse signal of the nerve and
compares the desired arm position and response arm position of the nerve defected arm. Nerves system based arm
2. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[160]
position sensor is a type of neuro modulation therapy in which electrodes are surfacely placed next to a selected
peripheral nerve considered to be the source of nerve pain. One way of trying to control the arm position is that
arises from peripheral nerves calls for a device that sends low levels of electricity to stimulate part(s) of the nerve.
This electrical voltage is thought to interfere with how the nerve transmits the voltage impulse signals and response
through arm motion.
The mathematical description of the system is shown bellow
2 2
2
1
d y t v t dy t
dt s y t s dt
Where
y(t) Arm position output
v(t) Impulse voltage input
γ Arm position acceleration
s Device sensitivity function
α Nerve transmission coefficient
β Nerve delay coefficient
The block diagram of the nerves system based arm position sensor device is shown in Figure 1 bellow.
Fig. 1. Block diagram of the nerves system based arm position sensor device
B. Design of NARMA-L2 Neural Network Controller
The neuro controller described on this phase is cited through two different names: response linearization control and
NARMA-L2 manipulate. It is known as comments linearization when the plant shape has a specific form (associate
form). It is known as NARMA-L2 manipulate while the fortification mold may be approximated by using the same
form. The vital principle of this type of control is to convert nonlinear designsystem into linear dynamics with the
aid of canceling the nonlinearities. This phase starts off evolved with the aid of submitting the associate system form
and presentation how you may use a neural community to become aware of this model. Then it describes how the
identified neural network model may be used to broaden a controller.
3. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[161]
1) Identification of the NARMA-L2 Model: The first step in the use of feedback linearization (or NARMA-L2)
manipulate is to identify the design to be controlled. You train a neural network to represent the forward dynamics
of the system.
The first step is to pick out a styles association to use. One standard patterns this is used to symbolize fashionable
discrete-time nonlinear system is the nonlinear autoregressive-moving average (NARMA) model:
, 1 ,..., 1 , , 1 ,...., 1 2y k d N y k y k y k n u k u k u k n
Where u(k) is the system input, and y(k) is the Where u(k) is the system input, and y(k) is the system output. For the
identification section, you can teach a neural network to approximate the nonlinear function N. If you want the
system output to follow some reference trajectory y (k + d) = yr(k + d) the subsequent step is to expand a nonlinear
controller of the form:
, 1 ,..., 1 , , 1 ,...., 1 3ru k G y k y k y k n y k d u k u k m
The trouble with the usage of this controller is that in case you need to teach a neural network to create the
characteristic G to minimize mean square blunders, you need to apply dynamic returned propagation. This can be
pretty sluggish. One answer is to apply approximate models to symbolize the system. The controller used on this
section is based totally at the NARMA-L2 approximate model:
, 1 ,.., , 1 ,.., 1 ,
ˆ 4
1 , 1 ,.., 1 1 ,.., 1
y k y k y k y k y k n
y k d f g u k
y k n u k u k m u k u k m
This model is in associate shape, wherein the next controller inputu(k) is not contained in the nonlinearity. The gain
of this form is that you could resolve for the control input that causes the system output to comply with the reference
y (k + d) = yr(k + d). The resulting controller would have the form
, 1 ,..., 1 , 1 ,...., 1
5
, 1 ,..., 1 , 1 ,...., 1
ry k d f y k y k y k n u k u k n
u k
g y k y k y k n u k u k n
Using this equation immediately can motive awareness problems, due to the fact you ought to determine the control
input u(k) primarily based on the output at the same time, y(k). So, rather, use the model
, 1 ,.., 1 , , 1 ,..,
1 6
1 ,.., 1 1 , 1 ,.., 1
y k y k y k n y k y k y
y k d f g u k
u k u k m k n u k u k m
Where d ≥ 2. Figure 2 shows the structure of a neural network representation
4. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[162]
Fig. 2. The structure of a neural network representation.
Using the NARMA-L2 model, you can obtain the controller
, 1 ,..., 1 , ,...., 1
1 7
, 1 ,..., 1 , ,...., 1
ry k d f y k y k y k n u k u k n
u k
g y k y k y k n u k u k n
Which is realizable for d ≥ 2. Figure 3 shows the block diagram of the NARMA-L2 controller.
Fig. 3. Block diagram of the NARMA-L2 controller
This controller can be implemented with the formerly diagnosed NARMA-L2 plant model, as shown in Figure 4
below.
5. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[163]
Fig. 4. Previously identified NARMA-L2 plant model
C. Design of NARMA-L2 Model Controller Using SystemIdentification
The NARMA-L2 based neural network predictive controller makes use of a neural network model of a nonlinear
plant to expect future plant performance. The controller then calculates the control input that will optimize plant
performance over a targeted destiny time horizon. The first step in model predictive control is to determine the
neural network plant model. Next, the plant model is utilized by the controller to predict future performance.
1) System Identification:
The first stage of model NARMAL2 based predictive controller is to train a neural network to symbolize the ahead
dynamics of the plant. The prediction errors among the plant output and the neural network output is used as the
neural network education signal. The method is shown in Figure 5 below:
Fig. 5. The process of training model predictive control
The neural network plant model uses preceding inputs and former plant outputs to be expecting destiny values of the
plant output. The structure of the neural network plant model is given in Figure 6 bellow.
6. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[164]
Fig. 6. The structure of the neural network plant model
2) Predictive Control:
The model predictive control technique is based totally on the receding horizon method. The neural network model
predicts the plant reaction over a unique time horizon. The predictions are used by a numerical optimization
software to decide the control signal that minimizes the following performance criterion over the required horizon
2
1
2 ' ' 2
m
1
( ( ) y ( )) ( ( 1) u (k+j 2))- - - - 8
uNN
r
j N j
J y k j k j u k j
Where N1, N2, and Nu define the horizons over which the tracking blunders and the manage increments are
evaluated. The u´ variable is the tentative control signal, yr is the preferred response, and ym is the network model
reaction. The cost determines the contribution that the sum of the squares of the control increments has on the
performance index.
The following block diagram illustrates the model predictive control method. The controller consists of the neural
network plant model and the optimization block. The optimization block determines the values of u´ that limit J,
after which the top of the line u is input to the plant.
Fig. 7. Block diagram of the model predictive control process
7. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[165]
D. Design of NARMA-L2 Model Controller Using AdaptiveControl
The NARMA-L2 based neural model reference adaptive control structure uses neural networks: a controller network
and a plant model network, as shown in Figure 8 below. The plant model is identified first, and then the controller is
trained in order that the plant output follows the reference model output.
Fig. 8. Block diagram of controller network and a plant model network
Figure 9 indicates the info of the neural network plant model and the neural network controller. Each network has
two layers, and you can pick out the quantity of neurons to use within the hidden layers. There are three units of
controller inputs:
Delayed reference inputs
Delayed controller outputs
Delayed plant outputs
For each of those inputs, you can select the variety of delayed values to apply. Typically, the variety of delays
increases with the order of the plant. There are two sets of inputs to the neural network plant model: Delayed
controller outputs
Delayed plant outputs
Fig. 9. The neural network plant model and the neural network controller
8. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[166]
III. RESULT AND DISSCUSION
This chapter basically focuses on the comparison of neural network controller with NARMA-L2 model, neural
network controller with NARMA-L2 model system identification based predictive controller and neural network
controller with NARMA-L2 model based model reference adaptive control . These three systems input is the desired
arm position and they generate impulse voltage signal to be given to the arm and the arm deliver arm output
position. These three systems tested with step, sine wave and random desired arm position signal.
A. Comparison of the Proposed Controllers using step input signal
The Simulink model for the comparison of neural network controller with NARMA-L2 model, neural network
controller with NARMA-L2 model system identification based predictive controller and neural network controller
with NARMA-L2 model based model reference adaptive control using step input signal is shown in the Figure 10
bellow
Fig. 10. Step response Simulink model
The simulation output for the comparison of the neural network controller with NARMA-L2 model, neural network
controller with NARMA-L2 model system identification based predictive controller and neural network controller
with NARMA-L2 model based model reference adaptive control using step input signal is shown in the Figure 11
bellow.
Fig. 11. Step response simulation result
9. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[167]
The neural network controller with NARMA-L2 controller has a high percentage overshoot and since the step input
signal is the desired arm position of the patient and the output of this controller has a steady state value of 0.5 m
while the desired arm position is 1m. This show us that the neural network controller with NARMA-L2 controller
does not feed enough nerve impulse voltage to the nerve of the arm. The neural network controller with NARMA-
L2 model system identification based predictive controller has a bigger percentage overshoot and since the step
input signal is the desired arm position of the patient and the output of this controller has a steady state value of 1.75
m while the desired arm position is 1m. This show us that the neural network controller with NARMA-L2 model
system identification based predictive controller feed excess nerve impulse voltage to the nerve of the arm. The
neural network controller with NARMAL2 model based model reference adaptive control has a no percentage
overshoot and since the step input signal is the desired arm position of the patient and the output of this controller
has the same steady state value of 1 m with the desired arm position. This show us that the neural network controller
with NARMA-L2 model based model reference adaptive control gives the exact nerve impulse voltage to the nerve
of the arm.
B. Comparison of the Proposed Controllers using Sine Wave Input Signal
The Simulink model for the comparison of neural network controller with NARMA-L2 model, neural network
controller with NARMA-L2 model system identification based predictive controller and neural network controller
with NARMA-L2 model based model reference adaptive control using sine wave input signal is shown in the Figure
12 bellow
Fig. 12. Sine wave response Simulink model
The simulation output for the comparison of the neural network controller with NARMA-L2 model, neural network
controller with NARMA-L2 model system identification based predictive controller and neural network controller
with NARMA-L2 model based model reference adaptive control using sine wave input signal is shown in the Figure
13 bellow
10. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[168]
Fig. 13. Sine wave response simulation result
The neural network controller with NARMA-L2 controller sine wave input signal is the desired arm position of the
patient and the output of this controller has a peak value of 0.6 m while the desired arm position is 1m. This show us
that the neural network controller with NARMA-L2 controller gives low impulse voltage to the nerve of the arm.
The neural network controller with NARMA-L2 model system identification based predictive controller sine wave
input signal is the desired arm position of the patient and the output of this controller has a peak value of 2.1 m
while the desired arm position is 1m. This show us that the neural network controller with NARMA-L2 model
system identification based predictive controller feed excess nerve impulse voltage to the nerve of the arm. The
neural network controller with NARMA-L2 model based model reference adaptive control sine wave input signal is
the desired arm position of the patient and the output of this controller has a peak value of 0.8 m while the desired
arm position is 1m. This show us that the neural network controller with NARMA-L2 model based model reference
adaptive control gives almost the exact nerve impulse voltage to the nerve of the arm.
C. Comparison of the Proposed Controllers using Random Input Signal
The Simulink model for the comparison of neural network controller with NARMA-L2 model, neural network
controller with NARMA-L2 model system identification based predictive controller and neural network controller
with NARMA-L2 model based model reference adaptive control using random input signal is shown in the Figure
14 bellow
Fig. 14. Random input response Simulink model
11. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[169]
The simulation output for the comparison of the neural network controller with NARMA-L2 model, neural network
controller with NARMA-L2 model system identification based predictive controller and neural network controller
with NARMA-L2 model based model reference adaptive control using random input signal is shown in the Figure
15 bellow
Fig. 15. Random input response simulation result
The neural network controller with NARMA-L2 controller random input signal is the desired arm position of the
patient and the output of this controller has a peak value of 4.4 m while the desired arm position is 3.5m. This show
us that the neural network controller with NARMA-L2 controller gives high impulse voltage to the nerve of the arm.
The neural network controller with NARMA-L2 model system identification based predictive controller random
input signal is the desired arm position of the patient and the output of this controller has a peak value of 8.5 m
while the desired arm position is 3.5 m. This show us that the neural network controller with NARMA-L2 model
system identification based predictive controller feed excess nerve impulse voltage to the nerve of the arm. The
neural network controller with NARMA-L2 model based model reference adaptive control random input signal is
the desired arm position of the patient and the output of this controller has a peak value of 3.5 m while the desired
arm position is 3.5 m. This show us that the neural network controller with NARMA-L2 model based model
reference adaptive control gives the exact nerve impulse voltage to the nerve of the arm.
D. Numerical Value Comparison of the proposed systems
The numerical value comparison of the proposed systems is shown in the Table 1 bellow.
Table 1 Numerical Value Comparison of the Proposed Systems
No System Step Sine
wave
Random
1 Desired Arm
Position
1 1 3.5
2 NARMA-L2
model
0.5 0.6 4.4
3 Model
reference
1 0.8 3.5
4 Predictive
controller
1.75 2.1 8.5
The result from Table 1 shows us that the neural network controller with NARMA-L2 model based model reference
adaptive control show the best response.
12. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[170]
IV. CONCLUSION
In this thesis, nerves system based arm position sensor device is used to measure the exact arm position for nerve
patients using the proposed systems. Three different systems are proposed which are a neural network controller is
designed with NARMA-L2 model, neural network controller is designed with NARMA-L2 model system
identification based predictive controller and neural network controller is designed with NARMA-L2 model based
model reference adaptive control system.
The proposed controllers are tested for comparing the actual and desired arm position of the nerves system based
arm position sensor device for three desired arm position inputs (step, sine wave and random).
The simulation result for a step input signals shows that the neural network controller with NARMA-L2 controller
feeds a high impulse voltage to the nerve of the arm and the neural network controller with NARMA-L2 model
system identification based predictive controller feed excess nerve impulse voltage to the nerve of the arm and the
neural network controller with NARMA-L2 model based model reference adaptive control gives the exact nerve
impulse voltage to the nerve of the arm.
The simulation result for a sine wave input signals shows that the neural network controller with NARMA-L2
controller gives high nerve impulse voltage to the nerve of the arm and the neural network controller with NARMA-
L2 model system identification based predictive controller feed excess nerve impulse voltage to the nerve of the arm
and the neural network controller with NARMA-L2 model based model reference adaptive control gives the exact
nerve impulse voltage to the nerve of the arm.
The simulation result for a random input signals shows that the neural network controller with NARMA-L2
controller gives high nerve impulse voltage to the nerve of the arm and the neural network controller with NARMA-
L2 model system identification based predictive controller feed excess nerve impulse voltage to the nerve of the arm
and the neural network controller with NARMA-L2 model based model reference adaptive control gives the exact
nerve impulse voltage to the nerve of the arm.
Finally, the comparative simulation result prove the effectiveness of the presented neural network controller with
NARMAL2 model based model reference adaptive control and it achieves to balance between the actual and desired
arm position tests for the nerve patient by adjusting the nerve impulse voltage given to the arm.
V. REFERENCES
[1]. T. A. Al-Zohary “Adaptive Control of Nonlinear Multivariable Systems Using Neural Networks and
Approximate Models” Computer and Systems Eng. Dept. Fac. Of Eng. Ain Shams University, 2018.
[2]. Yousif Al-Dunainawi “A New MIMO ANFIS-PSO Based NARMA-L2 Controller for Nonlinear Dynamic
Systems” IEEE Control Syst. Soc., vol. 1, p. 246, 2017.
[3]. Cidambaram Vijay Nagaraj “Design of Buck Boost Converter for Nonlinear Systems using Adaptive
Controller” Engineering and Technology, Pudukkottai-622507, Tamil Nadu, India, 2017.
[4]. Mehdi Ramezani “Design of NARMA L-2 Control of Nonlinear Inverted Pendulum” International Research
Journal of Applied and Basic Sciences, 2016
[5]. NgocKhoat Nguyen “An Investigation of Intelligent Controllers Based on Fuzzy Logic and Artificial Neural
Network for Power System Frequency Maintenance” Turkish Journal of Electrical Engineering & Computer
Sciences, (2016) 24: 2893 – 2909.
[6]. DhanrajSuman “Implementation of Narma-L2 Controller for Magnetic Levitation System” 6th
international
conference on science technology and management, 04 Dec, 2016.
13. e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
Volume:02/Issue:03/March-2020 www.irjmets.com
www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[171]
[7]. Pratik Ghutke “Performance Analysis of Neural Network Based Narma Control for CSTR” International
Journal for Innovative Research in Science & Technology| Volume 1 | Issue 8 | January 2015.
[8]. Cabrera, J. B. D. and Narendra, K. S., "On Regulation and Tracking in Nonlinear Discrete” Univ., New Haven,
CT, Tech. Rep, 2015.
[9]. Cabrera, J. B. D. and Narendra, K. S., "On Regulation and Tracking in Nonlinear Discrete” Univ., New Haven,
CT, Tech. Rep, 2015.
[10]. Priyanka Sharma “NARMA-L2 Controller for Five-Area Load Frequency Control” Int. Jour. of App. Sc. and
Eng. (IJASE) 2(2): Dec 2014, 91-101.
[11]. RazikaZamoumBoushaki “Artificial Neural Network Control of the Recycle Compression System” Studies in
Informatics and Control, Vol. 23, No. 1, March 2014.
[12]. Priyanka Sharma “NARMA-L2 Controller for Five-Area Load Frequency Control” Proceedings of the IEEE
2014; 121(7):601–8.