In this paper, an accurate method for determination of fault location and fault type in power distribution systems by neural network is proposed. This method uses neural network to classify and locate normal and composite types of faults as phase to earth, two phases to earth, phase to phase. Also this method can distinguish three phase short circuit from normal network position. In the presented method, neural network is trained by αβ space vector parameters. These parameters are obtained using clarke transformation. Simulation results are presented in the MATLAB software. Two neural networks (MLP and RBF) are investigated and their results are compared with each other. The accuracy and benefit of the proposed method for determination of fault type and location in distribution power systems has been shown in simulation results.
Fault detection and diagnosis ingears using wavelet enveloped power spectrum ...eSAT Journals
Abstract In this work, automatic detection and diagnosis of gear condition monitoring technique is presented. The vibration signals in time domain wereobtained from a fault simulator apparatus from a healthy gear and an induced faulty gear. These time domain signals were processed using Laplace and Morlet wavelet based enveloped power spectrum to detect the faults in gears. The vibration signals obtained were filtered to enhance the signal components before the application of wavelet analysis. The time and frequency domain features extracted from Laplace wavelet based wavelet transform are used as input to ANN for gear fault classification. Genetic algorithm was used to optimize the wavelet and ANN classification parameters. The result shows the successful classification of ANN test process. Index Terms:Continuous wavelet transform, Envelope power spectrum, Wavelet, Filtering, ANN.
COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN NEURAL NETWORK BASED IDENT...ijcsit
This paper explores the application of artificial neural networks for online identification of a multimachine power system. A recurrent neural network has been proposed as the identifier of the two area, four machine system which is a benchmark system for studying electromechanical oscillations in multimachine power systems. This neural identifier is trained using the static Backpropagation algorithm. The emphasis of the paper is on investigating the performance of the variants of the Backpropagation algorithm in training the neural identifier. The paper also compares the performances of the neural identifiers trained using variants of the Backpropagation algorithm over a wide range of operating conditions. The simulation results establish a satisfactory performance of the trained neural identifiers in identification of the test power system.
IRJET- A Review on SVM based Induction MotorIRJET Journal
This document summarizes several research papers on using support vector machines (SVMs) and other machine learning techniques for fault detection in induction motors. Specifically:
1. It discusses using an artificial immune system-optimized SVM for detecting broken rotor bars and stator faults in induction motors based on motor current data.
2. It describes using wavelet analysis, principal component analysis, and SVM classification to detect faults like frequency variations, unbalanced voltages, and interturn shorts based on motor current spectra.
3. It proposes using dq0 voltage components analyzed with fast Fourier transforms as features for an SVM classifier to detect stator winding shorts, achieving over 98% accuracy.
The power supply system is completely hooked into three major parts. First one is generation, second one is
transmission and the last one is distribution of electricity supply at the range of 415V to 400V approx. But while
the fault occurs it affects other lines additionally, and this causes difficulties for local people and additionally
perturb the flow of current in different areas. This eccentric and perturbed supply of nuisance is very
hazardous as it cannot be ceased when it comes to equal distribution of electricity. The area suffering from
faults and the other both get affected. So to stop all these we have implemented this project of Coordination of
over current relay utilising optimisation technique. We have utilised crow search algorithms with Kennedy as
swarm perspicacity algorithms which are very auxiliary in storing excess electricity supply and can be used
when needed. With the avail of this we can renovate the potency supply and this will conclusively implement
our main objective of this project.
A real-time fault diagnosis system for high-speed power system protection bas...IJECEIAES
This paper puts forward a real-time smart fault diagnosis system (SFDS) intended for high-speed protection of power system transmission lines. This system is based on advanced signal processing techniques, traveling wave theory results, and machine learning algorithms. The simulation results show that the SFDS can provide an accurate internal/external fault discrimination, fault inception time estimation, fault type identification, and fault location. This paper presents also the hardware requirements and software implementation of the SFDS.
Performance evaluation of ann based plasma position controllers for aditya to...IAEME Publication
This paper evaluates the performance of artificial neural network (ANN) based plasma position controllers for the Aditya tokamak device. Radial basis function networks and generalized recurrent neural networks are developed as controllers and their performance is compared to an existing backpropagation network controller. Training data for the ANNs comes from the Aditya RZIP model. Testing shows the backpropagation network provides better performance in terms of signal-to-noise ratio and root mean square error compared to the other controllers. Further testing on actual plasma discharge data from Aditya is recommended, as well as exploring neuro-fuzzy controllers for plasma position control.
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
Softmax function is an integral part of object detection frameworks based on most deep or shallow neural
networks. While the configuration of different operation layers in a neural network can be quite different,
softmax operation is fixed. With the recent advances in object detection approaches, especially with the
introduction of highly accurate convolutional neural networks, researchers and developers have suggested
different hardware architectures to speed up the overall operation of these compute-intensive algorithms.
Xilinx, one of the leading FPGA vendors, has recently introduced a deep neural network development kit for
exactly this purpose. However, due to the complex nature of softmax arithmetic hardware involving
exponential function, this functionality is only available for bigger devices. For smaller devices, this operation is
bound to be implemented in software. In this paper, a light-weight hardware implementation of this function
has been proposed which does not require too many logic resources when implemented on an FPGA device.
The proposed design is based on the analysis of the statistical properties of a custom convolutional neural
network when used for classification on a standard dataset i.e. CIFAR-10. Specifically, instead of using a brute
force approach to design a generic full precision arithmetic circuit for SoftMax function using real numbers, an
approximate integer-only design has been suggested for the limited range of operands encountered in realworld
scenario. The approximate circuit uses fewer logic resources since it involves computing only a few
iterations of the series expansion of exponential function. However, despite using fewer iterations, the function
has been shown to work as good as the full precision circuit for classification and leads to only minimal error
being introduced in the associated probabilities. The circuit has been synthesized using Hardware Description
Language (HDL) Coder and Vision HDL toolboxes in Simulink® by Mathworks® which provide higher level
abstraction of image processing and machine learning algorithms for quick deployment on a variety of target
hardware. The final design has been implemented on a Xilinx FPGA development board i.e. Zedboard which
contains the necessary hardware components such as USB, Ethernet and HDMI interfaces etc. to implement a
fully working system capable of processing a machine learning application in real-time.
Fault detection and diagnosis ingears using wavelet enveloped power spectrum ...eSAT Journals
Abstract In this work, automatic detection and diagnosis of gear condition monitoring technique is presented. The vibration signals in time domain wereobtained from a fault simulator apparatus from a healthy gear and an induced faulty gear. These time domain signals were processed using Laplace and Morlet wavelet based enveloped power spectrum to detect the faults in gears. The vibration signals obtained were filtered to enhance the signal components before the application of wavelet analysis. The time and frequency domain features extracted from Laplace wavelet based wavelet transform are used as input to ANN for gear fault classification. Genetic algorithm was used to optimize the wavelet and ANN classification parameters. The result shows the successful classification of ANN test process. Index Terms:Continuous wavelet transform, Envelope power spectrum, Wavelet, Filtering, ANN.
COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN NEURAL NETWORK BASED IDENT...ijcsit
This paper explores the application of artificial neural networks for online identification of a multimachine power system. A recurrent neural network has been proposed as the identifier of the two area, four machine system which is a benchmark system for studying electromechanical oscillations in multimachine power systems. This neural identifier is trained using the static Backpropagation algorithm. The emphasis of the paper is on investigating the performance of the variants of the Backpropagation algorithm in training the neural identifier. The paper also compares the performances of the neural identifiers trained using variants of the Backpropagation algorithm over a wide range of operating conditions. The simulation results establish a satisfactory performance of the trained neural identifiers in identification of the test power system.
IRJET- A Review on SVM based Induction MotorIRJET Journal
This document summarizes several research papers on using support vector machines (SVMs) and other machine learning techniques for fault detection in induction motors. Specifically:
1. It discusses using an artificial immune system-optimized SVM for detecting broken rotor bars and stator faults in induction motors based on motor current data.
2. It describes using wavelet analysis, principal component analysis, and SVM classification to detect faults like frequency variations, unbalanced voltages, and interturn shorts based on motor current spectra.
3. It proposes using dq0 voltage components analyzed with fast Fourier transforms as features for an SVM classifier to detect stator winding shorts, achieving over 98% accuracy.
The power supply system is completely hooked into three major parts. First one is generation, second one is
transmission and the last one is distribution of electricity supply at the range of 415V to 400V approx. But while
the fault occurs it affects other lines additionally, and this causes difficulties for local people and additionally
perturb the flow of current in different areas. This eccentric and perturbed supply of nuisance is very
hazardous as it cannot be ceased when it comes to equal distribution of electricity. The area suffering from
faults and the other both get affected. So to stop all these we have implemented this project of Coordination of
over current relay utilising optimisation technique. We have utilised crow search algorithms with Kennedy as
swarm perspicacity algorithms which are very auxiliary in storing excess electricity supply and can be used
when needed. With the avail of this we can renovate the potency supply and this will conclusively implement
our main objective of this project.
A real-time fault diagnosis system for high-speed power system protection bas...IJECEIAES
This paper puts forward a real-time smart fault diagnosis system (SFDS) intended for high-speed protection of power system transmission lines. This system is based on advanced signal processing techniques, traveling wave theory results, and machine learning algorithms. The simulation results show that the SFDS can provide an accurate internal/external fault discrimination, fault inception time estimation, fault type identification, and fault location. This paper presents also the hardware requirements and software implementation of the SFDS.
Performance evaluation of ann based plasma position controllers for aditya to...IAEME Publication
This paper evaluates the performance of artificial neural network (ANN) based plasma position controllers for the Aditya tokamak device. Radial basis function networks and generalized recurrent neural networks are developed as controllers and their performance is compared to an existing backpropagation network controller. Training data for the ANNs comes from the Aditya RZIP model. Testing shows the backpropagation network provides better performance in terms of signal-to-noise ratio and root mean square error compared to the other controllers. Further testing on actual plasma discharge data from Aditya is recommended, as well as exploring neuro-fuzzy controllers for plasma position control.
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
Softmax function is an integral part of object detection frameworks based on most deep or shallow neural
networks. While the configuration of different operation layers in a neural network can be quite different,
softmax operation is fixed. With the recent advances in object detection approaches, especially with the
introduction of highly accurate convolutional neural networks, researchers and developers have suggested
different hardware architectures to speed up the overall operation of these compute-intensive algorithms.
Xilinx, one of the leading FPGA vendors, has recently introduced a deep neural network development kit for
exactly this purpose. However, due to the complex nature of softmax arithmetic hardware involving
exponential function, this functionality is only available for bigger devices. For smaller devices, this operation is
bound to be implemented in software. In this paper, a light-weight hardware implementation of this function
has been proposed which does not require too many logic resources when implemented on an FPGA device.
The proposed design is based on the analysis of the statistical properties of a custom convolutional neural
network when used for classification on a standard dataset i.e. CIFAR-10. Specifically, instead of using a brute
force approach to design a generic full precision arithmetic circuit for SoftMax function using real numbers, an
approximate integer-only design has been suggested for the limited range of operands encountered in realworld
scenario. The approximate circuit uses fewer logic resources since it involves computing only a few
iterations of the series expansion of exponential function. However, despite using fewer iterations, the function
has been shown to work as good as the full precision circuit for classification and leads to only minimal error
being introduced in the associated probabilities. The circuit has been synthesized using Hardware Description
Language (HDL) Coder and Vision HDL toolboxes in Simulink® by Mathworks® which provide higher level
abstraction of image processing and machine learning algorithms for quick deployment on a variety of target
hardware. The final design has been implemented on a Xilinx FPGA development board i.e. Zedboard which
contains the necessary hardware components such as USB, Ethernet and HDMI interfaces etc. to implement a
fully working system capable of processing a machine learning application in real-time.
Optimization of workload prediction based on map reduce frame work in a cloud...eSAT Journals
Abstract Nowadays cloud computing is emerging Technology. It is used to access anytime and anywhere through the internet. Hadoop is an open-source Cloud computing environment that implements the Googletm MapReduce framework. Hadoop is a framework for distributed processing of large datasets across large clusters of computers. This paper proposes the workload of jobs in clusters mode using Hadoop. MapReduce is a programming model in hadoop used for maintaining the workload of the jobs. Depend on the job analysis statistics the future workload of the cluster is predicted for potential performance optimization by using genetic algorithm. Key Words: Cloud computing, Hadoop Framework, MapReduce Analysis, Workload
- Motivated Electrical Engineer with 1 year of experience in power transmission planning, generator interconnection studies, and NERC compliance studies seeking a position in power systems engineering.
- Master's degree in Electrical Engineering with a focus on power systems and experience in software development.
- Skilled in transmission planning tools like PSSE and experience analyzing power flows, contingencies, and reliability standards.
Fault diagnosis of a high voltage transmission line using waveform matching a...ijsc
This paper is based on the problem of accurate fault diagnosis by incorporating a waveform matching technique. Fault isolation and detection of a double circuit high voltage power transmission line is of immense importance from point of view of Energy Management services. Power System Fault types namely single line to ground faults, line to line faults, double line to ground faults etc. are responsible for transients in current and voltage waveforms in Power Systems. Waveform matching deals with the approximate superimposition of such waveforms in discretized versions obtained from recording devices and Software respectively. The analogy derived from these waveforms is obtained as an error function of voltage and current, from the considered metering devices. This assists in modelling the fault identification as an optimization problem of minimizing the error between these sets of waveforms. In other words, it utilizes the benefit of software discrepancies between these two waveforms. Analysis has been done using the Bare Bones Particle Swarm Optimizer on an IEEE 2 bus, 6 bus and 14 bus system. The performance of the algorithm has been compared with an analogous meta-heuristic algorithm called BAT optimization on a 2 bus level. The primary focus of this paper is to demonstrate the efficiency of such methods and state the common peculiarities in measurements, and the possible remedies for such distortions.
This paper presents an optimization method called the Simplex method to coordinate directional overcurrent relays in a power system modeled with a 3-bus system. The Simplex method was used to find the minimum total operation time of the relays by solving the optimization problem as a linear program with constraints. The optimal solution found all relays coordinated with coordination time intervals of at least 0.2 seconds and time multiplier settings greater than 0.1. DigSilent software was used to calculate fault currents and validate the Simplex method provides an effective approach for relay coordination optimization problems.
In this paper, impedance based method and matching approaches were used separately to detect three phase to ground fault (LLLGF). In order to observe the accuracy of each method, Non-homogeneous distribution network was used as a tested network. Actual data from TNB (Tenaga National Berhad) Malaysia was adopted to model the network by using PSCAD/EMTDC simulation program. Both methods were tested to observe the accuracy of fault distance estimation. The comparison result shows different accuracy for each section which simulated in the middle of section. Based on the complexity of the distribution network, it possible to contribute difficulty to obtain the maximum accuracy. The result was obtained through the complete process which involves the database formation acquired through the PSCAD/EMTDC software simulator and the fault location distance calculation carried out by the MATLAB software.
Robust System for Patient Specific Classification of ECG Signal using PCA and...IRJET Journal
This document proposes a robust system for classifying electrocardiogram (ECG) signals specific to individual patients. It uses principal component analysis (PCA) and neural networks. Features are extracted from ECG data using time-invariant discrete wavelet transforms. PCA is then used to reduce the dimensionality of the feature space. An artificial neural network classifies the ECG patterns for each patient based on the features. The system was tested on the MIT-BIH arrhythmia database and achieved accurate classification of normal and abnormal heart rhythms for individual patients.
Genetic algorithm approach into relay co ordinationIAEME Publication
This document summarizes a research paper that uses a genetic algorithm to optimize the coordination of overcurrent relays in an electrical power distribution system. The paper formulates the relay coordination problem as an optimization problem to minimize the total operating times of relays while satisfying coordination constraints. A genetic algorithm is applied to find the optimal settings for time multipliers on the relays. As a case study, the algorithm is applied to coordinate relays on a simple radial system and finds settings that achieve the minimum fitness function value while satisfying constraints. The genetic algorithm approach provides an effective method for automating the optimization of relay coordination in electrical power systems.
Open switch fault diagnosis in three phase inverter using diagnostic variable...eSAT Journals
The reliability of power electronics system such as three phase inverter is important in various applications. Different types of faults occur in it, which may influence the operation of system. Such faults require unexpected maintenance, which increases the cost of manufacturing. Therefore fault diagnosis of such devices plays vital role in industry. One possible fault that occurs in inverter is an open switch fault. This paper provides a new technique based on diagnostic variable which detects single as well as multiple open switch fault in three phase inverter. In this method, diagnostic variables are used to detect faulty phase. Along with these diagnostic variables, an average current of three phase inverter is used for the detection of single as well as multiple faulty switches. Key Words: Power electronics, open switch fault, diagnostic variables.
Neural Network Based Individual Classification SystemIRJET Journal
This document describes a neural network model developed for individual classification. The model was designed to measure personality traits through a questionnaire. It then uses a neural network trained on sample data through unsupervised and supervised learning with multi-layer perceptions. The backpropagation algorithm was used to train the network. The neural network architecture included multiple neuron layers trained on a 200 item data set, achieving 99.82% accuracy. The goal was to classify individuals into high, middle, and low personality categories for use in job selection or training.
Neural wavelet based hybrid model for short-term load forecastingAlexander Decker
This document summarizes a research paper that proposes a neural-wavelet based hybrid model for short-term load forecasting. The paper introduces neural networks and how they can be used for electric load forecasting. It then proposes a model that uses wavelet transforms for preprocessing the original load signal data into different levels, before inputting these into a neural network for short-term load forecasting. The model is tested and results show the neural-wavelet model provides more accurate forecasts than an artificial neural network alone.
Ameliorate Threshold Distributed Energy Efficient Clustering Algorithm for He...chokrio
Ameliorating the lifetime in heterogeneous wireless sensor network is an important task because the sensor nodes are limited in the resource energy. The best way to improve a WSN lifetime is the clustering based algorithms in which each cluster is managed by a leader called Cluster Head. Each other node must communicate with this CH to send the data sensing. The nearest base station nodes must also send their data to their leaders, this causes a loss of energy. In this paper, we propose a new approach to ameliorate a threshold distributed energy efficient clustering protocol for heterogeneous wireless sensor networks by excluding closest nodes to the base station in the clustering process. We show by simulation in MATLAB that the proposed approach increases obviously the number of the received packet messages and prolongs the lifetime of the network compared to TDEEC protocol.
Single Hard Fault Detection in Linear Analog Circuits Based On Simulation bef...IJERD Editor
This document presents a method for detecting single hard faults in linear analog circuits using a simulation before testing approach. The method generates test vectors for nominal and tolerance-bound component values to form a fault dictionary. The circuit under test is then simulated with injected faults. Fault variables are derived by comparing nominal and faulty responses. The component with the lowest relative standard deviation of its fault variable is identified as faulty. The method was tested on benchmark circuits like a linear voltage divider and correctly identified injected short and open faults in components. The technique addresses tolerance challenges in analog circuit testing.
This paper discusses the time-frequency transform based fault detection and classification of STATCOM (Static synchronous compensator) integrated single circuit transmission line. Here, fast-discrete S-Transform (FDST) based time-frequency transformation is proposed for evaluation of fault detection and classification including STATCOM in transmission line. The STATCOM is placed at mid-point of transmission line. The system starts processing by extracting the current signals from both end of current transformer (CT) connected in transmission line. The current signals from CT’s are fed to FDST to compute the spectral energy (SE) of phase current at both end of the line. The differential spectral energy (DSE) is evaluated by subtracting the SE obtained from sending end and SE obtained from receiving end of the line. The DSE is the key indicator for deciding the fault pattern detection and classification of transmission line. This proposed scheme is simulated using MATLAB simulink R2010a version and successfully tested under various parameter condition such as fault resistance (Rf),source impedance (SI), fault inception angle (FIA) and reverse flow of current. The proposed approach is simple, reliable and efficient as the processing speed is very fast to detect the fault within a cycle period of FDT (fault detection time).
Transformers are the vital parts of an electrical grid system. A faulty transformer can destabilize the electrical
supply along with the other devices of the transmission system. Due to its significant role in the
system, a transformer has to be free from faults and irregularities. Dissolved Gas-in-oil Analysis (DGA)
is a method that helps in diagnosing the faults present in an electrical transformer. This paper proposes
a hybrid system based on Genetic Neural Computing (GNC) for analyzing and interpreting the data
derived from the concentration of the dissolved gases. It is further analyzed and clustered into four subsets
according to the standard C57.104 defined by IEEE using genetic algorithm (GA). The clustered data is
fed to the neural network that is used to predict the different types of faults present in the transformers.
The hybrid system generates the necessary decision rules to assist the system’s operator in identifying
the exact fault in the transformer and its fault status. This analysis would then be helpful in performing
the required maintenance check and plan for repairs.
IRJET-Efficient Shortest Path Approach using Cluster Based Warshall's Algorit...IRJET Journal
This document presents a study on efficient shortest path approaches for wireless body sensor networks using a cluster-based Warshall's algorithm. Wireless body sensor networks are used for healthcare monitoring and consist of sensor nodes that monitor vital signs. Energy efficiency is important as data is transmitted from sensor nodes to a local server. The proposed method uses Warshall's algorithm to find the shortest paths between nodes within clusters to increase network lifetime. Simulation results show the proposed approach achieves higher classification rates, packet delivery ratios, and lower latency compared to conventional shortest path algorithms like Dijkstra's algorithm and distance vector hop localization. The cluster-based Warshall's algorithm is concluded to efficiently utilize energy and increase network lifetime for wireless body sensor networks.
Fault detection in power transformers using random neural networksIJECEIAES
This paper discuss the application of artificial neural network-based algorithms to identify different types of faults in a power transformer, particularly using DGA (Dissolved Gas Analysis) test. The analysis of Random Neural Network (RNN) using Levenberg-Marquardt (LM) and Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithms has been done using the data of dissolved gases of power transformers collected from Punjab State Transmission Corporation Ltd.(PSTCL), Ludhiana, India. Sorting of the preprocessed data have been done using dimensionality reduction technique, i.e., principal component analysis. The sorted data is used as inputs to the Random Neural Networks (RNN) classifier. It has been seen from the results obtained that BFGS has better performance for the diagnosis of fault in transformer as compared to LM.
Artificial Neural Networks for ON Line Assessment of Voltage Stability using ...IOSR Journals
This document describes using an artificial neural network (ANN) technique to assess voltage stability online in power transmission systems. The ANN model is trained to correlate voltage stability status with changing load patterns using two stability indices: the fast voltage stability index (FVSI) and line stability factor (LQF). Simulation results on the IEEE 30-bus test system and Indian 72-bus power grid show the ANN method can accurately calculate the stability indices without complex calculations and can effectively monitor voltage stability online.
Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio ...IJMER
The behaviour of soil at the location of the project and interactions of the earth materials during and after construction has a major influence on the success, economy and safety of the work. Another complexity associated with some geotechnical engineering materials, such as sand and gravel, is the difficulty in obtaining undisturbed samples and time consuming involving skilled
technician. Knowledge of California Bearing Ratio (C.B.R) is essential in finding the road thickness. To cope up with the difficulties involved, an attempt has been made to model C.B.R in terms of Fine Fraction, Liquid Limit, Plasticity Index, Maximum Dry density, and Optimum Moisture content. A multi-layer perceptron network with feed forward back propagation is used to model varying the
number of hidden layers. For this purposes 50 soils test data was collected from the laboratory test
results. Among the test data 30 soils data is used for training and remaining 20 soils for testing using
60-40 distribution. The architectures developed are 5-4-1, 5-5-1, and 5-6-1. Model with 5-6-1 architecture is found to be quite satisfactory in predicting C.B.R of soils. A graph is plotted between
the predicted values and observed values of outputs for training and testing process, from the graph it
is found that all the points are close to equality line, indicating predicted values are close to observed
values
Power system transient stability margin estimation using artificial neural ne...elelijjournal
This paper presents a methodology for estimating the normalized transient stability margin by using the multilayered perceptron (MLP) neural network. The complex relationship between the input variables and output variables is established by using the neural networks. The nonlinear mapping relation between the normalized transient stability margin and the operating conditions of the power system is established by using the MLP neural network. To obtain the training set of the neural network the potential energy boundary surface (PEBS) method along with time domain simulation method is used. The proposed method is applied on IEEE 9 bus system and the results shows that the proposed method provides fast and accurate tool to assess online transient stability.
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.
Wavelet energy moment and neural networks based particle swarm optimisation f...journalBEEI
In this study, a combined approach of discrete wavelet transform analysis and a feed forward neural networks algorithm to detect and classify transmission line faults. The proposed algorithm uses a multi -resolution analysis decoposition of three-phasecurrents only to calculate the wavelet energy moment of detailed coefficients. In comparison with the energy spectrum, the energy moment could reveal the energy distribution features better, which is beneficial when extracting signal features. Theapproach use particle swarm optimization algorithm to train a feed forward neural network. The goal is the enhancement of the convergence rate, learning process and fill up the gap of local minimum point.The purposed scheme consists of two FNNs, one for detecting and another for classifying all the ten types of faults using Matlab/Simulink. The proposed algorithm have been extensively tested on a system 400 kV, 3 phases, 100 km line consideringvarious fault parameter variations.
This document discusses a method for detecting, classifying, and locating faults on 220kV transmission lines using discrete wavelet transform and neural networks. Fault detection is performed by calculating the energy of detail coefficients from wavelet transformation of phase current signals. A neural network is then used for fault classification and location. The neural network is trained using patterns generated by simulating different fault conditions, including varying fault location, type, and resistance. The proposed method aims to classify 10 different fault types and locate faults occurring at different points along the transmission line.
Optimization of workload prediction based on map reduce frame work in a cloud...eSAT Journals
Abstract Nowadays cloud computing is emerging Technology. It is used to access anytime and anywhere through the internet. Hadoop is an open-source Cloud computing environment that implements the Googletm MapReduce framework. Hadoop is a framework for distributed processing of large datasets across large clusters of computers. This paper proposes the workload of jobs in clusters mode using Hadoop. MapReduce is a programming model in hadoop used for maintaining the workload of the jobs. Depend on the job analysis statistics the future workload of the cluster is predicted for potential performance optimization by using genetic algorithm. Key Words: Cloud computing, Hadoop Framework, MapReduce Analysis, Workload
- Motivated Electrical Engineer with 1 year of experience in power transmission planning, generator interconnection studies, and NERC compliance studies seeking a position in power systems engineering.
- Master's degree in Electrical Engineering with a focus on power systems and experience in software development.
- Skilled in transmission planning tools like PSSE and experience analyzing power flows, contingencies, and reliability standards.
Fault diagnosis of a high voltage transmission line using waveform matching a...ijsc
This paper is based on the problem of accurate fault diagnosis by incorporating a waveform matching technique. Fault isolation and detection of a double circuit high voltage power transmission line is of immense importance from point of view of Energy Management services. Power System Fault types namely single line to ground faults, line to line faults, double line to ground faults etc. are responsible for transients in current and voltage waveforms in Power Systems. Waveform matching deals with the approximate superimposition of such waveforms in discretized versions obtained from recording devices and Software respectively. The analogy derived from these waveforms is obtained as an error function of voltage and current, from the considered metering devices. This assists in modelling the fault identification as an optimization problem of minimizing the error between these sets of waveforms. In other words, it utilizes the benefit of software discrepancies between these two waveforms. Analysis has been done using the Bare Bones Particle Swarm Optimizer on an IEEE 2 bus, 6 bus and 14 bus system. The performance of the algorithm has been compared with an analogous meta-heuristic algorithm called BAT optimization on a 2 bus level. The primary focus of this paper is to demonstrate the efficiency of such methods and state the common peculiarities in measurements, and the possible remedies for such distortions.
This paper presents an optimization method called the Simplex method to coordinate directional overcurrent relays in a power system modeled with a 3-bus system. The Simplex method was used to find the minimum total operation time of the relays by solving the optimization problem as a linear program with constraints. The optimal solution found all relays coordinated with coordination time intervals of at least 0.2 seconds and time multiplier settings greater than 0.1. DigSilent software was used to calculate fault currents and validate the Simplex method provides an effective approach for relay coordination optimization problems.
In this paper, impedance based method and matching approaches were used separately to detect three phase to ground fault (LLLGF). In order to observe the accuracy of each method, Non-homogeneous distribution network was used as a tested network. Actual data from TNB (Tenaga National Berhad) Malaysia was adopted to model the network by using PSCAD/EMTDC simulation program. Both methods were tested to observe the accuracy of fault distance estimation. The comparison result shows different accuracy for each section which simulated in the middle of section. Based on the complexity of the distribution network, it possible to contribute difficulty to obtain the maximum accuracy. The result was obtained through the complete process which involves the database formation acquired through the PSCAD/EMTDC software simulator and the fault location distance calculation carried out by the MATLAB software.
Robust System for Patient Specific Classification of ECG Signal using PCA and...IRJET Journal
This document proposes a robust system for classifying electrocardiogram (ECG) signals specific to individual patients. It uses principal component analysis (PCA) and neural networks. Features are extracted from ECG data using time-invariant discrete wavelet transforms. PCA is then used to reduce the dimensionality of the feature space. An artificial neural network classifies the ECG patterns for each patient based on the features. The system was tested on the MIT-BIH arrhythmia database and achieved accurate classification of normal and abnormal heart rhythms for individual patients.
Genetic algorithm approach into relay co ordinationIAEME Publication
This document summarizes a research paper that uses a genetic algorithm to optimize the coordination of overcurrent relays in an electrical power distribution system. The paper formulates the relay coordination problem as an optimization problem to minimize the total operating times of relays while satisfying coordination constraints. A genetic algorithm is applied to find the optimal settings for time multipliers on the relays. As a case study, the algorithm is applied to coordinate relays on a simple radial system and finds settings that achieve the minimum fitness function value while satisfying constraints. The genetic algorithm approach provides an effective method for automating the optimization of relay coordination in electrical power systems.
Open switch fault diagnosis in three phase inverter using diagnostic variable...eSAT Journals
The reliability of power electronics system such as three phase inverter is important in various applications. Different types of faults occur in it, which may influence the operation of system. Such faults require unexpected maintenance, which increases the cost of manufacturing. Therefore fault diagnosis of such devices plays vital role in industry. One possible fault that occurs in inverter is an open switch fault. This paper provides a new technique based on diagnostic variable which detects single as well as multiple open switch fault in three phase inverter. In this method, diagnostic variables are used to detect faulty phase. Along with these diagnostic variables, an average current of three phase inverter is used for the detection of single as well as multiple faulty switches. Key Words: Power electronics, open switch fault, diagnostic variables.
Neural Network Based Individual Classification SystemIRJET Journal
This document describes a neural network model developed for individual classification. The model was designed to measure personality traits through a questionnaire. It then uses a neural network trained on sample data through unsupervised and supervised learning with multi-layer perceptions. The backpropagation algorithm was used to train the network. The neural network architecture included multiple neuron layers trained on a 200 item data set, achieving 99.82% accuracy. The goal was to classify individuals into high, middle, and low personality categories for use in job selection or training.
Neural wavelet based hybrid model for short-term load forecastingAlexander Decker
This document summarizes a research paper that proposes a neural-wavelet based hybrid model for short-term load forecasting. The paper introduces neural networks and how they can be used for electric load forecasting. It then proposes a model that uses wavelet transforms for preprocessing the original load signal data into different levels, before inputting these into a neural network for short-term load forecasting. The model is tested and results show the neural-wavelet model provides more accurate forecasts than an artificial neural network alone.
Ameliorate Threshold Distributed Energy Efficient Clustering Algorithm for He...chokrio
Ameliorating the lifetime in heterogeneous wireless sensor network is an important task because the sensor nodes are limited in the resource energy. The best way to improve a WSN lifetime is the clustering based algorithms in which each cluster is managed by a leader called Cluster Head. Each other node must communicate with this CH to send the data sensing. The nearest base station nodes must also send their data to their leaders, this causes a loss of energy. In this paper, we propose a new approach to ameliorate a threshold distributed energy efficient clustering protocol for heterogeneous wireless sensor networks by excluding closest nodes to the base station in the clustering process. We show by simulation in MATLAB that the proposed approach increases obviously the number of the received packet messages and prolongs the lifetime of the network compared to TDEEC protocol.
Single Hard Fault Detection in Linear Analog Circuits Based On Simulation bef...IJERD Editor
This document presents a method for detecting single hard faults in linear analog circuits using a simulation before testing approach. The method generates test vectors for nominal and tolerance-bound component values to form a fault dictionary. The circuit under test is then simulated with injected faults. Fault variables are derived by comparing nominal and faulty responses. The component with the lowest relative standard deviation of its fault variable is identified as faulty. The method was tested on benchmark circuits like a linear voltage divider and correctly identified injected short and open faults in components. The technique addresses tolerance challenges in analog circuit testing.
This paper discusses the time-frequency transform based fault detection and classification of STATCOM (Static synchronous compensator) integrated single circuit transmission line. Here, fast-discrete S-Transform (FDST) based time-frequency transformation is proposed for evaluation of fault detection and classification including STATCOM in transmission line. The STATCOM is placed at mid-point of transmission line. The system starts processing by extracting the current signals from both end of current transformer (CT) connected in transmission line. The current signals from CT’s are fed to FDST to compute the spectral energy (SE) of phase current at both end of the line. The differential spectral energy (DSE) is evaluated by subtracting the SE obtained from sending end and SE obtained from receiving end of the line. The DSE is the key indicator for deciding the fault pattern detection and classification of transmission line. This proposed scheme is simulated using MATLAB simulink R2010a version and successfully tested under various parameter condition such as fault resistance (Rf),source impedance (SI), fault inception angle (FIA) and reverse flow of current. The proposed approach is simple, reliable and efficient as the processing speed is very fast to detect the fault within a cycle period of FDT (fault detection time).
Transformers are the vital parts of an electrical grid system. A faulty transformer can destabilize the electrical
supply along with the other devices of the transmission system. Due to its significant role in the
system, a transformer has to be free from faults and irregularities. Dissolved Gas-in-oil Analysis (DGA)
is a method that helps in diagnosing the faults present in an electrical transformer. This paper proposes
a hybrid system based on Genetic Neural Computing (GNC) for analyzing and interpreting the data
derived from the concentration of the dissolved gases. It is further analyzed and clustered into four subsets
according to the standard C57.104 defined by IEEE using genetic algorithm (GA). The clustered data is
fed to the neural network that is used to predict the different types of faults present in the transformers.
The hybrid system generates the necessary decision rules to assist the system’s operator in identifying
the exact fault in the transformer and its fault status. This analysis would then be helpful in performing
the required maintenance check and plan for repairs.
IRJET-Efficient Shortest Path Approach using Cluster Based Warshall's Algorit...IRJET Journal
This document presents a study on efficient shortest path approaches for wireless body sensor networks using a cluster-based Warshall's algorithm. Wireless body sensor networks are used for healthcare monitoring and consist of sensor nodes that monitor vital signs. Energy efficiency is important as data is transmitted from sensor nodes to a local server. The proposed method uses Warshall's algorithm to find the shortest paths between nodes within clusters to increase network lifetime. Simulation results show the proposed approach achieves higher classification rates, packet delivery ratios, and lower latency compared to conventional shortest path algorithms like Dijkstra's algorithm and distance vector hop localization. The cluster-based Warshall's algorithm is concluded to efficiently utilize energy and increase network lifetime for wireless body sensor networks.
Fault detection in power transformers using random neural networksIJECEIAES
This paper discuss the application of artificial neural network-based algorithms to identify different types of faults in a power transformer, particularly using DGA (Dissolved Gas Analysis) test. The analysis of Random Neural Network (RNN) using Levenberg-Marquardt (LM) and Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithms has been done using the data of dissolved gases of power transformers collected from Punjab State Transmission Corporation Ltd.(PSTCL), Ludhiana, India. Sorting of the preprocessed data have been done using dimensionality reduction technique, i.e., principal component analysis. The sorted data is used as inputs to the Random Neural Networks (RNN) classifier. It has been seen from the results obtained that BFGS has better performance for the diagnosis of fault in transformer as compared to LM.
Artificial Neural Networks for ON Line Assessment of Voltage Stability using ...IOSR Journals
This document describes using an artificial neural network (ANN) technique to assess voltage stability online in power transmission systems. The ANN model is trained to correlate voltage stability status with changing load patterns using two stability indices: the fast voltage stability index (FVSI) and line stability factor (LQF). Simulation results on the IEEE 30-bus test system and Indian 72-bus power grid show the ANN method can accurately calculate the stability indices without complex calculations and can effectively monitor voltage stability online.
Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio ...IJMER
The behaviour of soil at the location of the project and interactions of the earth materials during and after construction has a major influence on the success, economy and safety of the work. Another complexity associated with some geotechnical engineering materials, such as sand and gravel, is the difficulty in obtaining undisturbed samples and time consuming involving skilled
technician. Knowledge of California Bearing Ratio (C.B.R) is essential in finding the road thickness. To cope up with the difficulties involved, an attempt has been made to model C.B.R in terms of Fine Fraction, Liquid Limit, Plasticity Index, Maximum Dry density, and Optimum Moisture content. A multi-layer perceptron network with feed forward back propagation is used to model varying the
number of hidden layers. For this purposes 50 soils test data was collected from the laboratory test
results. Among the test data 30 soils data is used for training and remaining 20 soils for testing using
60-40 distribution. The architectures developed are 5-4-1, 5-5-1, and 5-6-1. Model with 5-6-1 architecture is found to be quite satisfactory in predicting C.B.R of soils. A graph is plotted between
the predicted values and observed values of outputs for training and testing process, from the graph it
is found that all the points are close to equality line, indicating predicted values are close to observed
values
Power system transient stability margin estimation using artificial neural ne...elelijjournal
This paper presents a methodology for estimating the normalized transient stability margin by using the multilayered perceptron (MLP) neural network. The complex relationship between the input variables and output variables is established by using the neural networks. The nonlinear mapping relation between the normalized transient stability margin and the operating conditions of the power system is established by using the MLP neural network. To obtain the training set of the neural network the potential energy boundary surface (PEBS) method along with time domain simulation method is used. The proposed method is applied on IEEE 9 bus system and the results shows that the proposed method provides fast and accurate tool to assess online transient stability.
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.
Wavelet energy moment and neural networks based particle swarm optimisation f...journalBEEI
In this study, a combined approach of discrete wavelet transform analysis and a feed forward neural networks algorithm to detect and classify transmission line faults. The proposed algorithm uses a multi -resolution analysis decoposition of three-phasecurrents only to calculate the wavelet energy moment of detailed coefficients. In comparison with the energy spectrum, the energy moment could reveal the energy distribution features better, which is beneficial when extracting signal features. Theapproach use particle swarm optimization algorithm to train a feed forward neural network. The goal is the enhancement of the convergence rate, learning process and fill up the gap of local minimum point.The purposed scheme consists of two FNNs, one for detecting and another for classifying all the ten types of faults using Matlab/Simulink. The proposed algorithm have been extensively tested on a system 400 kV, 3 phases, 100 km line consideringvarious fault parameter variations.
This document discusses a method for detecting, classifying, and locating faults on 220kV transmission lines using discrete wavelet transform and neural networks. Fault detection is performed by calculating the energy of detail coefficients from wavelet transformation of phase current signals. A neural network is then used for fault classification and location. The neural network is trained using patterns generated by simulating different fault conditions, including varying fault location, type, and resistance. The proposed method aims to classify 10 different fault types and locate faults occurring at different points along the transmission line.
This paper presents a discrete wavelet transform and neural network approach to fault
detection and classification and location in transmission lines. The fault detection is carried out by
using energy of the detail coefficients of the phase signals and artificial neutral network algorithm
used for fault type classification and fault distance location for all the types of faults for 220 KV
transmission line. The energies of the all three phases A, B, C and ground phase are given in put to
the neural network for the fault classification. For each type of fault separate neural network is
prepared for finding out the fault location. An improved performance is obtained once the neutral
network is trained suitably, thus performance correctly when faced with different system parameters
and conditions.
Distance protection scheme for transmission line using back propagation 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
This document presents a novel technique for fault detection and classification on double circuit transmission lines using artificial neural networks (ANNs). The technique uses high frequency transients caused by faults to identify internal and external faults. ANNs with suitable numbers of neurons are used to analyze voltage and current signals and decompose them to identify faults. Extensive simulation studies show the proposed approach can accurately discriminate between internal and external faults, providing fast, effective, and efficient protection. The document describes modeling a double circuit transmission line system in MATLAB, selecting ANN input/output parameters, developing a 3-layer 45-neuron ANN structure, and presenting simulation results demonstrating the ANN can detect and classify different fault types within a few milliseconds.
This document presents a novel methodology for fault section estimation in power systems. The methodology uses protective device settings and a search algorithm to identify isolated sections. It considers changes in network topology caused by protective devices operating. The methodology calculates a fault reference value for each section based on relay settings and topology. It then calculates the deviation between this reference and the actual weights based on operated protections to identify the most likely fault sections. The result provides operators a prioritized list of fault candidates to assist with decision making during disturbances. The methodology uses intrinsic system information rather than uncertainties used in other existing methods.
An accurate technique for supervising distance relays during power swingnooriasukmaningtyas
The document proposes an accurate technique for supervising distance relays during power swings. It constructs a locus diagram of the current and voltage differences between the two ends of a protected transmission line using synchronized phasor measurements. It then calculates the circumference of the constructed ellipse as an index to discriminate between faults and power swings in the first stage. If no fault is detected, it checks the power angle in the second stage to identify power swings. Simulation tests on a two-area four-machine power system demonstrate that the technique can accurately differentiate faults from power swings and ensure proper blocking/unblocking of distance relays.
Signal-Energy Based Fault Classification of Unbalanced Network using S-Transf...idescitation
This document presents a technique for classifying faults on overhead transmission lines using S-Transform and a Probabilistic Neural Network (PNN) classifier. Voltage signals are processed using S-Transform to extract energy features from each phase. These 3 features (1 per phase) are used as inputs to a PNN classifier to determine the type of fault (e.g. line-ground, line-line) and faulty phase. The method was tested on a simulated 3-phase transmission line model in MATLAB with different fault conditions. It produced accurate classification results, even when noise was added to the signals. The paper concludes the method provides fast and accurate fault classification.
The document presents a new method for fault classification and direction discrimination in transmission lines using 1D convolutional neural networks (1D-CNNs). A 132kV transmission line model is simulated to generate training and testing data for the 1D-CNN algorithm. The proposed 1D-CNN approach directly uses the voltage and current signals from one end as input, merging feature extraction and classification into a single learning process. Testing shows the 1D-CNN method accurately classifies and discriminates fault direction with higher accuracy than conventional neural network and fuzzy neural network methods under different fault conditions.
IRJET- A Simple Approach to Identify Power System Transmission Line Faults us...IRJET Journal
This paper presents a Probabilistic Neural Network (PNN) approach for identifying and classifying faults on power transmission lines. The PNN is trained on voltage waveform data simulated using Electromagnetic Transient Program (EMTP) software for different fault types and locations on a 150km transmission line. Only two sets of simulated data are used to train the PNN, requiring less computation than other methods that preprocess data. The trained PNN is able to accurately identify and classify fault types based on the voltage waveform, which helps ensure reliable power transmission by isolating only faulty lines or phases.
IRJET- Three Phase Line Fault Detection using Artificial Neural NetworkIRJET Journal
This document describes a study that uses an artificial neural network to detect and classify faults on electric power transmission lines. The researchers modeled a three-phase transmission line system in MATLAB/Simulink and simulated different types of faults at various locations and resistances. Voltage and current data from the simulations were extracted and preprocessed as inputs to train an artificial neural network. The trained network was then able to detect and classify faults with 95.7% accuracy, demonstrating its effectiveness. Previous methods had issues with stability and slow dynamic response, but the artificial neural network approach provided improved fault detection performance.
Enhanced two-terminal impedance-based fault location using sequence valuesIJECEIAES
Fault at transmission line system may lead to major impacts such as power quality problems and cascading failure in the grid system. Thus, it is very important to locate it fast so that suitable solution can be taken to ensure power system stability can be retained. The complexity of the transmission line however makes the fault point identification a challenging task. This paper proposes an enhanced fault detection and location method using positive and negative-sequence values of current and voltage, taken at both local and remote terminals. The fault detection is based on comparison between the total fault current with currents combination during the pre-fault time. While the fault location algorithm was developed using an impedancebased method and the estimated fault location was taken at two cycles after fault detection. Various fault types, fault resistances and fault locations have been tested in order to verify the performance of the proposed method. The developed algorithms have successfully detected all faults within high accuracy. Based on the obtained results, the estimated fault locations are not affected by fault resistance and line charging current. Furthermore, the proposed method able to detect fault location without the needs to know the fault type.
Artificial Neural Network Based Fault Classifier for Transmission Line Protec...IJERD Editor
This paper presents a method for classification of transmission line faults based on Artificial Neural Network (ANN).Samples of prefault and postfault three phase currents taken at one end of transmission line are used as ANN inputs. Simulation studies have been carried out extensively on two power system models: one in which the transmission line is fed from one end and another, in which the transmission line is fed from two ends. Different types of faults at different operating conditions have been considered for carrying out simulation studies. The simulation results confirm the feasibility of the proposed approach.
The document presents an artificial neural network (ANN) based method for classifying and locating faults on transmission lines. Simulation studies were conducted on two transmission line models - one fed from one end and the other fed from both ends. Different fault types were considered along with variations in fault resistance, inception angle, location and load. Separate ANNs were trained to classify faults involving ground and not involving ground. The ANNs were tested under varying conditions and the results confirmed the feasibility of using the proposed ANN approach for fault classification on transmission lines.
Backpropagation Neural Network Modeling for Fault Location in Transmission Li...ijeei-iaes
In this topic research was provided about the backpropagation neural network to detect fault location in transmission line 150 kV between substation to substation. The distance relay is one of the good protective device and safety devices that often used on transmission line 150 kV. The disturbances in power system are used distance relay protection equipment in the transmission line. However, it needs more increasing large load and network systems are increasing complex. The protection system use the digital control, in order to avoid the error calculation of the distance relay impedance settings and spent time will be more efficient. Then backpropagation neural network is a computational model that uses the training process that can be used to solve the problem of work limitations of distance protection relays. The backpropagation neural network does not have limitations cause of the impedance range setting. If the output gives the wrong result, so the correct of the weights can be minimized and also the response of galat, the backpropagation neural network is expected to be closer to the correct value. In the end, backpropagation neural network modeling is expected to detect the fault location and identify operational output current circuit breaker was tripped it. The tests are performance with interconnected system 150 kV of Riau Region.
This document presents a new method for detecting DC voltage faults in switched reluctance motor (SRM) drives. The method uses K-means clustering to analyze torque waveform data and classify faults using support vector machines (SVM). Simulation results show that torque ripple patterns change with different DC voltage levels. The proposed approach clusters the torque data and uses SVM to detect and classify DC voltage faults, which enables intelligent fault identification and diagnosis in SRM drives.
- This paper proposes a new technique of using discrete wavelet transform (DWT) and back-propagation neural network (BPNN) based on Clarke’s transformation for fault classification and detection on a single circuit transmission line. Simulation and training process for the neural network are done by using PSCAD / EMTDC and MATLAB. Daubechies4 mother wavelet (DB4) is used to decompose the high frequency components of these signals. The wavelet transform coefficients (WTC) and wavelet energy coefficients (WEC) for classification fault and detect patterns used as input for neural network training back-propagation (BPNN). This information is then fed into a neural network to classify the fault condition. A DWT with quasi optimal performance for preprocessing stage are presented. This study also includes a comparison of the results of training BPPN and DWT with and without Clarke’s transformation, where the results show that using Clarke transformation in training will give in a smaller mean square error (MSE) and mean absolute error (MAE). The simulation also shows that the new algorithm is more reliable and accurate.
Permanent Fault Location in Distribution System Using Phasor Measurement Unit...IJECEIAES
This paper proposes a new method for locating high impedance fault in distribution systems using phasor measurement units (PMUs) installed at certain locations of the system. To implement this algorithm, at first a new method is suggested for the placement of PMUs. Taking information from the units, voltage and current of the entire distribution system are calculated. Then, the two buses in which the fault has been occurred is determined, and location and type of the fault are identified. The main characteristics of the proposed method are: the use of distributed parameter line model in phase domain, considering the presence of literals, and high precision in calculating the high impedance fault location. The results obtained from simulations in EMTP-RV and MATLAB software indicate high accuracy and independence of the proposed method from the fault type, fault location and fault resistance compared to previous methods, so that the maximum observed error was less than 0.15%.
An appropriate fault detection and classification of power system transmission line using discrete wavelet transform and artificial neural networks is performed in this paper. The analysis is carried out by applying discrete wavelet transform for obtained fault phase currents. The work represented in this paper are mainly concentrated on classification of fault and this classification is done based on the obtained energy values after applying discrete wavelet transform by taking this values as an input for the neural network. The proposed system and analysis is carried out in Matlab Simulink.
Similar to Determination of Fault Location and Type in Distribution Systems using Clark Transformation and Neural Network (20)
Effects of the Droop Speed Governor and Automatic Generation Control AGC on G...IJAPEJOURNAL
In power system, as any inequality between production and consumption results in an instantaneous change in frequency from nominal, frequency should be always monitored and controlled. Traditionally, frequency regulation is provided by varying the power output of generators which have restricted ramp rates. The Automatic Generation Control AGC process performs the task of adjusting system generation to meet the load demand and of regulating the large system frequency changes. A result of the mismatches between system load and system generation, system frequency and the desired value of 50 Hz is the accumulation of time error. How equilibrium system frequency is calculated if load parameters are frequency dependent, and how can frequency be controlled. Also, how do parameters of a speed governor affect generated power. The transient processes before system frequency settles down to steady state. Finally, AGC in what way is it different from governor action. This paper presents new approaches for AGC of power system including two areas having one steam turbines and one hydro turbine tied together through power lines.
Underwater Target Tracking Using Unscented Kalman FilterIJAPEJOURNAL
Unlike conventional active sonar, that transmits the sound signals and revealing their presence and position to enemy forces. The probable advantage of passive sonar is that it detects the signals emitted by the target, leads to improve localization, target tracking, and categorization. The challenging aspect is to estimate the true bearing and frequency measurements from the noisy measurements of the target. Here in this paper, it is recommended for the Unscented Kalman Filter (UKF) to track the target by using these noisy measurements. The Target Motion Analysis (TMA), which is the way to find the target’s trajectory by using frequency and bearing measurements, is explored. This method provides a tactical advantage over the classical bearing only tracking target motion analysis. It makes the observer maneuver unnecessary.
Investigation of Dependent Rikitake System to Initiation PointIJAPEJOURNAL
In this paper we investigate depending of the Rikitake system to initiation point, and monitor changing behavior of this system. We will have 4 initiation points in Cartesian system. We at 4 positions, will monitor behavior of this system, while holding constant other values, and after per position, will draw operation of system on axes of x, y, z and 3-D plot. We want to know, what is the effect of initiation point on Rikitake system? Numerical simulations to illustrate the effect of initiation point are presented, and at the end conclusions and comparing the states together are obtained.
Optimization of Economic Load Dispatch with Unit Commitment on Multi MachineIJAPEJOURNAL
Economic load dispatch (ELD) and Unit Commitment (UC) are significant research applications in power systems that optimize the total production cost of the predicted load demand. The UC problem determines a turn-on and turn-off schedule for a given combination of generating units, thus satisfying a set of dynamic operational constraints. ELD optimizes the operation cost for all scheduled generating units with respect to the load demands of customers. The first phase in this project is to economically schedule the distribution of generating units using Gauss seidal and the second phase is to determine optimal load distribution for the scheduled units using dynamic programming method is applied to select and choose the combination of generating units that commit and de-commit during each hour. These precommitted schedules are optimized by dynamic programming method thus producing a global optimum solution with feasible and effective solution quality, minimal cost and time and higher precision. The effectiveness of the proposed techniques is investigated on two test systems consisting of five generating units and the experiments are carried out using MATLAB R2010b software. Experimental results prove that the proposed method is capable of yielding higher quality solution including mathematical simplicity, fast convergence, diversity maintenance, robustness and scalability for the complex ELD-UC problem.
Impact of Buried Conductor Length on Computation of Earth Grid ResistanceIJAPEJOURNAL
Effective design of substation earth grid implies achieving low earth grid resistance and fulfillment of the safety criteria at the lowest possible cost. This paper presents an evaluation of IEEE Standard 80-2000 Equations 50 to 52 to determine the impact of buried conductor length on computation of earth grid resistance. Calculated results indicated that a saturation point is reached beyond which further addition of more conductor length does not significantly reduce the earth grid resistance but incurs more economic implications. These were validated by earth grids designed using CDEGS where good agreement between the calculated and simulated results was found.
Enhancing Photoelectric Conversion Efficiency of Solar Panel by Water CoolingIJAPEJOURNAL
Photovoltaic solar cell generates electricity by receiving solar irradiance. The electrical efficiency of photovoltaic (PV) cell is adversely affected by the significant increase of cell operating temperature during absorption of solar radiation. This undesirable effect can be partially avoided by cooling the back side of the photovoltaic panel using water absorption sponge which was fixed on of PV panel and maintain wet condition by circulation of drop by drop water. The objective of the present work is to reduce the temperature of the solar cell in order to increase its electrical efficiency. Experiments were performed with and without water cooling. A linear trend between the efficiency and temperature was found. Without cooling, the temperature of the panel was high and solar cells were achieved an efficiency of 8–9%. However, when the panel was operated under water cooling condition, the temperature dropped maximally by 40C leading to an increase in efficiency of solar cells by 12%.
PMU-Based Transmission Line Parameter Identification at China Southern Power ...IJAPEJOURNAL
China Southern Power Grid Company (CSG) recently developed and implemented an online PMU-based transmission line (TL) parameter identification system (TPIS). Traditionally, TL parameters are calculated based on transmission tower geometries, conductor dimension, estimates of line length, conductor sags, etc. These parameters only approximate the effect of conductor sag and ignore the dependence of impedance parameters on temperature variation. Recent development in PMU technology has made it possible to calculate TL parameters accurately. The challenges are that such application requires highly accurate PMU data while the accuracy of PMU measurements under different working/system conditions can be uncertain. With a large number of PMUs widely installed in its system, CSG plans to improve and update the EMS database using the newly developed TPIS. TPIS provides an innovative yet practical problem formulation and solution for TL parameter identification. In addition, it proposes a new metric that can be used to determine the credibility of the calculated parameters, which is missing in the literature. This paper discusses the methodologies, challenges, as well as implementation issues noticed during the development of TPIS.
Investigation of Electric Field Distribution Inside 500/220 kV Transformation...IJAPEJOURNAL
This study depicts the electric field distributions inside a typical 500/220 kV open distribution substation under actual loading conditions and during different working conditions, Hot-Stick position and Bar-Hand position. The electric field is investigated for different workers heights of 1m, 1.5m and 1.8m above ground during normal working condition (Hot-Stick position) inside this substation. This in addition to assessment of the electric field at a height levels of 8m, 11m, 14m and 17m above ground as positions for live line maintenance under 220 kV Busbars, 500 kV Busbars, 220 kV Incoming and Outgoing feeders and 500 kV Incoming and Outgoing feeders respectively. In this study the simulation results of the electric field obtained using three dimensional (3D) computer model for existing typical high voltage transformation substation are compared with field values measured inside this typical substation and presented and discussed not only in the form of contour maps but also in the form 3D surface and wireframe maps. The simulation results are good matched and agreed with measured values. This in addition to the electric field will be tabulated and compared to international guidelines for personnel exposure to electric field. This study will serve for planning service works or for inspection of equipment inside high voltage (HV) power transformation substations.
Economic Load Dispatch for Multi-Generator Systems with Units Having Nonlinea...IJAPEJOURNAL
This document presents an economic load dispatch problem that uses the Gravity Search Algorithm to minimize total generation costs for multi-generator power systems. It discusses how practical constraints like valve point loading, multi-fuel operation, and forbidden zones result in non-ideal, non-continuous generator cost curves. The Gravity Search Algorithm is applied to find the optimal dispatch schedule that accounts for these realistic cost functions and minimizes the total cost of generation while satisfying demand. The algorithm is tested on sample power systems and able to find solutions within acceptable timeframes that outperform traditional optimization methods for large, complex problems.
Improving Light-Load Efficiency by Eliminating Interaction Effect in the Grid...IJAPEJOURNAL
A wind turbine equipped with doubly-fed induction generator (DFIG) is used in wind power plant industry. This paper studies the maximum power extraction of DFIG via evaluation of state-space equations in closed loop control condition for improving light-load efficiency. The DFIG state-space equations have been considered in the form of a multi-input- multi output (MIMO) system. Also, the tracing table has been used to determine the speed which the generated power will be proportional to the maximum load. The tracing table input is the generator speed, and its output is the optimum active power that has been considered as the reference power of the active power control system of the convertor. A controller is presented for the tracing table and the extracted power is able to follow the reference power with minimum ripple. Then, the results are compared with the single-input and single-output (SISO) case, for the values up to 0.2 times of the rated load. Therefore, in MIMO modeling, in the case that the DFIG connected to the grid, by eliminating the interaction effect, the efficiency in light-load can be increased
An Application of Ulam-Hyers Stability in DC MotorsIJAPEJOURNAL
In this paper, a generalization to nonlinear systems is proposed and applied to the motor dynamic, rotor model and stator model in DC motor equation. We argue that Ulam-Hyers stability concept is quite significant in design problems and in design analysis for the class of DC motor’s parameters. We prove the stability of nonlinear partial differential equation by using Banach’s contraction principle. As an application, the Ulam-Hyers stability of DC motor dynamics equations is investigated. To the best of our knowledge this is the first time Ulam-Hyers stability is considered from the applications point of view.
Implementation of Hybrid Generation Power System in PakistanIJAPEJOURNAL
A solar-wind hybrid power generation system has been presented here. The application based system illustrated in this paper is designed on the basis of the solar and wind data for Pakistan. The power generated by the system is intended for domestic use. The most common source of unconventional power in homes is battery based UPS (Uninterrupted power supply) inverter. The UPS inverter charges the battery with conventional grid power. This system will charge the battery of UPS inverter by using only wind and solar power, which will make the system cost effective and more reliable. The reason for using both solar and wind is that recent studies have proven that combined system can be more productive and consistent and other thing is that neither of them can be used for continuous power generation. In the system illustrated in this paper the solar-wind system provides power periodically which is controlled by electronic methods and a microcontroller is used to monitor the power from both the inputs. The switching action is provided from the microcontroller to the battery charging based on the power received from solar photovoltaic panel and wind generators. In this paper, an efficient system has been presented comprising of solar panel, wind generator, charge controller and charge storage unit (battery). Solar panel is selected as the main input and the wind resource will be used only in the absence of the solar photovoltaic (PV) output.
Modeling and Simulation of SVPWM Based ApplicationIJAPEJOURNAL
Recent developments in power electronics and semiconductor technology have lead to widespread use of power electronic converters in the power electronic systems. A number of Pulse width modulation (PWM) schemes are used to obtain variable voltage and frequency supply from a three-phase voltage source inverter. Among the different PWM techniques proposed for voltage fed inverters, the sinusoidal PWM technique has been popularly accepted. But there is an increasing trend of using space vector PWM (SVPWM) because of their easier digital realization, reduced harmonics, reduced switching losses and better dc bus utilization. This project focuses on step by step development of SVPWM technique. Simulation results are obtained using MATLAB/Simulink software for effectiveness of the study.
Comparison of FACTS Devices for Two Area Power System Stability Enhancement u...IJAPEJOURNAL
This document compares the performance of SVC and STATCOM FACTS devices for enhancing transient stability in a two-area power system modelled in MATLAB. It first provides background on power system stability challenges and the role of FACTS devices in addressing these issues. It then reviews previous research comparing different FACTS devices. The paper models an SVC and STATCOM controller in MATLAB and simulates their performance under a three-phase fault. Simulation results indicate that the STATCOM controller provides better damping of rotor angle oscillations, suggesting it enhances transient stability more than the SVC in the two-area power system model.
Influence of Static VAR Compensator for Undervoltage Load Shedding to Avoid V...IJAPEJOURNAL
In the recent years, operation of power systems at lower stability margins has increased the importance of system protection methods that protect the system stability against various disturbances. Among these methods, the load shedding serves as an effective and last-resort tool to prevent system frequency/voltage instability. The analysis of recent blackouts suggests that voltage collapse and voltage-related problems are also important concerns in maintaining system stability. For this reason, voltage also needs to be taken into account in load shedding schemes. This paper considers both parameters in designing a load shedding scheme to determine the amount of load to be shed and its appropriate location .The amount of load to be shed from each bus is decided using the fixed step size method and it’s location has been identified by using voltage collapse proximity index method. SVC is shunt connected FACTS device used to improve the voltage profile of the system. In this paper impact of SVC on load shedding for IEEE 14 bus system has been presented and analyzed.
Assessment of Electric Field Distribution Inside 500/220 kV Open Distribution...IJAPEJOURNAL
The high level electric field intensity produced by high voltage (HV) equipments inside 500/220 kV substations is harmful for the human (staff) health. Therefore the minimum health and safety requirements regarding the exposure of workers to the risk arising from electric fields produced inside these substations is still considered as a competitive topic for utility designers, world health organization (WHO) and biomedical field researchers. It is very important to have knowledge about levels distribution of electric field intensity within these high voltage substations as early stage in the process of substation design. This paper presents results of investigation 50Hz electric field intensity distribution inside 500/220 kV power transmission substations in Cairo, Egypt. This paper presents a method for assessment the distribution of 50HZ electric field intensity distribution inside this substation, this method of analysis is based on the charge simulation technique (CSM). This study will serve for planning service works or for inspection of equipment on HV power transmission substations.
Towards An Accurate Modeling of Frequency-dependent Wind Farm Components Unde...IJAPEJOURNAL
This document describes modeling the components of a wind farm in order to accurately simulate its transient response under lightning conditions. It details models for the wind turbines, transformers, transmission lines, surge arresters, and other components. The models include frequency dependence to capture transient behavior. The wind farm model is implemented and validated in ATP/EMTP software. Comparison is made between models with and without frequency dependence. This accurate modeling of wind farm components allows simulation of the transient response and analysis of lightning hazards.
Hybrid Generation Power System for Domestic ApplicationsIJAPEJOURNAL
This work presents the plan and model of the control strategy for the interconnection of the hybrid energy system able to regulating this load’s voltage and controlling the energy generation with the energy options. The control strategy contains controlling the energy generated through each energy source, in a hierarchical mode using sliding/dropping mode control, while consuming consideration elements that have an impact on each electrical power source and transform the energy generated in order to suitable circumstances for lower power and domestic programs. The cross alternative energy system consists of photovoltaic cellular material, fuel cellular material and battery packs. A numerical equation in order to estimate the perfect voltage involving photovoltaic systems for virtually every solar irradiance and temperature circumstances is suggested. Simulations of a single or a lot more systems interconnected towards the load with the entire proposed control scheme, under different ecological and weight conditions, usually are introduced to indicate this efficiency with the procedure.
Ash Cooler Heat Recovery Under Energy Conservation SchemeIJAPEJOURNAL
A healthy fluidization state in circulating fluidized-bed combustion (CFBC) combustor is attributed to proper quantity of hot bed material (ash), which acts as a thermal fly-wheel. It receives & stores thermal energy from the burning of fuel (lignite) & distributes uniformly throughout the combustor & helps in maintaining a sustained combustion. The quantity of bed ash inside the combustor or size of the bed, depends upon boiler load & subsequently upon combustor temperature, lignite feed rate and ash % in lignite. As these parameters varies during process continuously, sometimes it becomes necessary to drain out the ash from the combustor. As & when differential pressure across the bed is increased from a justified level, draining of hot bed ash starts into Ash Coolers. Bed ash is drained at very high temperature of 850 oC & it also contains burning particles of lignite. This paper describes the heat recovery from bed ash, unloaded from the combustor into ash cooler, by pre-heating the condensate water of turbine cycle in a 125 MW CFB boiler of Surat Lignite Power Plant in India. The thermal performance of ash cooler was derived by doing a heat balance calculation based on the measured temperature of ash and cooling water with different load. From the heat balance calculation influence of ash temperature and ash amount on heat transfer coefficient is determined. Simulation is carried out around main turbine cycle indicates improved thermal economy of the unit, higher plant thermal efficiency, lower plant heat rate and reduce fuel consumption rate. Also simulation result shows that the heat transfer coefficient increase with ash amount and decreases with increase in ash temperature.
Harmonic Voltage Distortions in Power Systems Due to Non Linear LoadsIJAPEJOURNAL
This document summarizes research on harmonic voltage distortions in power systems due to non-linear loads. It describes how non-linear loads can generate harmonics and discusses their effects. It also examines harmonic reduction methods like passive filters. The research uses MiPower software to model a sample IEEE 5-bus power system and analyze harmonic distortions with and without filters. Installation of single and dual passive filters at different buses is shown to significantly reduce total harmonic distortion throughout the system. The document concludes that accurate harmonic analysis of power systems can be achieved using such simulation tools.
We have compiled the most important slides from each speaker's presentation. This year’s compilation, available for free, captures the key insights and contributions shared during the DfMAy 2024 conference.
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
ACEP Magazine edition 4th launched on 05.06.2024Rahul
This document provides information about the third edition of the magazine "Sthapatya" published by the Association of Civil Engineers (Practicing) Aurangabad. It includes messages from current and past presidents of ACEP, memories and photos from past ACEP events, information on life time achievement awards given by ACEP, and a technical article on concrete maintenance, repairs and strengthening. The document highlights activities of ACEP and provides a technical educational article for members.
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.
A review on techniques and modelling methodologies used for checking electrom...nooriasukmaningtyas
The proper function of the integrated circuit (IC) in an inhibiting electromagnetic environment has always been a serious concern throughout the decades of revolution in the world of electronics, from disjunct devices to today’s integrated circuit technology, where billions of transistors are combined on a single chip. The automotive industry and smart vehicles in particular, are confronting design issues such as being prone to electromagnetic interference (EMI). Electronic control devices calculate incorrect outputs because of EMI and sensors give misleading values which can prove fatal in case of automotives. In this paper, the authors have non exhaustively tried to review research work concerned with the investigation of EMI in ICs and prediction of this EMI using various modelling methodologies and measurement setups.
2. ISSN: 2252-8792
IJAPE Vol. 1, No. 2, August 2012, pp. 75–86
76
distance and the eigenvalue of line current matrix [8-9]. The restriction and limitation of this method is
dependence of fault location to load for some fault types.
Recently fault detection which is based on neural networks in several papers has been introduced
[10-12]. One of the methods uses neural network to fault detections which scrutiny the breakers state and
relay status in a feeder and then the destroyed element is identified [10]. This method is presented for small
and simple power systems [10].
For major power networks which have too many lines and buses, multiple neural networks are used, in
order to time reduction of neural network training. The employment of multiple neural networks is possible
in different form, for example a great power system is subdivided into several subsystems and a neural
network has been separately introduced for each one of them [11].
In Ref.10, the authors present a hierarchical artificial neural network (HANN) for determining of
fault location. This technique identifies fault distance step by step. Applied neural network consists of three
classes [12-14]. In other word, problem solution by hierarchical ANN is down through three levels which are
low, medial and upper level [12]. This method only determines fault location.
In this paper, a new neural network based method for determination of fault location and fault type
is proposed. This network is trained by αβ space vector technique and the eigenvalue of line current matrix.
The main advantage of the proposed method is that only three phase current sampling for each feeder is
sufficient. Also the proposed method is not depending on fault impedance, thus it is useful for determination
of fault type and fault location in fault condition with different impedance value. Also high impedance faults
can be detected by this method.
This paper is organized as follows. Section 2 describes the proposed method for determination of
fault location and type. Simulation results are presented in section 3 to achieve the suitable neural network. In
section 4, determination of fault location and fault classification in the radial distribution feeders is presented.
Section 5 presents the main conclusions of this paper.
2. RESEARCH METHOD
In this section a neural network is proposed to determine the fault type and location. This neural
network is trained with suitable parameters. These parameters change regularly with fault type and distance
variations. The proposed method fundamentally subdivided in three following stages.
- The first stage is to convert the line current into αβ space components using Clark transformation.
- The second stage is to determine the eigenvalue for neural network training in order to identify the fault
distance.
- The third stage is to calculate the eigenvector for neural network training in order to identify the fault
type.
2.1. Convert the Line Current into αβ Space Components
One of the best de-coupling procedures for three phase line currents is Clark transformation. The
static two-phase variables are named "alpha" and "beta". The third parameter is zero-sequence [8].
Tc=
−−
−−
2
1
2
1
2
1
2
3
2
3
0
2
1
2
1
1
(1)
The first step is to achieve a data sample of the line currents in matrix form as following:
S=
i1ሺt0ሻ i2ሺt0ሻ i3ሺt0ሻ
⋮ ⋮ ⋮
i1൫t0+൫n-1൯∆t൯ i2൫t0+൫n-1൯∆t൯ i3൫t0+൫n-1൯∆t൯
(2)
Where t0 is the start time of data sampling and ∆t is the sample interval.
The conversion of line current into αβ space ingredients is obtained as following:
A = Tc. S =
݅ሺݐሻ iሺt + ∆tሻ ⋯ iሺݐ + ሺ݊ − 1ሻ∆tሻ
iஒሺtሻ iஒሺt + ∆tሻ ⋯ iஒሺݐ + ሺ݊ − 1ሻ∆tሻ
iሺtሻ iሺt + ∆tሻ ⋯ iሺݐ + ሺ݊ − 1ሻ∆tሻ
(3)
3. IJAPE ISSN: 2252-8792
Determination of Fault Location and Type in Distribution Systems using Clark Transformation … (M. Sarvi)
77
2.2. The Proposed Neural Network for Determination of Fault Location
Fault location is obtained from the neural network. This network is trained with eigenvalues. Line
currents are characterized by eigenvalues of data sample correlation matrix. Correlation matrix of A is
obtained as following:
B=AT.A (4)
The operator "eig" has been used to achieve eigenvalue of matrix B, as following:
[F,C]=eig(B) (5)
Where matrix C is as the following:
C =
ߣఈ 0 0
0 ߣఉ 0
0 0 ߣ
(6)
Where λα, λβ and λ0 are eigenvalues of B. Simulation results indicate that only the λ0 eigenvalue
has relationship with fault location. Relationship between λ0 and distance for two types of fault are shown in
Figures 1-2.
The columns of matrix F (in Eq.5) are defined with eigenvectors f1, f2 and f3. This subject is
described in the next section.
Figure 1. Relationship between λ0 and fault distance for phase A to ground (A-G) fault.
Figure 2. Relationship between λ0 and fault distance for phase A to C and phase B to ground (A-C &B-G)
fault.
1.52 1.54 1.56 1.58 1.6 1.62 1.64 1.66
x 10
8
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
distance
eigenvalue
0 2 4 6 8 10 12 14 16 18
x 10
13
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
distance
eigenvalue
4. ISSN: 2252-8792
IJAPE Vol. 1, No. 2, August 2012, pp. 75–86
78
2.3. The Proposed Neural Network For Determination Of Fault Type
Fault classification is obtained by a neural network. This network is trained with eigenvectors of line
currents matrix for each type of fault.
Matrix F columns (in Eq.5) are defined with eigenvectors f1, f2 and f3, as following:
F=ሾ݂ଵ ݂ଶ ݂ଷሿ (7)
Where,
݂ଵ = [݂ଵଵ ݂ଵଶ ݂ଵଷ] ்
݂ଶ = [݂ଶଵ ݂ଶଶ ݂ଶଷ] ்
(8)
݂ଷ = [݂ଷଵ ݂ଷଶ ݂ଷଷ] ்
Simulation results indicate that the sign of components of matrix F varies according to fault type; therefore
each one of fault types constitutes a particular matrix.
The sign of matrix F components, for some different fault types are presented in table 1.
Table 1. The sign of matrix F components for some different fault types
f33f23f13f32f22f12f31f21f11Matrix F:
Fault Type
----+-++-A-G
--++--+-+B-G
+---+-+++C-G
+-+---+--A-B-G
--++--+-+C-B-G
0-+---+--A-B
--+0--+-0C-B
--++--+++A-B , C-G
0-+0-++--Pre-fault
In fault classification step, the output of neural network is a number. Each number refers to a particular type
of fault as shown in Table 2.
Table 2. The output of neural network for determination of fault type
Fault TypeANN OutputFault TypeANN Output
B-C-G8A-G1
A-C-G9B-G2
A-B-C10C-G3
A-B , C-G11A-B4
B-C , A-G12B-C5
A-C , B-G13A-C6
Pre-Fault14A-B-G7
2.4. The Block Diagram and Algorithm of The Proposed Method
The block diagram of the proposed method for determination of fault classification and location are
shown in Figures 3-4. It includes below main steps:
- The first step is to achieve a data sample of the line currents.
- The second step is mathematical treatment on the achieved data sample using Clark.
- The third step is acquiring the eigenvalue (λ0) and eigenvector components (f11…f33).
- The forth step is applying eigenvector components (f11…f33) as inputs of first artificial neural network
(ANN). The output of the first ANN is the type of the fault.
- The fifth step is applying eigenvalue (λ0) and fault type as inputs of second ANN. The output of the
second ANN is the distance of the fault.
5. IJAPE ISSN: 2252-8792
Determination of Fault Location and Type in Distribution Systems using Clark Transformation … (M. Sarvi)
79
Clark
Transformatio
n
icibia
Matrix
A
B=AT
.A
[F,C]=eig(B)
e11…e3 First neural
network:
Fault Classification
Second neural
network:
Fault Classification
λ0
Fault type
Fault
distance
Figure 3. The algorithm for determination of fault type and location
Figure 4. The algorithm for determination of fault type and location.
NN#2 output:
Fault location
Clark transformation:
Eigen value and Eigen vector derivation
Use Eigen vector as input of a first Neural
Network (NN#1)
NN#1 ANN output:
Fault detection and fault classification
Use λ0 and fault type as input of the second
neural network (NN#2)
Three phase sampling and creating a
matrix
Fault
Yes
No
Line break
6. ISSN: 2252-8792
IJAPE Vol. 1, No. 2, August 2012, pp. 75–86
80
2.5. Determination Of Fault Location And Type With Neural Network
A neural network is defined and characterized by its architecture, input, number of neurons, output,
size, and by the training technique that is used to determine its weights. Several architectures have been
proposed in the literatures. The best architecture of neural network depends on the type of problem.
In order to obtain an optimum neural network, the simulation results for RBF and MLP neural
networks are compared.
3. RESULTS AND ANALYSIS
In order to investigate accuracy and quality of the proposed method and to achieve the best neural
networks for determination of fault type and location, a typical power distribution system is considered. The
main characteristics of this system are as the following:
- Distribution line with: S=118 mm2 , R=0.2791 Ω/km, L= 0.326 mH/km
- Substation power transformer of 10 MVA, 63/20 kV, Y/d, artificial neutral formed for 1 kA
- Load: 2MVA, cosφ=0.9
- Substation power transformers of 3MVA, 20/0.4 kV, Dyn
- Phase-phase fault impedance= 0.0001 Ω
- Phase-ground fault impedance=1 Ω
3.1. Determination of fault location and type with neural network
A neural network is defined and characterized by its architecture, input, number of neurons, output,
size, and by the training technique that is used to determine its weights. Several architectures have been
proposed in the literatures. The best architecture of neural network depends on the type of problem.
In order to obtain an optimum neural network, the simulation results for RBF and MLP neural networks
are compared.
3.1.1. Determination of fault location and type with MLP neural network
In this section, in order to achieve the most suitable MLP network for determination of fault location
and type, several excitation functions for MLP neural networks with different characteristics are investigated
and studied.
To compare between the different types of neural networks results, the absolute error is defined as
following:
linelengthtotal
locationfaultcalculatedlocationfaultactual
errorabsolute
−
=
(9)
Total absolute error for whole 13 types of faults is calculated as following:
( )
kk
errorabsoluterrorabsolutTotal ∑=
=
13
1
(10)
In Eq.10, k is the number of fault type, where each number refers to a particular type of fault as
shown in table 2.
In order to determination of fault location by MLP neural network, the relationship between
eigenvalue (λ0) and fault distance is used to train the MLP neural network. The typical MLP excitation
functions are logsig, purelin, radbas, staling, satlins, tansig, and tribas.
The total absolute error (in percentage of total length line) for fault location using different
excitation functions is shown in Figure 5.
As shown in Figure 5, the total absolute error for fault location using functions purelin, satlins and
tansig is less than the error among the defined excitation functions.
The total absolute error for different pair of functions which are used for two layers of MLP neural
network has been presented in Figure 6.
As shown in Figure 6, the total absolute error for the third pair of functions (purelin, tansig) is less
than total absolute error among other pair of functions. Therefore in ultimate structure for MLP neural
network, purelin and tansig are applied for two layers in network.
7. IJAPE ISSN: 2252-8792
Determination of Fault Location and Type in Distribution Systems using Clark Transformation … (M. Sarvi)
81
Figure 5. The total absolute error (in percentage of
total length line) for fault location by different
functions
Figure 6. The total absolute error (in percentage of
total length line) for different pair of functions
The final step to achieve a suitable neural network is to obtain an optimum number of neurons for
MLP network. As shown in Figure 7 the total absolute error of neural network with 6 and 7 neurons in
hidden layer, is not significantly less than the total absolute error of the neural network with 5 neurons,
therefore a MLP neural network with two layers, (five neurons in hidden layer and one neuron in output
layer) has a suitable response. The final MLP neural network for fault location is shown in Figure 8.
Figure 7. The total absolute error (in percentage of
total length line) for different number of neurons.
Figure 8. MLP neural network for determination of
fault location.
Figure 9. The total absolute error for fault
classification with different number of neurons.
Figure 10. MLP neural network for determination of
fault type.
8. ISSN: 2252-8792
IJAPE Vol. 1, No. 2, August 2012, pp. 75–86
82
In similar method, a MLP neural network is achieved for determination of fault type. In obtained
MLP network, satlin and logsig constitute the best pair of functions which contain the least total absolute
error. To select the optimum number of neuron, several networks with different number of neurons are
studied. Absolute error for fault classification is obtained as following:
absolute error = | Actual rate ሺFault typeሻ - Computed result(Fault type)| (11)
The total absolute error in vertical axis is obtained from Eq.10.
As shown in Figure 9 the total absolute error of neural network with 6 and 7 neurons in hidden
layer, is not significantly less than the total absolute error of the neural network with 5 neurons, therefore a
MLP neural network with two layers, (five neurons in hidden layer and one neuron in output layer) has a
suitable response as shown in Figure 10.
3.1.2. Determination of Fault Location and Type With RBF Neural Network
The function RBF iteratively creates a radial basis network one neuron at a time. Radial basis
networks can be used to approximate functions. RBF creates a two-layer network (The hidden layer and
output layer). One of the RBF neural network parameters is spread.
It is important that the spread parameter be large enough that the neurons of RBF respond to
overlapping regions of the input space, but not so large that all the neurons respond in essentially the same
manner. In order to achieve the most suitable RBF network for determination of fault location and type,
several RBF network have been studied. The absolute error for fault location is obtain by Eq.9 and absolute
error for fault type is obtain by Eq.11 and total absolute error (for vertical axis in diagrams) is obtained using
Eq.10.
To obtain a suitable RBF network for fault locating, in the first step several RBF network with
different number of neurons are studied, in this step spread parameter is assumed 1. The simulation results
are shown in Figure 11. As shown in Figure 11 the total absolute error of neural network 10 neurons in
hidden layer, is not significantly less than the total absolute error of the neural network with 9 neurons,
therefore RBF neural network with 9 neurons is perfected.
In second step, several RBF network with different value of spread are studied. In this step the
number of neurons is considered 9. The simulation results are shown in Figure 12.
Figure 11. The total absolute error (in percentage of
total length line) for different number of neurons.
Figure 12. The total absolute error (in percentage of
total length line) for different value of spread
parameter.
As shown in Figure 12 if spread parameter is 3, then the total absolute error is greater than the total
absolute error when the spread parameter is 2, therefore for obtain a suitable RBF the spread parameter is set
to 2.
To obtain a suitable RBF network for determination of fault type, in the first step several RBF
network with different number of neurons are studied. In this analysis spread parameter is considered 1. The
simulation results are shown in Figure 13. As shown in Figure 13 the total absolute error of neural network
with 7 neurons in hidden layer, is not significantly less than the total absolute error of the neural network
with 8 neurons, therefore the RBF neural network with 7 neurons is perfected.
9. IJAPE ISSN: 2252-8792
Determination of Fault Location and Type in Distribution Systems using Clark Transformation … (M. Sarvi)
83
Figure 13. The total absolute error for fault
classification with different number of neurons.
Figure 14. The total absolute error for different value
of spread parameter.
In the next step, several RBF network with different value of spread are studied, in this step the
number of neurons is 7. The simulation results are shown in Figure 14.
As shown in Figur 14, if the spread parameter is 5, then the total absolute error is greater than the
total absolute error when the spread parameter is 4, therefore for obtain a suitable RBF the spread parameter
is set to 4.
3.2. Comparison of the RBF and MLP neural networks
In order to investigate the quality and accuracy of proposed RBF and MLP neural networks, and to
compare them with each other, the simulation results for determination of fault type and location have been
presented in tables 3-4.
For determination of fault location, MLP and RBF neural networks have been trained with ten
different λ0 which are dependent on ten different fault distances. Also for determination of fault type, MLP
and RBF neural networks have been trained with ten different eigenvectors which are dependent on 13
different fault types.
Table 3. Simulation results (fault type) of MLP and RBF neural networks.
Error:
|actual rate - computed
result|
Computed result (Fault
type)
Actual
rate
(Fault
type) for MLP
neural
network
for RBF
neural
network
MLP
neural
network
output
RBF neural
network
output
0.30.031.30.971
0.330.091.671.912
0.250.083.253.083
0.220.023.784.024
0.360.024.645.025
0.450.0075.556.0076
0.350.0017.357.0017
0.150.047.858.048
0.070.038.939.039
0.120.0610.129.9410
0.260.01310.7411.01311
0.360.00612.3612.00612
0.420.1113.4212.8913
As shown in table 3 the output of RBF neural network for fault classification is more accurate than
the MLP neural network output. Therefore for determination of fault type, RBF is more suitable than MLP.
As shown in table 4 the output of MLP neural network for fault location is more accurate than the
RBF neural network output, thus for determination of fault location, MLP is more suitable than RBF.
As discussed above in proposed method, RBF neural network is applied for fault classification and
MLP neural network is applied for fault location.
10. ISSN: 2252-8792
IJAPE Vol. 1, No. 2, August 2012, pp. 75–86
84
Table 4. Fault distance from begin of distribution line (in percentage of total line length) for MLP and RBF
neural networks.
FAULT DISTANCE FROM BEGIN OF DISTRIBUTION LINE IN
PERCENTAGE OF TOTAL LINE LENGTH (%)
Error: | actual rate - computed result |Computed resultActual fault locationFault type
For
MLP
Neural
network
for RBF neural networkMLP neural network outputRBF neural network output
0.11.565.163.5651
0.82.924.9222.1252
0.210.5235.2131.52353
0.151.3837.6536.1237.54
0.170.747.3348.247.55
0.072.2364.9367.23656
0.160.932.6633.432.57
0.012.144.9947.1458
0.132.6985.1382.31859
0.141.637.6439.137.510
0.125.0937.3832.4137.511
0.111.565.1163.56512
0.154.635.1530.43513
The final flowchart for determination of fault location and type is shown in Figure 15.
Figure 15. Final algorithm for determination of fault type and fault location.
MLP output:
Fault location
Clark transformation:Eigen
value and Eigen vector
derivation
Use Eigen vector as input
of RBF ANN
RBF ANN output:Fault
detection and fault
classification
Use λ0 and fault type as
input of MLP ANN
Three phase sampling and
creating a matrix
Fault
Yes
No
Line break
11. IJAPE ISSN: 2252-8792
Determination of Fault Location and Type in Distribution Systems using Clark Transformation … (M. Sarvi)
85
4. FAULT LOCATING AND FAULT CLASSIFICATION IN THE RADIAL DISTRIBUTION
FEEDERS
A radial feeder has been shown in Figure 16. The characteristics of the main line and each one of the
branches are equal to the line characteristic which are presented in section 3.
Figure 16. The configuration of a simple radial distribution feeder
In order to determination of fault location and fault type in the radial distribution feeders, in the first
step for each one of the branches, the eigenvectors of line currents matrix is analyzed and investigated based
on the proposed method. As soon as the faulty branch is detected, determination of fault location is done in
the same branch. If all of the branches are at the pre-fault condition, the eigenvectors of main line current
matrix is analyzed and investigated based on the proposed method. If the main line is at the fault condition,
determination of fault location is done using proposed method in the main line. The simulation results are
shown in table 5.
Table 5. The simulation results for determination of fault location and fault type in a branchy feeder
Calculated
fault
location
Actual
fault
location
First ANN output:
fault type
Line
number
Fault
type
With
round
operat
or
Without
round
operator
In percentage of total
line length (%)
65.66511.4511
21.72521.9212
36.323533.2433
37.3837544.3814
47.664754.9125
64.426566.3146
32.6532577.137
45.24588.2518
85.528598.8329
37.4837.51010.25310
37.7237.51111.41411
65.13651212.34312
34.8351312.86213
5. CONCLUSION
In this paper a neural network based method is proposed for determination of fault type and
location. The simulation results of two neural network (MLP and RBF) are analyzed and compared. In this
method, neural network has been trained with αβ space vector parameters.
The main conclusions of the proposed method are as the following:
- All types of faults can be classified in this method.
- In this method the number of inputs is decreased, as determination of fault type and location is down only
by the three line currents sampling, where other methods use both voltage and current sampling data
together.
- This method is useful for distribution feeders which have several branches, as only the three phase current
sampling at the sending end of each branch is enough for determination of fault type and location using
proposed method.
Load 2
Current
Sampling 1
Source
Current
Sampling 2
Current
Sampling 3
Current
Sampling 4
Load 3 Load 4
12. ISSN: 2252-8792
IJAPE Vol. 1, No. 2, August 2012, pp. 75–86
86
- The proposed method is not depending on fault impedance, thus it is useful for fault classification and
fault location in fault condition with different impedance value. Also high impedance faults can be
detected by this method.
- The RBF neural network is applied for determination of fault type and MLP neural network is applied for
determination of fault location.
REFERENCES
[1] T. Takagi, Y. Yamakoshi, M. Yamuna, R Konodow, T. Matsushima, "Development of a New Type Fault Locator
Using One-Terminal Voltage and Current Data, " IEEE Trans. on Power Apparatus System, 101 (1982) 2892-2898.
[2] M. Bolin, "Travelling-Wave-Based Protection of Double-Circuit Lines," IEEE Trans on Power Delivery, 140
(1999) 37-47.
[3] H. Mokhlis, "A Comprehensive Fault Location Estimation Using Voltage Sag Profile for Non-Homogenous
Distribution Networks," International Review of Electrical Engineering (IREE), Vol.5, n.5: 2310-2316,September-
October 2010.
[4] H. Mokhlis, "Evaluation of Fault Location based on Voltage Sags Profiles: a Study," International Review of
Electrical Engineering (IREE), Vol.6, n.2: 874-880, March – April 2011.
[5] I. daubechies, "The wavelet transformation time – frequency localization and signal analysis, " International
Review of Electrical Engineering (IREE), Vol.5, n.3: 1165-1171, MAY-JUN 2010.
[6] L. A. Snider, "High impedance fault detection using third harmonic current, " EPRI Report El 2430, prepared by
Hughes Aircraft co. (1980).
[7] Eldin, El Sayed Mohamed Tag, "Fault Location for a Series Compensated Transmission Line Based on Wavelet
Transform and an Adaptive Neuro-Fuzzy Inference System, " International Review of Electrical Engineering
(IREE), Vol.5, n.3: 1165-1171,MAY-JUN 2010.
[8] J. B. Faria, "Application of clarke transformation to the modal analysis of asymmetrical single-circuit three-phase
line configurations, " ETE European Trans. on Electrical Power, 10 (2004) 231-255.
[9] J. B. Faria, "Application of clarke transformation to the modal analysis of asymmetrical single-circuit three-phase
line configurations, " ETE European Trans. on Electrical Power, 10 (2004) 231-255.
[10] L. Sousa Martins, V. Fernao Pires, C.M. Alegria, "A New Accurate Fault Locating Method using αβ Space Vector
Algorithm, " Proceedings of the 14th PSCC (2005) 1-6.
[11] T. Tanaka, "Design and Evaluation of Neural Network for Fault Diagnosis, Proceedings of the Second Symposium
on Expert Application to Power Systems, " Seattle, USA (1989) 378-384.
[12] W. Cen, "Power System Fault Diagnosis Based on New Feed Forward Neural Networks, " Proceedings of
International Power Engineering Conference (IPEC'93), Singapore, (1993) 760-765.
[13] K. K. Ho, P. I. Keum, "Application of hierarchical neural networks to fault diagnosis of power systems,"
International Journal of Electrical Power & Energy Systems, 15 (1993) 65-70.
[14] H. Podvin, "Fault location on MV networks, " PMAPS (2000) 1-6.
BIOGRAPHIES OF AUTHORS
Mohammad Sarvi received his Bachelor in Electrical Engineering in 1998 from the Amirkabir
Polytechnic University, and Master and PhD degrees in 2000 and 2004, respectively, from the Iran
University of Science and Technology, Tehran, Iran. His research interest includes power
electronics and Renewable Energy, FACTs and HVDC. Presently, Dr. Sarvi is an Assistant
Professor at the Imam Khomeini International University, Qazvin, Iran.
Seyyed Makan Torabi received his Bachelor in Electrical Engineering from Shahrood University,
and Master degrees in 2010 from the Islamic Azad University of Saveh, Saveh, Iran. His research
interest includes power system modeling and fault detection in distribution system. Presently, Mr.
torabi is an engineer at the Semnan Electrical Power Distribution Company, Semnan, Iran.