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.
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.
A Novel Study on Bipolar High Voltage Direct Current Transmission Lines Prote...IJECEIAES
In long dc transmission lines identification of fault is important for transferring a large amount of power. In bipolar Line commutated converter transmission lines are subjected to harsh weather condition so accurate and rapid clearance of fault is essential. A comparative study of the bipolar system with both converters healthy and one converter tripped is studied. Most of the research paper has focussed on transmission line faults in bipolar mode but none of them had focussed when HVDC system works in monopolar mode after the fault. In the proposed scheme the voltage signals are extracted from both poles of the rectifier ends and are processed to identify the faults in transmission lines.The Artificial neural network is utilised in detecting the fault in both bipolar and monopolar system. Since it can identify the relationship between input and output data to detect the fault pattern it can be utilised under all conditions. Moreover, benefits of the proposed method are its accuracy, no requirement of the communication system as it acquires data from one end and has a reach setting of 99%.
Wavelet based detection and location of faults in 400kv, 50km Underground Po...ijceronline
This document presents a method for detecting and locating faults in underground power cables using wavelet transforms. A 400kV, 50km underground cable system is modeled in MATLAB Simulink. Various single-phase, two-phase, and three-phase faults are simulated at distances of 25km and 50km from the measurement point. Voltage and current signals are analyzed using continuous wavelet transforms to detect and locate faults. Simulation results show the method can accurately estimate fault locations, with errors generally under 7%. The method is capable of determining fault type and location for both transmission and distribution cables.
The document proposes a new busbar protection scheme that uses two techniques:
1. One technique uses three-phase alienation coefficients to perform fault detection, identify the faulty phase, and discriminate between internal and external faults within half a cycle.
2. The second technique adapts the differential relay characteristics during periods of current transformer saturation to avoid incorrect operation during external faults. It uses alienation coefficients to evaluate the degree of distortion in the secondary current caused by current transformer saturation for external faults.
The techniques are evaluated using simulations of a 19.57 kV busbar in ATP/EMTP and Matlab, and the results demonstrate the accurate operation of the proposed scheme for different fault types.
Wavelet Based Fault Detection, Classification in Transmission System with TCS...IJERA Editor
This paper presents simulation results of the application of distance relays for the protection of transmission systems employing flexible alternating current transmission controllers such as Thyristor Controlled Series Capacitor (TCSC). The complete digital simulation of TCSC within a transmission system is performed in the MATLAB/Simulink environment using the Power System Block set (PSB). This paper presents an efficient method based on wavelet transforms both fault detection and classification which is almost independent of fault impedance, fault location and fault inception angle of transmission line fault currents with FACTS controllers.
To identify and simulate conventional type of disturbance on the overhead transmission line by using PSCAD / EMTDC software package
To develop mathematical model for various type of disturbance on overhead transmission line.
To develop a smart algorithm for fault detection using Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO).
Fault location and correction are important in case of any power systems. This process has to be prompt and accurate so that system reliability can be improved , outage time can be reduced and restoration of system from fault can be accelerated.
Fault location calculation using Magnetoresistance sensor is described here.
Effective two terminal single line to ground fault location algorithmMuhd Hafizi Idris
This paper presents an effective algorithm to locate Single Line to Ground (SLG) fault at a transmission line. Post fault voltages and currents from both substation terminals were used as the input parameters to the algorithm. Discrete Fourier Transform (DFT) was used to extract the magnitudes and phase angles of three phase voltages and currents. The modeling of the transmission line along with the algorithm was performed using Matlab/Simulink package. The results of fault location for SLG faults along the transmission line demonstrated the validity of the algorithm used even for high resistance earth fault.
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.
A Novel Study on Bipolar High Voltage Direct Current Transmission Lines Prote...IJECEIAES
In long dc transmission lines identification of fault is important for transferring a large amount of power. In bipolar Line commutated converter transmission lines are subjected to harsh weather condition so accurate and rapid clearance of fault is essential. A comparative study of the bipolar system with both converters healthy and one converter tripped is studied. Most of the research paper has focussed on transmission line faults in bipolar mode but none of them had focussed when HVDC system works in monopolar mode after the fault. In the proposed scheme the voltage signals are extracted from both poles of the rectifier ends and are processed to identify the faults in transmission lines.The Artificial neural network is utilised in detecting the fault in both bipolar and monopolar system. Since it can identify the relationship between input and output data to detect the fault pattern it can be utilised under all conditions. Moreover, benefits of the proposed method are its accuracy, no requirement of the communication system as it acquires data from one end and has a reach setting of 99%.
Wavelet based detection and location of faults in 400kv, 50km Underground Po...ijceronline
This document presents a method for detecting and locating faults in underground power cables using wavelet transforms. A 400kV, 50km underground cable system is modeled in MATLAB Simulink. Various single-phase, two-phase, and three-phase faults are simulated at distances of 25km and 50km from the measurement point. Voltage and current signals are analyzed using continuous wavelet transforms to detect and locate faults. Simulation results show the method can accurately estimate fault locations, with errors generally under 7%. The method is capable of determining fault type and location for both transmission and distribution cables.
The document proposes a new busbar protection scheme that uses two techniques:
1. One technique uses three-phase alienation coefficients to perform fault detection, identify the faulty phase, and discriminate between internal and external faults within half a cycle.
2. The second technique adapts the differential relay characteristics during periods of current transformer saturation to avoid incorrect operation during external faults. It uses alienation coefficients to evaluate the degree of distortion in the secondary current caused by current transformer saturation for external faults.
The techniques are evaluated using simulations of a 19.57 kV busbar in ATP/EMTP and Matlab, and the results demonstrate the accurate operation of the proposed scheme for different fault types.
Wavelet Based Fault Detection, Classification in Transmission System with TCS...IJERA Editor
This paper presents simulation results of the application of distance relays for the protection of transmission systems employing flexible alternating current transmission controllers such as Thyristor Controlled Series Capacitor (TCSC). The complete digital simulation of TCSC within a transmission system is performed in the MATLAB/Simulink environment using the Power System Block set (PSB). This paper presents an efficient method based on wavelet transforms both fault detection and classification which is almost independent of fault impedance, fault location and fault inception angle of transmission line fault currents with FACTS controllers.
To identify and simulate conventional type of disturbance on the overhead transmission line by using PSCAD / EMTDC software package
To develop mathematical model for various type of disturbance on overhead transmission line.
To develop a smart algorithm for fault detection using Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO).
Fault location and correction are important in case of any power systems. This process has to be prompt and accurate so that system reliability can be improved , outage time can be reduced and restoration of system from fault can be accelerated.
Fault location calculation using Magnetoresistance sensor is described here.
Effective two terminal single line to ground fault location algorithmMuhd Hafizi Idris
This paper presents an effective algorithm to locate Single Line to Ground (SLG) fault at a transmission line. Post fault voltages and currents from both substation terminals were used as the input parameters to the algorithm. Discrete Fourier Transform (DFT) was used to extract the magnitudes and phase angles of three phase voltages and currents. The modeling of the transmission line along with the algorithm was performed using Matlab/Simulink package. The results of fault location for SLG faults along the transmission line demonstrated the validity of the algorithm used even for high resistance earth fault.
This document describes a method for separating source signals from interfering signals using an adaptive AMUSE algorithm. It begins with background on blind source separation and the AMUSE algorithm. The proposed method applies the adaptive AMUSE algorithm to signals obtained from nodes in an analog resistor-capacitor circuit, where one input signal is known. The algorithm estimates the source signals by reconstructing the signals using an extended Kalman smoother. The method is experimentally tested on a simulated resistor-capacitor circuit with three input signals and signals measured at random nodes.
The transmission overhead line is one of the vital elements in the power system for transmitting the electrical energy. In the transmission, the disturbances are often occurred. In the conventional algorithm, alpha and beta (mode) currents generated by Clarke’s transformation are utilized to convert the signal of Discrete Wavelet Transform (DWT) to obtain the Wavelet Transform Coefficient (WTC) and the Wavelet Coefficient Energy (WCE). This study introduces a new algorithm, called Modified Clarke for fault detection and classification using DWT and Back-Propagation Neural Network (BPNN) based on Clarke’s transformation on transmission overhead line by adding gamma current in the system. Daubechies4 (Db4) is used as a mother wavelet to decompose the high frequency components of the signal error. Simulation is performed using PSCAD / EMTDC transmission system modeling and carried out at different locations along the transmission line with different types of fault, fault resistances, fault locations and fault of the initial angle on a given power system model. The simulated fault types are in the study are the Single Line to Ground, the Line To Line, the Double Line to Ground and the Three Phases. There are four statistic methods utilized in the present study to determine the accuracy of detection and classification of faults. The result shows that the best and the worst structures of BPNN occurred on the configuration of 12-24-48-4 and 12-12-6-4, respectively. For instance, the error using Mean Square Error Method. The Error Of Clarke’s, Without Clarke’s and Modified Clarke’s are 0.05862, 0.05513 and 0.03721 which are the best, respectively, whereas, the worst are 0.06387, 0.0753 and 0.052, respectively. This indicates that the Modified Clarke’s result is in the lowest error. The method is successfully implement can be utilized in the detection and classification of fault in transmission line by utilities and power regulation in power system planning and operation.
Errors analysis in distance relay readings with presence of facts devicesAlexander Decker
1) The document analyzes errors in distance relay readings with the presence of FACTS devices like STATCOM and SSSC.
2) It presents models of SSSC and STATCOM and studies their impact on the measured impedance seen by the distance relay for single line to ground faults.
3) The analysis shows how the measured impedance, and the ideal tripping characteristic of the distance relay, are affected by the location and operational conditions of FACTS devices.
Transmission line is one the important compnent in protection of electric power system because the transmission line connects the power station with load centers.
The fault includes storms, lightning, snow, damage to insulation, short circuit fault [1].
Fault needs to be predicted earlier in order to be prevented before it occur
- 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.
Wavelet based double line and double line -to- ground fault discrimination i...IAEME Publication
In this paper, an accurate method to discriminate double line and double line to ground faults
in a three terminal transmission circuit based on wavelet transforms is presented. The proposed
algorithm uses the fault indices of three phase currents of all terminals. Fault indices are obtained by
1st level decomposition of current signals using Bior 1.5 mother wavelet considering the variations
in fault resistance, fault inception angle and distance along the transmission circuit. The entire test
results clearly show that the variation in the value of fault index of the healthy phase with the
presence of ground and constant value in the case of non- presence of ground which discriminates
double line fault from the double line to ground faults in the path along one terminal towards the
other terminal with variations in fault inception angle and fault resistance. The algorithm is proved to
be effective and efficient in detection and discrimination of faults.
Power System’stransmission Line Relaying Improvement Using Discrete Wavelet T...IJERA Editor
Transmission line is a path between the generating station and load(Industries & Domestic). These lines are several kilometres and always attracted towards faults. These Faults are Phase to Ground (P-G), Phase to Phase (P-P), Phase to Phase to Ground (P-P-G) and Symmetrical Fault (P-P-P\P-P-P-G).In order to protect the power system, faults should be cleared within stipulated time. Relay plays a key role in power system protection, before employing them in system, their parameters should be pre-determined.The proposed system uses Discrete Wavelet Transform to determine the fault levels in power system. It is used to extract the hidden factors i.e. Transients, from the faulty current signals by performing decomposition at different levels. Test system is modelled and fault signals are imported to workspace and test the reliability of the algorithm. The proposed system modelled in MATLAB\SIMULINK to detect, classify and locate all the possible faults in the transmission line in the power system which are nothing but parameters of relays.
This document presents a mathematical model and MATLAB simulation of a solar photovoltaic cell and array. It describes the equivalent circuit of a solar cell and defines equations for photocurrent, saturation current, and output current of an ideal cell. A Simulink model of a single cell is used to generate I-V and P-V curves showing maximum power point. The document also discusses modeling a solar array by connecting modules in series and parallel. Simulation results show output characteristics at different irradiances and temperatures.
This document presents the design and simulation of three different SU-8 microelectromechanical systems (MEMS) switch configurations for radio frequency (RF) applications with low actuation voltages: cantilever, clamped-clamped beam, and meandered. The switches were simulated using Coventorware software. The cantilever and meandered switches had a pull-in voltage of 2.5V, while the clamped-clamped beam's pull-in voltage ranged from 4-7V depending on width. Material selection studies showed SU-8 provided the lowest pull-in voltages. Wider beams increased resonant frequency but also increased pull-in voltage. RF simulations in Agilent ADS showed
Brief Literature Review on Phasor Based Transmission Line Fault Location Algo...sarasijdas
This document summarizes various phasor-based fault location algorithms for transmission lines. It categorizes algorithms as traditional knowledge-based, traveling wave-based, or phasor-based methods that can use synchronized or unsynchronized data from single-end, double-end, or multi-terminal lines. Factors affecting accuracy are discussed. Selected algorithms are presented for untransposed parallel lines, lines with cables, multi-terminal lines, and series compensated lines. References for various algorithms are provided.
This document describes a special project on using an artificial neural network (ANN) for load flow studies of the MSU-IIT electrical system. The objectives are to model the power system as a 5-bus system, evaluate bus voltages using a power flow program under different loads, train an ANN using the power flow results, and validate the ANN's accuracy by comparing its results to the power flow program. The document reviews literature on load flow studies, numerical methods, ANNs, and discusses how ANNs could provide faster and more accurate solutions to complex load flow problems compared to numerical methods.
Double Circuit Transmission Line Protection using Line Trap & Artificial Neur...IRJET Journal
This document presents a technique for protecting double circuit transmission lines using line traps and artificial neural networks. Line traps are placed at the terminals of the protected line to detect faults based on high frequency transients. An artificial neural network is trained using the RMS voltage and current signals to classify fault types. MATLAB simulation studies were conducted to model a 300km, 25kV, 50Hz transmission system with three zones. RMS measurements from one end were used to train the neural network to classify faults. The neural network approach provides fast, secure and reliable protection for double circuit transmission lines.
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.
A Fault Detection and Classification Method for SC Transmission Line Using Ph...paperpublications3
Abstract: In this paper, fault detection and classification for Series Compensated Line (SCL) using phasor measurement unit is presented. The algorithm presented in this paper uses the PMU synchronized measurements and not depends on the data to be provided by the electricity utility. The compensated line parameters and Thevenin’s equivalent (TE) of the system at SCL terminals are calculated online, using three independent sets of pre-fault phasor measurements. The accuracy of fault location is performed with respect to fault location/position, types of fault, fault angle. The accuracy of the algorithm is simulated in MATLAB for 9-bus transmission system.
Optimal Location of Multi-types of FACTS Devices using Genetic Algorithm IJORCS
The problem of improving the voltage profile and reducing power loss in electrical networks is a task that must be solved in an optimal manner. Therefore, placement of FACTS devices in suitable location can lead to control in-line flow and maintain bus voltages in desired level and reducing losses is required. This paper presents one of the heuristic methods i.e. a Genetic Algorithm to seek the optimal location of FACTS devices in a power system. Proposed algorithm is tested on IEEE 30 bus power system for optimal location of multi-type FACTS devices and results are presented.
Faults Diagnosis in Five-Level Three-Phase Shunt Active Power FilterIAES-IJPEDS
In this paper, characteristics of open transistor faults in cascaded H-bridge
five-level three-phase PWM controlled shunt active power filter are
determined. Phase currents can’t be trusted as fault indicator since their
waveforms are slightly changed in the presence of open transistor fault. The
proposed method uses H bridges output voltages to determine the faulty
phase, the faulty bridge and more precisely, the open fault transistor.
Wavelet based analysis for transmission line fault locationAlexander Decker
This document summarizes a technique for locating faults on electric power transmission lines using wavelet analysis. It begins with an introduction to transmission line faults and issues with existing fault location methods. It then describes the basics of traveling wave theory and modal analysis for decomposing fault currents. A proposed algorithm is outlined that uses the discrete wavelet transform to analyze modal components of fault current received at a relay point. Time delays between modal components are used to determine the fault location based on the faulted transmission line length and wave propagation speed. Simulation results using MATLAB are presented to illustrate the approach. The method aims to provide accurate fault location independently of factors like fault inception angle and impedance.
Switched DC Sources Based Novel Multilevel InverterIRJET Journal
This document summarizes a research paper on a novel multilevel inverter topology that uses switched DC sources. The proposed topology connects alternate DC sources in opposite polarities through power switches, significantly reducing the number of switches compared to existing topologies. The operating principle of a single-phase five-level inverter using two DC sources is demonstrated. Mathematical equations are provided to describe the output voltage, source currents, voltage stresses on switches, and number of output levels for the generalized topology. Losses associated with the power switches are also discussed.
This document describes an "EasyQ" system that aims to remotely handle queues at filling stations. The system consists of three main components: 1) an EasyQ mobile application that allows users to submit their location and vehicle information and receive queue allocation details, 2) an EasyQ central system that allocates users to the closest filling station queue using a special algorithm, and 3) an EasyQ system at each filling station that authenticates users and manages queue status using RFID technology. The system is described as helping to reduce traffic, stress, and fuel usage by segmenting long queues into smaller temporal queues. Details are provided on the functions and interactions of the mobile app, central system, and station systems. The document concludes by discussing
Design and Implementation of New Encryption algorithm to Enhance Performance...IOSR Journals
This document summarizes a research paper that proposes a new encryption algorithm to improve performance parameters. The algorithm is divided into two phases. Phase 1 involves reversing, swapping, circularly shifting bits of the plaintext and XORing with the key. Phase 2 divides the output into blocks, then recombines the left bits of each block. The paper analyzes avalanche effect and execution time of the proposed algorithm compared to existing algorithms to evaluate its performance. The results show better performance than existing algorithms.
Periodic Table Gets Crowded In Year 2011.IOSR Journals
Abstract: Year 2011, has been specially important for teachers and students of chemistry, as after a gap of about 14 years at least five new elements were named and included in the periodic table. All these elements are synthetic and radioactive and some were actually made in 1999, but got their name and status by IUPAC, in July 2011. The total number of elements now in periodic table is 112, and scientists are trying their best to prepare elements with atomic numbers 118, 119 and 120 as well.
This document describes a method for separating source signals from interfering signals using an adaptive AMUSE algorithm. It begins with background on blind source separation and the AMUSE algorithm. The proposed method applies the adaptive AMUSE algorithm to signals obtained from nodes in an analog resistor-capacitor circuit, where one input signal is known. The algorithm estimates the source signals by reconstructing the signals using an extended Kalman smoother. The method is experimentally tested on a simulated resistor-capacitor circuit with three input signals and signals measured at random nodes.
The transmission overhead line is one of the vital elements in the power system for transmitting the electrical energy. In the transmission, the disturbances are often occurred. In the conventional algorithm, alpha and beta (mode) currents generated by Clarke’s transformation are utilized to convert the signal of Discrete Wavelet Transform (DWT) to obtain the Wavelet Transform Coefficient (WTC) and the Wavelet Coefficient Energy (WCE). This study introduces a new algorithm, called Modified Clarke for fault detection and classification using DWT and Back-Propagation Neural Network (BPNN) based on Clarke’s transformation on transmission overhead line by adding gamma current in the system. Daubechies4 (Db4) is used as a mother wavelet to decompose the high frequency components of the signal error. Simulation is performed using PSCAD / EMTDC transmission system modeling and carried out at different locations along the transmission line with different types of fault, fault resistances, fault locations and fault of the initial angle on a given power system model. The simulated fault types are in the study are the Single Line to Ground, the Line To Line, the Double Line to Ground and the Three Phases. There are four statistic methods utilized in the present study to determine the accuracy of detection and classification of faults. The result shows that the best and the worst structures of BPNN occurred on the configuration of 12-24-48-4 and 12-12-6-4, respectively. For instance, the error using Mean Square Error Method. The Error Of Clarke’s, Without Clarke’s and Modified Clarke’s are 0.05862, 0.05513 and 0.03721 which are the best, respectively, whereas, the worst are 0.06387, 0.0753 and 0.052, respectively. This indicates that the Modified Clarke’s result is in the lowest error. The method is successfully implement can be utilized in the detection and classification of fault in transmission line by utilities and power regulation in power system planning and operation.
Errors analysis in distance relay readings with presence of facts devicesAlexander Decker
1) The document analyzes errors in distance relay readings with the presence of FACTS devices like STATCOM and SSSC.
2) It presents models of SSSC and STATCOM and studies their impact on the measured impedance seen by the distance relay for single line to ground faults.
3) The analysis shows how the measured impedance, and the ideal tripping characteristic of the distance relay, are affected by the location and operational conditions of FACTS devices.
Transmission line is one the important compnent in protection of electric power system because the transmission line connects the power station with load centers.
The fault includes storms, lightning, snow, damage to insulation, short circuit fault [1].
Fault needs to be predicted earlier in order to be prevented before it occur
- 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.
Wavelet based double line and double line -to- ground fault discrimination i...IAEME Publication
In this paper, an accurate method to discriminate double line and double line to ground faults
in a three terminal transmission circuit based on wavelet transforms is presented. The proposed
algorithm uses the fault indices of three phase currents of all terminals. Fault indices are obtained by
1st level decomposition of current signals using Bior 1.5 mother wavelet considering the variations
in fault resistance, fault inception angle and distance along the transmission circuit. The entire test
results clearly show that the variation in the value of fault index of the healthy phase with the
presence of ground and constant value in the case of non- presence of ground which discriminates
double line fault from the double line to ground faults in the path along one terminal towards the
other terminal with variations in fault inception angle and fault resistance. The algorithm is proved to
be effective and efficient in detection and discrimination of faults.
Power System’stransmission Line Relaying Improvement Using Discrete Wavelet T...IJERA Editor
Transmission line is a path between the generating station and load(Industries & Domestic). These lines are several kilometres and always attracted towards faults. These Faults are Phase to Ground (P-G), Phase to Phase (P-P), Phase to Phase to Ground (P-P-G) and Symmetrical Fault (P-P-P\P-P-P-G).In order to protect the power system, faults should be cleared within stipulated time. Relay plays a key role in power system protection, before employing them in system, their parameters should be pre-determined.The proposed system uses Discrete Wavelet Transform to determine the fault levels in power system. It is used to extract the hidden factors i.e. Transients, from the faulty current signals by performing decomposition at different levels. Test system is modelled and fault signals are imported to workspace and test the reliability of the algorithm. The proposed system modelled in MATLAB\SIMULINK to detect, classify and locate all the possible faults in the transmission line in the power system which are nothing but parameters of relays.
This document presents a mathematical model and MATLAB simulation of a solar photovoltaic cell and array. It describes the equivalent circuit of a solar cell and defines equations for photocurrent, saturation current, and output current of an ideal cell. A Simulink model of a single cell is used to generate I-V and P-V curves showing maximum power point. The document also discusses modeling a solar array by connecting modules in series and parallel. Simulation results show output characteristics at different irradiances and temperatures.
This document presents the design and simulation of three different SU-8 microelectromechanical systems (MEMS) switch configurations for radio frequency (RF) applications with low actuation voltages: cantilever, clamped-clamped beam, and meandered. The switches were simulated using Coventorware software. The cantilever and meandered switches had a pull-in voltage of 2.5V, while the clamped-clamped beam's pull-in voltage ranged from 4-7V depending on width. Material selection studies showed SU-8 provided the lowest pull-in voltages. Wider beams increased resonant frequency but also increased pull-in voltage. RF simulations in Agilent ADS showed
Brief Literature Review on Phasor Based Transmission Line Fault Location Algo...sarasijdas
This document summarizes various phasor-based fault location algorithms for transmission lines. It categorizes algorithms as traditional knowledge-based, traveling wave-based, or phasor-based methods that can use synchronized or unsynchronized data from single-end, double-end, or multi-terminal lines. Factors affecting accuracy are discussed. Selected algorithms are presented for untransposed parallel lines, lines with cables, multi-terminal lines, and series compensated lines. References for various algorithms are provided.
This document describes a special project on using an artificial neural network (ANN) for load flow studies of the MSU-IIT electrical system. The objectives are to model the power system as a 5-bus system, evaluate bus voltages using a power flow program under different loads, train an ANN using the power flow results, and validate the ANN's accuracy by comparing its results to the power flow program. The document reviews literature on load flow studies, numerical methods, ANNs, and discusses how ANNs could provide faster and more accurate solutions to complex load flow problems compared to numerical methods.
Double Circuit Transmission Line Protection using Line Trap & Artificial Neur...IRJET Journal
This document presents a technique for protecting double circuit transmission lines using line traps and artificial neural networks. Line traps are placed at the terminals of the protected line to detect faults based on high frequency transients. An artificial neural network is trained using the RMS voltage and current signals to classify fault types. MATLAB simulation studies were conducted to model a 300km, 25kV, 50Hz transmission system with three zones. RMS measurements from one end were used to train the neural network to classify faults. The neural network approach provides fast, secure and reliable protection for double circuit transmission lines.
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.
A Fault Detection and Classification Method for SC Transmission Line Using Ph...paperpublications3
Abstract: In this paper, fault detection and classification for Series Compensated Line (SCL) using phasor measurement unit is presented. The algorithm presented in this paper uses the PMU synchronized measurements and not depends on the data to be provided by the electricity utility. The compensated line parameters and Thevenin’s equivalent (TE) of the system at SCL terminals are calculated online, using three independent sets of pre-fault phasor measurements. The accuracy of fault location is performed with respect to fault location/position, types of fault, fault angle. The accuracy of the algorithm is simulated in MATLAB for 9-bus transmission system.
Optimal Location of Multi-types of FACTS Devices using Genetic Algorithm IJORCS
The problem of improving the voltage profile and reducing power loss in electrical networks is a task that must be solved in an optimal manner. Therefore, placement of FACTS devices in suitable location can lead to control in-line flow and maintain bus voltages in desired level and reducing losses is required. This paper presents one of the heuristic methods i.e. a Genetic Algorithm to seek the optimal location of FACTS devices in a power system. Proposed algorithm is tested on IEEE 30 bus power system for optimal location of multi-type FACTS devices and results are presented.
Faults Diagnosis in Five-Level Three-Phase Shunt Active Power FilterIAES-IJPEDS
In this paper, characteristics of open transistor faults in cascaded H-bridge
five-level three-phase PWM controlled shunt active power filter are
determined. Phase currents can’t be trusted as fault indicator since their
waveforms are slightly changed in the presence of open transistor fault. The
proposed method uses H bridges output voltages to determine the faulty
phase, the faulty bridge and more precisely, the open fault transistor.
Wavelet based analysis for transmission line fault locationAlexander Decker
This document summarizes a technique for locating faults on electric power transmission lines using wavelet analysis. It begins with an introduction to transmission line faults and issues with existing fault location methods. It then describes the basics of traveling wave theory and modal analysis for decomposing fault currents. A proposed algorithm is outlined that uses the discrete wavelet transform to analyze modal components of fault current received at a relay point. Time delays between modal components are used to determine the fault location based on the faulted transmission line length and wave propagation speed. Simulation results using MATLAB are presented to illustrate the approach. The method aims to provide accurate fault location independently of factors like fault inception angle and impedance.
Switched DC Sources Based Novel Multilevel InverterIRJET Journal
This document summarizes a research paper on a novel multilevel inverter topology that uses switched DC sources. The proposed topology connects alternate DC sources in opposite polarities through power switches, significantly reducing the number of switches compared to existing topologies. The operating principle of a single-phase five-level inverter using two DC sources is demonstrated. Mathematical equations are provided to describe the output voltage, source currents, voltage stresses on switches, and number of output levels for the generalized topology. Losses associated with the power switches are also discussed.
This document describes an "EasyQ" system that aims to remotely handle queues at filling stations. The system consists of three main components: 1) an EasyQ mobile application that allows users to submit their location and vehicle information and receive queue allocation details, 2) an EasyQ central system that allocates users to the closest filling station queue using a special algorithm, and 3) an EasyQ system at each filling station that authenticates users and manages queue status using RFID technology. The system is described as helping to reduce traffic, stress, and fuel usage by segmenting long queues into smaller temporal queues. Details are provided on the functions and interactions of the mobile app, central system, and station systems. The document concludes by discussing
Design and Implementation of New Encryption algorithm to Enhance Performance...IOSR Journals
This document summarizes a research paper that proposes a new encryption algorithm to improve performance parameters. The algorithm is divided into two phases. Phase 1 involves reversing, swapping, circularly shifting bits of the plaintext and XORing with the key. Phase 2 divides the output into blocks, then recombines the left bits of each block. The paper analyzes avalanche effect and execution time of the proposed algorithm compared to existing algorithms to evaluate its performance. The results show better performance than existing algorithms.
Periodic Table Gets Crowded In Year 2011.IOSR Journals
Abstract: Year 2011, has been specially important for teachers and students of chemistry, as after a gap of about 14 years at least five new elements were named and included in the periodic table. All these elements are synthetic and radioactive and some were actually made in 1999, but got their name and status by IUPAC, in July 2011. The total number of elements now in periodic table is 112, and scientists are trying their best to prepare elements with atomic numbers 118, 119 and 120 as well.
This document describes using the Taguchi method to optimize process parameters for an extrusion blown film machinery that produces high-density polyethylene (HDPE) films. Four process parameters were considered: extrusion pressure, melting temperature, winding speed, and extruder speed. Experiments were conducted using an L9 orthogonal array. The tensile strength results showed that melting temperature has the most significant effect on tensile strength, followed by extruder speed, extrusion pressure, and winding speed. The optimal parameter settings found were an extrusion pressure of 180 MPa, melting temperature of 200°C, winding speed of 40 rpm, and extruder speed of 75 rpm.
On The Origin of Electromagnetic Waves from Lightning DischargesIOSR Journals
Interaction of up going ion beam forming current flow in the pre-ionized stepped leader plasma and
the way, how the kinetic energy of the beam particles is converted into electromagnetic energy have been
discussed. The ion beam interaction with the plasma wave modes in the stepped leader channel produces
perturbations in the return stroke current flow and changes its uniformity and becomes non-uniform. In the
present study, the return current is taken to be deeply modulated at a given modulation frequency, and
considered that it behaves like an antenna for electromagnetic radiation. In this paper the total amount of
energy associated with return stroke is given to electromagnetic waves is estimated.
This document summarizes a research paper that proposes and evaluates two multi-agent learning algorithms, strategy sharing and joint rewards, to improve decision making. It first provides background on multi-agent learning and reinforcement learning. It then describes a multi-agent model and the two proposed algorithms - strategy sharing averages Q-tables across agents, while joint rewards combines Q-learning with shared rewards. The paper presents results showing the performance of the two algorithms and concludes that multi-agent learning can enhance decision making.
The document discusses using Learning Factor Analysis (LFA), an educational data mining technique, to model student knowledge based on student-tutor interaction log data. LFA uses a multiple logistic regression model with difficulty factors defined by subject experts to quantify skills. A combinatorial search method called A* search is used to select the best-fitting model. The document illustrates applying LFA to data from an online math tutor, identifying 5 skills and presenting the results of the logistic regression modeling, including fit statistics and learning rates for skills. Learning curves are used to visualize student performance over time.
Dynamic Error Concealment Algorithm for Multiview Coding Using Lost MBs Size...IOSR Journals
The document proposes an adaptive error concealment algorithm for multiview video coding that exploits spatial, temporal, and inter-view information. For intra macroblocks, a Spatial-Inter View algorithm is used to conceal errors using weighted pixel averaging and disparity vectors from other views. For inter macroblocks, the algorithm adaptively selects candidate macroblocks for replacement based on the size of the lost macroblock and the view of the reference frame, generating additional candidates to find better matches. Simulation results show the proposed algorithm achieves up to 12.4 dB and 0.73 dB higher PSNR than applying no error concealment or a normal algorithm, respectively, with better subjective quality and lower complexity.
This document describes a smart manufacturing execution system called NIRMAN Factory Information System (FIS) that is designed to acquire data from a factory floor and provide real-time monitoring and analysis capabilities to managers. The system uses sensors and an Arduino board to collect data on production status, factory environment conditions, power usage, and employee attendance. This data is transmitted via Bluetooth to an Android application that displays summaries, calculations of efficiency and productivity, and graphical analyses. The system is intended to help managers optimize operations and respond quickly to issues or emergencies on the factory floor.
Privacy Preserving Clustering on Distorted dataIOSR Journals
- The document discusses privacy-preserving clustering on distorted data using singular value decomposition (SVD) and sparsified singular value decomposition (SSVD).
- It applies SVD and SSVD to distort a real-world dataset of 100 terrorists with 42 attributes, generating distorted datasets.
- K-means clustering is then performed on the original and distorted datasets for different numbers of clusters (k). The results show that SSVD more effectively groups the data objects into clusters compared to the original and SVD-distorted datasets, while preserving data privacy as measured by various metrics.
This document proposes an autonomous self-assessment application that can intelligently determine the running time of processes based on the processor state and process priority. It uses several scheduling algorithms like shortest job first, first come first serve, priority, round robin, and multilevel queue scheduling. The application divides work into predicting process running times and scheduling a series of processes to optimize results. It calculates process weights, stores running time data, and uses that historical data to predict future running times. It then schedules processes using a priority-based approach and adjusts priorities if smaller processes are waiting too long. The results show the application can determine expected running times for given processes using this approach.
This document proposes a novel method for generating secret keys for stream ciphers used in secure communication. The method constructs keys from digital images by:
1. Separating the image into grayscale color channels.
2. Calculating the number of pixels in intensity ranges for each channel.
3. Comparing the pixel counts to a threshold to generate a 50-bit key for each channel.
The keys are then used to encrypt messages by applying XOR operations between the plaintext and key bits. The same method decrypts ciphertexts by reversing the XOR operations. Examples demonstrate encrypting messages with keys generated from images.
The document describes a laser pointer interaction system for manipulating 3D medical images on a large display in operating rooms. The system uses a webcam to detect the laser spot and track its movements. It recognizes two types of gestures - a circle gesture with two directions and a line gesture with four directions. The system was tested on 15 subjects performing rotation and zooming tasks on a 3D model. Experiments showed that the dynamic time warping algorithm recognized gestures with 89.6% accuracy and was faster than the 1$ recognizer algorithm. The laser pointer system provides a potential hands-free alternative to traditional mouse/keyboard control in operating rooms.
This document proposes a Quorum-based Medium Access Control (QMAC) protocol to improve energy efficiency in wireless sensor networks. QMAC enables sensor nodes to sleep longer under light traffic loads by only waking up during scheduled "quorum times". Each node selects one row and column from a grid as its quorum set. This ensures any two nodes' quorums will intersect at some time, allowing communication while keeping individual duty cycles low. Results show QMAC conserves more energy and maintains low latency compared to existing protocols that require waking at every time frame regardless of traffic. QMAC selectively wakes sensor nodes only when needed to balance energy savings and communication ability.
This document describes an improved Max-Min scheduling algorithm that considers additional constraints beyond just completion time. The improved algorithm calculates a proportional fairness score for each job/task based on its size, completion time, payload storage rate, and RAM requirements. It then sorts the jobs based on these scores to prioritize jobs with the highest scores, addressing limitations of the traditional Max-Min algorithm that only considers completion time. The algorithm is evaluated using a simulator with scientific workflows and workloads. Results show the improved algorithm efficiently schedules jobs while accounting for multiple constraints.
IOSR Journal of Humanities and Social Science is an International Journal edited by International Organization of Scientific Research (IOSR).The Journal provides a common forum where all aspects of humanities and social sciences are presented. IOSR-JHSS publishes original papers, review papers, conceptual framework, analytical and simulation models, case studies, empirical research, technical notes etc.
Significance of Solomon four group pretest-posttest method in True Experiment...IOSR Journals
The document reviews the co-management approach in Hail Haor, Sylhet, Bangladesh to address climate change impacts. It finds that the two main Resource Management Organizations (RMOs), Borogangina and Dumuria, are reasonably operational but Borogangina (score of 80.60) performs better than Dumuria (score of 66). The respondent community perceives increases in temperature and siltation as well as decreases in rainfall and water flow. The co-management system aims to sustainably manage fisheries and conserve the ecosystem, though some challenges remain for the RMOs.
This document presents an optimized framework for online admission systems with reference to professional programs in Maharashtra, India. It summarizes the key steps:
1) The framework is derived from studying the admission processes of 46 organizations offering various professional programs like engineering, management, health sciences, etc.
2) Common steps in the admission processes are identified through data mining and grouped into 5 main admission processes.
3) Generic process diagrams are presented for each major professional program by combining the steps from the different organizations.
4) The framework is proposed to standardize, evaluate and optimize the online admission processes for professional programs in Maharashtra.
The document summarizes the debottlenecking of a Bernoulli's apparatus that had been out of order for over a decade at BIT Sindri Dhanbad, India. It aims to verify Bernoulli's principle with this apparatus. The document provides background on fluid mechanics, including fluid properties, types of fluids, basic laws, and Bernoulli's theorem. It then describes the construction details and experimental method used for the Bernoulli's apparatus. Observations and calculations are presented to verify Bernoulli's theorem, with final results confirming the theorem.
This document describes a system for extracting named entities and their relationships from unstructured text data using n-gram features. It uses a hidden Markov model to extract and classify entities into types like person, location, organization. It then uses a conditional random field with kernel approach to detect relationships between the extracted entities. The system takes unstructured text as input, performs preprocessing like tokenization and stop word removal, extracts n-gram, part-of-speech and lexicon features which are then combined and used to train the HMM model to classify entities and CRF model to detect relationships between entities.
Ann and impedance combined method for fault location in electrical power dist...IAEME Publication
This document describes a method for single line-to-ground fault location in electrical power distribution systems using an artificial neural network (ANN) combined with apparent impedance. The method estimates the fault resistance and apparent reactance using voltage and current measurements, which are then used as inputs to an ANN to determine the faulty section. The ANN is trained using simulated faults on a real 7.5 km distribution feeder. Test results show the ANN can accurately locate faults for resistances from 0-100 ohms and locations along the line.
International Journal of Engineering Research and Applications (IJERA) aims to cover the latest outstanding developments in the field of all Engineering Technologies & science.
International Journal of Engineering Research and Applications (IJERA) is a team of researchers not publication services or private publications running the journals for monetary benefits, we are association of scientists and academia who focus only on supporting authors who want to publish their work. The articles published in our journal can be accessed online, all the articles will be archived for real time access.
Our journal system primarily aims to bring out the research talent and the works done by sciaentists, academia, engineers, practitioners, scholars, post graduate students of engineering and science. This journal aims to cover the scientific research in a broader sense and not publishing a niche area of research facilitating researchers from various verticals to publish their papers. It is also aimed to provide a platform for the researchers to publish in a shorter of time, enabling them to continue further All articles published are freely available to scientific researchers in the Government agencies,educators and the general public. We are taking serious efforts to promote our journal across the globe in various ways, we are sure that our journal will act as a scientific platform for all researchers to publish their works online.
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.
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.
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
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%.
This document summarizes a research paper that explores using synchrophasor technology for transmission line fault detection via current differential protection. It begins by discussing limitations of traditional current differential protection schemes. It then provides details on implementing a digital current differential protection scheme using synchronized phasor measurements from Phasor Measurement Units at both ends of a transmission line. The paper describes simulating this approach in MATLAB for different fault types, locations, and resistances on a sample transmission system. It is able to compensate for charging currents and achieve nearly 100% reliability in fault detection using synchrophasor-based current differential protection.
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.
Determination of Fault Location and Type in Distribution Systems using Clark ...IJAPEJOURNAL
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.
Intelligent Fault Identification System for Transmission Lines Using Artifici...IOSR Journals
Transmission and distribution lines are vital links between generating units and consumers. They are
exposed to atmosphere, hence chances of occurrence of fault in transmission line is very high, which has to be
immediately taken care of in order to minimize damage caused by it. This paper focuses on detecting the faults
on electric power transmission lines using artificial neural networks. A feed forward neural network is
employed, which is trained with back propagation algorithm. Analysis on neural networks with varying number
of hidden layers and neurons per hidden layer has been provided to validate the choice of the neural networks
in each step. The developed neural network is capable of detecting single line to ground and double line to
ground for all the three phases. Simulation is done using MATLAB Simulink to demonstrate that artificial
neural network based method are efficient in detecting faults on transmission lines and achieve satisfactory
performances. A 300km, 25kv transmission line is used to validate the proposed fault detection system.
Hardware implementation of neural network is done on TMS320C6713.
Wavelet based double line and double line -to- ground fault discrimination i...IAEME Publication
This document presents a method for discriminating between double line faults and double line-to-ground faults in a three terminal transmission circuit using wavelet transforms. The proposed algorithm analyzes the detail coefficients from the first level decomposition of phase current signals at each terminal using the Bior 1.5 mother wavelet. The algorithm discriminates between the fault types based on variations in the fault index of the healthy phase, which remains constant for double line faults but varies for faults involving ground. Simulation results demonstrate the effectiveness of using the proposed wavelet-based fault indices to discriminate between the fault types at different locations along each transmission path with variations in fault inception angle and resistance.
Evaluation of earth fault location algorithm in medium voltage distribution n...IJECEIAES
This paper focused on studying an algorithm of earth fault location in the medium voltage distribution network. In power system network, most of the earth fault occurs is a single line to ground fault. A medium voltage distribution network with resistance earthing at the main substation and an earth fault attached along the distribution network is modeled in ATP Draw. The generated earth fault is simulated, and the voltage and current signal produced is recorded. The earth fault location algorithm is simulated and tested in MATLAB. The accuracy of the earth fault location algorithm is tested at several locations and fault resistances. A possible correction technique is explained to minimize the error. The results show an improvement fault location distance estimation with minimum error.
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.
The document describes a power system model used to obtain training data for an artificial neural network (ANN) to detect high impedance faults. The power system model includes two radial distribution feeders with linear and nonlinear loads, voltage correction capacitor banks, and an equivalent high impedance fault arc model. Digital simulations were performed using an electromagnetic transient program to generate training data for different fault types, locations, and contingencies like capacitor switching. The proposed ANN module processes current and voltage signals at the beginning of the distribution line. Its six inputs are the second and third harmonics of residual current and voltage, as well as the second and third harmonics of residual apparent impedance. The ANN is trained to detect high impedance faults based
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.
Modeling and simulation of single phase transformer inrush current using neur...Alexander Decker
This document discusses modeling and simulating transformer inrush current using a neural network. It presents equations to calculate inrush current based on transformer parameters. Data on time and flux linkage values during inrush are obtained via simulation in MATLAB and used to train a neural network. The trained network accurately models the inrush current waveform, with an average 1.056% error compared to a semi-analytic solution. Tables and figures show the neural network structure, weights, training error reduction, and ability to model the magnetization curve matching the semi-analytic solution.
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.
This document presents a technique for locating faults on double circuit transmission lines using wavelet transform and wavelet modulus maxima. The technique uses traveling wave theory and modal decomposition to transform coupled three-phase voltages and currents into independent modal components. Wavelet analysis is then used to obtain the wavelet transform coefficients of each modal component. The time difference between wavelet modulus maxima peaks of the modal components indicates the fault location. Simulation results demonstrate the validity of the technique for various fault types, locations, resistances, and inception angles. The technique can accurately locate faults using data from a single line terminal.
This document provides a technical review of secure banking using RSA and AES encryption methodologies. It discusses how RSA and AES are commonly used encryption standards for secure data transmission between ATMs and bank servers. The document first provides background on ATM security measures and risks of attacks. It then reviews related work analyzing encryption techniques. The document proposes using a one-time password in addition to a PIN for ATM authentication. It concludes that implementing encryption standards like RSA and AES can make transactions more secure and build trust in online banking.
This document analyzes the performance of various modulation schemes for achieving energy efficient communication over fading channels in wireless sensor networks. It finds that for long transmission distances, low-order modulations like BPSK are optimal due to their lower SNR requirements. However, as transmission distance decreases, higher-order modulations like 16-QAM and 64-QAM become more optimal since they can transmit more bits per symbol, outweighing their higher SNR needs. Simulations show lifetime extensions up to 550% are possible in short-range networks by using higher-order modulations instead of just BPSK. The optimal modulation depends on transmission distance and balancing the energy used by electronic components versus power amplifiers.
This document provides a review of mobility management techniques in vehicular ad hoc networks (VANETs). It discusses three modes of communication in VANETs: vehicle-to-infrastructure (V2I), vehicle-to-vehicle (V2V), and hybrid vehicle (HV) communication. For each communication mode, different mobility management schemes are required due to their unique characteristics. The document also discusses mobility management challenges in VANETs and outlines some open research issues in improving mobility management for seamless communication in these dynamic networks.
This document provides a review of different techniques for segmenting brain MRI images to detect tumors. It compares the K-means and Fuzzy C-means clustering algorithms. K-means is an exclusive clustering algorithm that groups data points into distinct clusters, while Fuzzy C-means is an overlapping clustering algorithm that allows data points to belong to multiple clusters. The document finds that Fuzzy C-means requires more time for brain tumor detection compared to other methods like hierarchical clustering or K-means. It also reviews related work applying these clustering algorithms to segment brain MRI images.
1) The document simulates and compares the performance of AODV and DSDV routing protocols in a mobile ad hoc network under three conditions: when users are fixed, when users move towards the base station, and when users move away from the base station.
2) The results show that both protocols have higher packet delivery and lower packet loss when users are either fixed or moving towards the base station, since signal strength is better in those scenarios. Performance degrades when users move away from the base station due to weaker signals.
3) AODV generally has better performance than DSDV, with higher throughput and packet delivery rates observed across the different user mobility conditions.
This document describes the design and implementation of 4-bit QPSK and 256-bit QAM modulation techniques using MATLAB. It compares the two techniques based on SNR, BER, and efficiency. The key steps of implementing each technique in MATLAB are outlined, including generating random bits, modulation, adding noise, and measuring BER. Simulation results show scatter plots and eye diagrams of the modulated signals. A table compares the results, showing that 256-bit QAM provides better performance than 4-bit QPSK. The document concludes that QAM modulation is more effective for digital transmission systems.
The document proposes a hybrid technique using Anisotropic Scale Invariant Feature Transform (A-SIFT) and Robust Ensemble Support Vector Machine (RESVM) to accurately identify faces in images. A-SIFT improves upon traditional SIFT by applying anisotropic scaling to extract richer directional keypoints. Keypoints are processed with RESVM and hypothesis testing to increase accuracy above 95% by repeatedly reprocessing images until the threshold is met. The technique was tested on similar and different facial images and achieved better results than SIFT in retrieval time and reduced keypoints.
This document studies the effects of dielectric superstrate thickness on microstrip patch antenna parameters. Three types of probes-fed patch antennas (rectangular, circular, and square) were designed to operate at 2.4 GHz using Arlondiclad 880 substrate. The antennas were tested with and without an Arlondiclad 880 superstrate of varying thicknesses. It was found that adding a superstrate slightly degraded performance by lowering the resonant frequency and increasing return loss and VSWR, while decreasing bandwidth and gain. Specifically, increasing the superstrate thickness or dielectric constant resulted in greater changes to the antenna parameters.
This document describes a wireless environment monitoring system that utilizes soil energy as a sustainable power source for wireless sensors. The system uses a microbial fuel cell to generate electricity from the microbial activity in soil. Two microbial fuel cells were created using different soil types and various additives to produce different current and voltage outputs. An electronic circuit was designed on a printed circuit board with components like a microcontroller and ZigBee transceiver. Sensors for temperature and humidity were connected to the circuit to monitor the environment wirelessly. The system provides a low-cost way to power remote sensors without needing battery replacement and avoids the high costs of wiring a power source.
1) The document proposes a model for a frequency tunable inverted-F antenna that uses ferrite material.
2) The resonant frequency of the antenna can be significantly shifted from 2.41GHz to 3.15GHz, a 31% shift, by increasing the static magnetic field placed on the ferrite material.
3) Altering the permeability of the ferrite allows tuning of the antenna's resonant frequency without changing the physical dimensions, providing flexibility to operate over a wide frequency range.
This document summarizes a research paper that presents a speech enhancement method using stationary wavelet transform. The method first classifies speech into voiced, unvoiced, and silence regions based on short-time energy. It then applies different thresholding techniques to the wavelet coefficients of each region - modified hard thresholding for voiced speech, semi-soft thresholding for unvoiced speech, and setting coefficients to zero for silence. Experimental results using speech from the TIMIT database corrupted with white Gaussian noise at various SNR levels show improved performance over other popular denoising methods.
This document reviews the design of an energy-optimized wireless sensor node that encrypts data for transmission. It discusses how sensing schemes that group nodes into clusters and transmit aggregated data can reduce energy consumption compared to individual node transmissions. The proposed node design calculates the minimum transmission power needed based on received signal strength and uses a periodic sleep/wake cycle to optimize energy when not sensing or transmitting. It aims to encrypt data at both the node and network level to further optimize energy usage for wireless communication.
This document discusses group consumption modes. It analyzes factors that impact group consumption, including external environmental factors like technological developments enabling new forms of online and offline interactions, as well as internal motivational factors at both the group and individual level. The document then proposes that group consumption modes can be divided into four types based on two dimensions: vertical (group relationship intensity) and horizontal (consumption action period). These four types are instrument-oriented, information-oriented, enjoyment-oriented, and relationship-oriented consumption modes. Finally, the document notes that consumption modes are dynamic and can evolve over time.
The document summarizes a study of different microstrip patch antenna configurations with slotted ground planes. Three antenna designs were proposed and their performance evaluated through simulation: a conventional square patch, an elliptical patch, and a star-shaped patch. All antennas were mounted on an FR4 substrate. The effects of adding different slot patterns to the ground plane on resonance frequency, bandwidth, gain and efficiency were analyzed parametrically. Key findings were that reshaping the patch and adding slots increased bandwidth and shifted resonance frequency. The elliptical and star patches in particular performed better than the conventional design. Three antenna configurations were selected for fabrication and measurement based on the simulations: a conventional patch with a slot under the patch, an elliptical patch with slots
1) The document describes a study conducted to improve call drop rates in a GSM network through RF optimization.
2) Drive testing was performed before and after optimization using TEMS software to record network parameters like RxLevel, RxQuality, and events.
3) Analysis found call drops were occurring due to issues like handover failures between sectors, interference from adjacent channels, and overshooting due to antenna tilt.
4) Corrective actions taken included defining neighbors between sectors, adjusting frequencies to reduce interference, and lowering the mechanical tilt of an antenna.
5) Post-optimization drive testing showed improvements in RxLevel, RxQuality, and a reduction in dropped calls.
This document describes the design of an intelligent autonomous wheeled robot that uses RF transmission for communication. The robot has two modes - automatic mode where it can make its own decisions, and user control mode where a user can control it remotely. It is designed using a microcontroller and can perform tasks like object recognition using computer vision and color detection in MATLAB, as well as wall painting using pneumatic systems. The robot's movement is controlled by DC motors and it uses sensors like ultrasonic sensors and gas sensors to navigate autonomously. RF transmission allows communication between the robot and a remote control unit. The overall aim is to develop a low-cost robotic system for industrial applications like material handling.
This document reviews cryptography techniques to secure the Ad-hoc On-Demand Distance Vector (AODV) routing protocol in mobile ad-hoc networks. It discusses various types of attacks on AODV like impersonation, denial of service, eavesdropping, black hole attacks, wormhole attacks, and Sybil attacks. It then proposes using the RC6 cryptography algorithm to secure AODV by encrypting data packets and detecting and removing malicious nodes launching black hole attacks. Simulation results show that after applying RC6, the packet delivery ratio and throughput of AODV increase while delay decreases, improving the security and performance of the network under attack.
The document describes a proposed modification to the conventional Booth multiplier that aims to increase its speed by applying concepts from Vedic mathematics. Specifically, it utilizes the Urdhva Tiryakbhyam formula to generate all partial products concurrently rather than sequentially. The proposed 8x8 bit multiplier was coded in VHDL, simulated, and found to have a path delay 44.35% lower than a conventional Booth multiplier, demonstrating its potential for higher speed.
This document discusses image deblurring techniques. It begins by introducing image restoration and focusing on image deblurring. It then discusses challenges with image deblurring being an ill-posed problem. It reviews existing approaches to screen image deconvolution including estimating point spread functions and iteratively estimating blur kernels and sharp images. The document also discusses handling spatially variant blur and summarizes the relationship between the proposed method and previous work for different blur types. It proposes using color filters in the aperture to exploit parallax cues for segmentation and blur estimation. Finally, it proposes moving the image sensor circularly during exposure to prevent high frequency attenuation from motion blur.
This document describes modeling an adaptive controller for an aircraft roll control system using PID, fuzzy-PID, and genetic algorithm. It begins by introducing the aircraft roll control system and motivation for developing an adaptive controller to minimize errors from noisy analog sensor signals. It then provides the mathematical model of aircraft roll dynamics and describes modeling the real-time flight control system in MATLAB/Simulink. The document evaluates PID, fuzzy-PID, and PID-GA (genetic algorithm) controllers for aircraft roll control and finds that the PID-GA controller delivers the best performance.
Unlocking Productivity: Leveraging the Potential of Copilot in Microsoft 365, a presentation by Christoforos Vlachos, Senior Solutions Manager – Modern Workplace, Uni Systems
AI 101: An Introduction to the Basics and Impact of Artificial IntelligenceIndexBug
Imagine a world where machines not only perform tasks but also learn, adapt, and make decisions. This is the promise of Artificial Intelligence (AI), a technology that's not just enhancing our lives but revolutionizing entire industries.
HCL Notes and Domino License Cost Reduction in the World of DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-and-domino-license-cost-reduction-in-the-world-of-dlau/
The introduction of DLAU and the CCB & CCX licensing model caused quite a stir in the HCL community. As a Notes and Domino customer, you may have faced challenges with unexpected user counts and license costs. You probably have questions on how this new licensing approach works and how to benefit from it. Most importantly, you likely have budget constraints and want to save money where possible. Don’t worry, we can help with all of this!
We’ll show you how to fix common misconfigurations that cause higher-than-expected user counts, and how to identify accounts which you can deactivate to save money. There are also frequent patterns that can cause unnecessary cost, like using a person document instead of a mail-in for shared mailboxes. We’ll provide examples and solutions for those as well. And naturally we’ll explain the new licensing model.
Join HCL Ambassador Marc Thomas in this webinar with a special guest appearance from Franz Walder. It will give you the tools and know-how to stay on top of what is going on with Domino licensing. You will be able lower your cost through an optimized configuration and keep it low going forward.
These topics will be covered
- Reducing license cost by finding and fixing misconfigurations and superfluous accounts
- How do CCB and CCX licenses really work?
- Understanding the DLAU tool and how to best utilize it
- Tips for common problem areas, like team mailboxes, functional/test users, etc
- Practical examples and best practices to implement right away
AI-Powered Food Delivery Transforming App Development in Saudi Arabia.pdfTechgropse Pvt.Ltd.
In this blog post, we'll delve into the intersection of AI and app development in Saudi Arabia, focusing on the food delivery sector. We'll explore how AI is revolutionizing the way Saudi consumers order food, how restaurants manage their operations, and how delivery partners navigate the bustling streets of cities like Riyadh, Jeddah, and Dammam. Through real-world case studies, we'll showcase how leading Saudi food delivery apps are leveraging AI to redefine convenience, personalization, and efficiency.
CAKE: Sharing Slices of Confidential Data on BlockchainClaudio Di Ciccio
Presented at the CAiSE 2024 Forum, Intelligent Information Systems, June 6th, Limassol, Cyprus.
Synopsis: Cooperative information systems typically involve various entities in a collaborative process within a distributed environment. Blockchain technology offers a mechanism for automating such processes, even when only partial trust exists among participants. The data stored on the blockchain is replicated across all nodes in the network, ensuring accessibility to all participants. While this aspect facilitates traceability, integrity, and persistence, it poses challenges for adopting public blockchains in enterprise settings due to confidentiality issues. In this paper, we present a software tool named Control Access via Key Encryption (CAKE), designed to ensure data confidentiality in scenarios involving public blockchains. After outlining its core components and functionalities, we showcase the application of CAKE in the context of a real-world cyber-security project within the logistics domain.
Paper: https://doi.org/10.1007/978-3-031-61000-4_16
Essentials of Automations: The Art of Triggers and Actions in FMESafe Software
In this second installment of our Essentials of Automations webinar series, we’ll explore the landscape of triggers and actions, guiding you through the nuances of authoring and adapting workspaces for seamless automations. Gain an understanding of the full spectrum of triggers and actions available in FME, empowering you to enhance your workspaces for efficient automation.
We’ll kick things off by showcasing the most commonly used event-based triggers, introducing you to various automation workflows like manual triggers, schedules, directory watchers, and more. Plus, see how these elements play out in real scenarios.
Whether you’re tweaking your current setup or building from the ground up, this session will arm you with the tools and insights needed to transform your FME usage into a powerhouse of productivity. Join us to discover effective strategies that simplify complex processes, enhancing your productivity and transforming your data management practices with FME. Let’s turn complexity into clarity and make your workspaces work wonders!
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc
How does your privacy program stack up against your peers? What challenges are privacy teams tackling and prioritizing in 2024?
In the fifth annual Global Privacy Benchmarks Survey, we asked over 1,800 global privacy professionals and business executives to share their perspectives on the current state of privacy inside and outside of their organizations. This year’s report focused on emerging areas of importance for privacy and compliance professionals, including considerations and implications of Artificial Intelligence (AI) technologies, building brand trust, and different approaches for achieving higher privacy competence scores.
See how organizational priorities and strategic approaches to data security and privacy are evolving around the globe.
This webinar will review:
- The top 10 privacy insights from the fifth annual Global Privacy Benchmarks Survey
- The top challenges for privacy leaders, practitioners, and organizations in 2024
- Key themes to consider in developing and maintaining your privacy program
Removing Uninteresting Bytes in Software FuzzingAftab Hussain
Imagine a world where software fuzzing, the process of mutating bytes in test seeds to uncover hidden and erroneous program behaviors, becomes faster and more effective. A lot depends on the initial seeds, which can significantly dictate the trajectory of a fuzzing campaign, particularly in terms of how long it takes to uncover interesting behaviour in your code. We introduce DIAR, a technique designed to speedup fuzzing campaigns by pinpointing and eliminating those uninteresting bytes in the seeds. Picture this: instead of wasting valuable resources on meaningless mutations in large, bloated seeds, DIAR removes the unnecessary bytes, streamlining the entire process.
In this work, we equipped AFL, a popular fuzzer, with DIAR and examined two critical Linux libraries -- Libxml's xmllint, a tool for parsing xml documents, and Binutil's readelf, an essential debugging and security analysis command-line tool used to display detailed information about ELF (Executable and Linkable Format). Our preliminary results show that AFL+DIAR does not only discover new paths more quickly but also achieves higher coverage overall. This work thus showcases how starting with lean and optimized seeds can lead to faster, more comprehensive fuzzing campaigns -- and DIAR helps you find such seeds.
- These are slides of the talk given at IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW 2022.
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfMalak Abu Hammad
Discover how MongoDB Atlas and vector search technology can revolutionize your application's search capabilities. This comprehensive presentation covers:
* What is Vector Search?
* Importance and benefits of vector search
* Practical use cases across various industries
* Step-by-step implementation guide
* Live demos with code snippets
* Enhancing LLM capabilities with vector search
* Best practices and optimization strategies
Perfect for developers, AI enthusiasts, and tech leaders. Learn how to leverage MongoDB Atlas to deliver highly relevant, context-aware search results, transforming your data retrieval process. Stay ahead in tech innovation and maximize the potential of your applications.
#MongoDB #VectorSearch #AI #SemanticSearch #TechInnovation #DataScience #LLM #MachineLearning #SearchTechnology
“An Outlook of the Ongoing and Future Relationship between Blockchain Technologies and Process-aware Information Systems.” Invited talk at the joint workshop on Blockchain for Information Systems (BC4IS) and Blockchain for Trusted Data Sharing (B4TDS), co-located with with the 36th International Conference on Advanced Information Systems Engineering (CAiSE), 3 June 2024, Limassol, Cyprus.
Monitoring and Managing Anomaly Detection on OpenShift.pdfTosin Akinosho
Monitoring and Managing Anomaly Detection on OpenShift
Overview
Dive into the world of anomaly detection on edge devices with our comprehensive hands-on tutorial. This SlideShare presentation will guide you through the entire process, from data collection and model training to edge deployment and real-time monitoring. Perfect for those looking to implement robust anomaly detection systems on resource-constrained IoT/edge devices.
Key Topics Covered
1. Introduction to Anomaly Detection
- Understand the fundamentals of anomaly detection and its importance in identifying unusual behavior or failures in systems.
2. Understanding Edge (IoT)
- Learn about edge computing and IoT, and how they enable real-time data processing and decision-making at the source.
3. What is ArgoCD?
- Discover ArgoCD, a declarative, GitOps continuous delivery tool for Kubernetes, and its role in deploying applications on edge devices.
4. Deployment Using ArgoCD for Edge Devices
- Step-by-step guide on deploying anomaly detection models on edge devices using ArgoCD.
5. Introduction to Apache Kafka and S3
- Explore Apache Kafka for real-time data streaming and Amazon S3 for scalable storage solutions.
6. Viewing Kafka Messages in the Data Lake
- Learn how to view and analyze Kafka messages stored in a data lake for better insights.
7. What is Prometheus?
- Get to know Prometheus, an open-source monitoring and alerting toolkit, and its application in monitoring edge devices.
8. Monitoring Application Metrics with Prometheus
- Detailed instructions on setting up Prometheus to monitor the performance and health of your anomaly detection system.
9. What is Camel K?
- Introduction to Camel K, a lightweight integration framework built on Apache Camel, designed for Kubernetes.
10. Configuring Camel K Integrations for Data Pipelines
- Learn how to configure Camel K for seamless data pipeline integrations in your anomaly detection workflow.
11. What is a Jupyter Notebook?
- Overview of Jupyter Notebooks, an open-source web application for creating and sharing documents with live code, equations, visualizations, and narrative text.
12. Jupyter Notebooks with Code Examples
- Hands-on examples and code snippets in Jupyter Notebooks to help you implement and test anomaly detection models.
Your One-Stop Shop for Python Success: Top 10 US Python Development Providersakankshawande
Simplify your search for a reliable Python development partner! This list presents the top 10 trusted US providers offering comprehensive Python development services, ensuring your project's success from conception to completion.
Ivanti’s Patch Tuesday breakdown goes beyond patching your applications and brings you the intelligence and guidance needed to prioritize where to focus your attention first. Catch early analysis on our Ivanti blog, then join industry expert Chris Goettl for the Patch Tuesday Webinar Event. There we’ll do a deep dive into each of the bulletins and give guidance on the risks associated with the newly-identified vulnerabilities.
1. IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE)
e-ISSN: 2278-1676,p-ISSN: 2320-3331, Volume 11, Issue 1 Ver. I (Jan – Feb. 2016), PP 41-53
www.iosrjournals.org
DOI: 10.9790/1676-11114153 www.iosrjournals.org 41 | Page
Artificial Neural Network based Fault Classifier and Locator for
Transmission Line Protection
Preeti Gupta1
, R. N. Mahanty2
1
(Electrical Engineering Department, National Institute of Technology, Jamshedpur, Jharkhand, 831016, India)
2
(Electrical Engineering Department, National Institute of Technology, Jamshedpur, Jharkhand, 831016, India)
Abstract: This paper presents a method for classification and location of transmission line faults based on
Artificial Neural Network (ANN). Although for fault classification prefault and postfault three phase currents
samples taken at one end of transmission line are used as ANN inputs, for location of faults post fault samples of
both current and voltages of three phases are required . 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 presented confirm the feasibility of the
proposed approach.
Keywords: Artificial Neural Network, Fault Classification, Fault Location, Transmission Line Protection.
I. Introduction
For providing the essential continuity of service from generating plants to end users power
transmission lines are vital links. Transmission line protection is therefore an important task for reliable power
system operation. The identification of the type of fault and the faulty phase/phases is known as fault
classification which is an important aspect of transmission line protection. The information provided by
classification of fault is necessary for locating the fault and assessing the extent of repair work to be carried out.
Various fault classification techniques have been developed by different researchers from time to time. Some of
the important fault classification and location techniques are: (1) wavelet transform based techniques [1]-[9] (2)
neural network based techniques [10]-[17] (3) fuzzy logic based techniques [18]-[20]. In this paper, an
alternative neural network based combined approach for classification and location of transmission line faults
has been proposed.
ANN is a mathematical model inspired by biological neural networks. A neural network is an adaptive
system changing its structure due to learning phase and responds to new events in the most appropriate manner
on the basis of experiences gained through training. The ability of ANNs to learn complex nonlinear
input/output relationships have motivated researchers to apply ANNs for solving nonlinear problems related to
various fields. ANNs have inherent advantages of excellent noise immunity and robustness and hence ANN
based approaches are less susceptible to changing operating conditions as compared to the conventional
approaches related to power system engineering. ANNs have been successfully applied to power system
protection. ANN applications to transmission line protection [12],[21]-[24] include detection,classification
[10],[11],[15]-[17],[21]-[23],[25]-[27] and precise location of faults [10],[13]-[17],[21]-[23],[25],[26]. Although
amongst the various available ANN based algorithms, back propagation (BP) training algorithm is the most
widely used one, it has some deficiencies including slow training and local minimum which make it unsuitable
for transmission line relaying [21]-[23],[25]. For such cases the radial basis function (RBF) based neural
network is well suited [10],[21]-[23],[25],[28],[29].
A RBF neural network based scheme for classification and location of transmission line faults is
presented in this paper. As many researchers [10],[21],[23],[27] have successfully carried out fault detection
using ANN approach, a priori knowledge of accurate fault detection has been taken for granted. The previous
researchers have generally used both current and voltage samples for fault classification. In the proposed
scheme three phase current samples (unfiltered) taken at one end of line are used for classification of faults.
However for locating the faults apart from current samples, voltage samples taken at one end of line are also
required. Large number of fault data has been generated by means of Electromagnetic Transient Program
(EMTP). Using the fault data generated through EMTP, simulation studies have been carried out by means of
MATLAB’s ‘Neural Network Toolbox’ [30] taking into account wide variations in fault resistance (RF), fault
inception angle (FIA), fault location () and load impedance (ZL) for different types of fault.
2. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 42 | Page
II. Power System Models
Figure 1: Model I: A faulted transmission line fed from one end Figure. 2: Model II: A faulted transmission line fed from
both ends
The two power system models: Model I and Model II, which have been considered for the development
of the fault classification and location algorithms are shown in Fig. 1 and Fig. 2 respectively [10].
As can be seen from the figures each model contains a faulted transmission line. In case of Model I, power is fed
to fault from one source, whereas in case of Model II, power is fed to fault from two sources. In each case the
fault is associated with a fault resistance and power is fed to fault and load simultaneously. The transmission
line parameters and other relevant data for Model-I and Model-II are given below:
2.1 Model I: Transmission line fed from one end
Line length = 100 km ,Source voltage (vS) = 400 kV,Positive sequence line parameters: R = 2.34 , L
= 95.10 mH, C = 1.24 F, Zero sequence line parameters: R = 38.85 , L = 325.08 mH, C = 0.845 F, Source
impedance (ZS): Positive sequence impedance = (0.45 + j5) per phase and Zero sequence impedance = 1.5
Positive sequence impedance, Load impedance (ZL) = 800 per phase with 0.8 p.f. lagging
2.2 Model II: Transmission line fed from both ends
The parameters of transmission line 1 are same as those considered for transmission line of Model I.
The load impedance variations are also same as in case of Model I. The parameters of transmission line 2 and
other parameters are: R2 =1.3 R1, L2 =1.3 L1, C2 =C1, where suffixes 1 and 2 refer to transmission line 1 and
transmission line 2 respectively, vS2 = 0.95 vS1, where vS1and vS2 are the voltages of source 1 and source 2,
(phase difference between vS1 and vS2 ) = 200
with vS1 leading , Source impedances: Positive sequence
impedance: ZS1 = (0.45 + j5) per phase, ZS2 = (0.34 + j4) per phase. Zero sequence impedance = 1.5
Positive sequence impedance, for both the sources.
III. The Proposed Fault Classifier
The proposed ANN based scheme for classification of faults is shown in Fig. 3. In the figure, F, D and
G represent the presence of fault, the fault direction and the involvement of ground in the fault. A, B and C are
the three phases. Simulation studies have been carried out to validate the proposed scheme on two power system
models: Model I and Model II, for various types of fault considering variations in operating conditions. Two
separate ANNs, one for ground faults and another for phase faults have been used. Hence, the prerequisite of the
proposed scheme is that the fault should be detected and also it should be known whether the fault involves
ground or not.
Figure 3: ANN based fault classifier
The various ANNs have been termed as:
ANN-1 / ANN-3: For classification of faults not involving ground in case of Model I / Model II,
ANN-2 / ANN-4: For classification of faults involving ground in case of Model I / Model II.
Source 1 Bus 1 Bus 2
Source 2
Tr. Line 1 Tr. Line 2
Fault
Load
Bus 3
Source
Load
Fault
Bus 1 Bus 2
Transmission Line
ANN for classification
of faults not involving
ground
ANN for classification
of faults involving
ground
A B C A B C
Output Output
Input
G≠ 0
Input
G=0
F=1
D=1
3. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 43 | Page
XX =
InInIn CBA
CBA
CBA
iii
iii
iii
...
...
222
111
Inputs
F(XX) = CBA Outputs
The input data, consisting of normalized absolute values of three pre-fault and four post-fault samples
of each of the three phase currents, iA, iB, iC are presented to each of the two ANNs used for fault classification,
in the form of multiple input vectors as shown above. This type of batching operation is more efficient than the
case when inputs are presented in the form of a single vector [30].
3.1. Generation of Training Data
An ANN based fault classifier should be trained with sufficient data for different fault situations. But as
the data encountered by an ANN based fault classifier is quite large, it is necessary to judiciously decide and
consider some representative fault situations and to train the network with data corresponding to these cases
such that the ANN gives correct output for all cases.Therefore, each of the ANNs has been trained with
different fault data. Fault data have been generated for fault at 5% of the line length from bus 1 of Model I and
Model II when the load impedance is 500 at 0.8 p. f. lagging. Training sets, for each of the two power system
models, have been generated through EMTP simulations for the load impedance as mentioned and by
varying fault resistance and fault inception angle. Fault resistances of 5, 50, 100 and 300 and fault
inception angles of 450
, 1350
and 2250
have been considered for training. It is important to select proper values
of spread and error goal in designing a RBF neural network.The spread should be smaller than the maximum
distance and larger than the minimum distance between the input vectors [29]. After a number of simulations
the spreads for the different ANNs have been selected, as indicated below.
ANN-1: Spread = 0.7 , ANN-2: Spread = 0.6 . ANN-3: Spread = 1.0 , ANN-4: Spread = 0.9
Error goal indicates how close the actual output is to the desired one. Lower the error goal, higher is the
accuracy and vice versa. After a number of simulation studies, it was decided to fix the error goal for all the
ANNs at 0.01. A comparison of the training times, number of epochs (iterations) required for the networks to
converge is shown in Table I. Based on this comparison, the ANNs with minimum number of hidden neurons
were selected for the proposed fault classifier. The selected values of spread, number of hidden neurons etc. for
each ANN are highlighted in Table I. The error convergences of the various ANNs during training have been
shown in Fig.4- Fig.7.
Table I: Rate of Convergence for various ANN’s relating to different RMS errors and spreads
Network RMS error Spread Number of
hidden neurons
Iterations
(epochs)
Time (sec)
ANN-1
0.001 0.7 66 66 18.16
0.01 0.6 45 45 9.907
0.01 0.7 44 44 9.461 selected
0.01 0.8 Computation incompatible
ANN-2
0.001 0.5 126 126 81.615
0.01 0.6 91 91 45.631 selected
0.01 0.7 Computation incompatible
0.01 0.8 98 98 52.43
ANN-3
0.001 1.0 75 75 21.77
0.01 0.8 51 51 12.41
0.01 0.9 50 50 12.15
0.01 1.0 50 50 11.91 selected
ANN-4
0.001 0.9 141 141 99.446
0.01 0.9 101 101 55.07 selected
4. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 44 | Page
0.01 1.0 Computation incompatible
0.01 1.1 103 103 56.51
After training, each ANN is tested for different types of faults considering wide variations in
operating conditions such as RF (fault resistance), FIA (fault inception angle), (fault location) and ZL( pre-fault
load). RF variation of 0-300, FIA variation of 0-3600
, variation of 0-90% of transmission line length and ZL
variation of 300-1200 in per phase load with power factor (lagging) variation of 0.7–0.9 have been considered.
Tables II and III contain the test results for various ANNs, which confirm the feasibility of the proposed ANN
based fault classification scheme.
Figure 4: Error convergence of ANN-1 in training.
Figure 5: Error convergence of ANN-2 in training.
0 20 40 60 80
10
-20
10
-15
10
-10
10
-5
10
0
10
5
Epoch
Sum-SquaredError
Error
0 10 20 30 40
10
-20
10
-15
10
-10
10
-5
10
0
10
5
Epoch
Sum-Squared Network Error for 44 Epochs
Sum-SquaredError
Error
Sum-Squared Network Error for 91 Epochs
6. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 46 | Page
Table III: Test Results for Model II.
Fault Type
Fault type
Fault Condition ANN Output
FIA
( 0
)
RF
()
ZL
()
A B C
Normal Condition - - - 80025.840
0.0013 -0.0258 0.432
B-G 0.1 60
110
200
70
40036.870
120045.570
0.0008
0.1408
0.9989
0.8667
-0.0022
0.1061
0.5 90
180
300
5
40036.870
30045.570
0.1012
-0.0008
0.8341
0.9538
0.0876
0.0898
C-A 0.5
30
180
100
5
80045.570
30045.570
1.0032
0.9986
-0.0032
-0.0003
1.0543
1.0112
0.9
75
360
20
70
30045.570
30025.840
1.0521
0.9990
1.0321
0.0021
0.0007
1.0013
B-C-G 0.1
0
110
0.01
70
80045.570
120045.570
0.0765
0.0765
1.0009
1.0563
1.0002
0.9956
0.9
250
60
200
70
120045.570
30025.840
0.0108
0.0028
0.7987
0.9597
0.7876
0.9876
A-B-C
0.1
60
340
200
50
40036.870
30036.870
0.9456
1.0075
1.1006
1.0021
0.9731
1.0398
0.5
30
180
100
5
80045.570
30045.570
1.0321
0.9989
0.9786
1.0043
0.8234
1.0532
IV. The Proposed Ann Based Fault Locator
The proposed ANN based fault locator is shown in Fig. 8. As shown in the figure, for each type of
fault, fault locator consists of two ANNs: ANN-I and ANN-II i.e. two ANNs for L-G fault, two ANNs for L-L
fault and so on. Similar to fault classification, for training of the ANNs, different values of spread are used to
find the first and second estimates of fault location. The significance of using two ANNs for each fault type is
explained in section 4.1. The inputs to the fault locator consist of samples of three phase voltages and currents.
The selection of appropriate ANN pair is made on the basis of the type of fault. Depending on the type of fault,
initially the estimate is made by ANN-I. Based on the value of this estimate, i.e. if this estimate falls below a
certain predetermined value, a second estimate is found out by ANN-II for the particular type of fault. However,
if the first estimate is equal to or greater than the predetermined value, there is no need to find the second
estimate.For the purpose of fault location only the post-fault samples have been found to be suitable.
Figure 8: The proposed ANN based fault locator
Seven post-fault samples of each of the three phase currents, voltages and zero sequence currents
(for faults involving ground only) taken at one end of line have been used as inputs to the proposed ANN
based fault locator. The sampling interval is considered as 1 ms. All these samples are normalized and presented
in the form of a single input vector. An output is obtained corresponding to the input vector in p.u. of the line
length up to the fault point. The input and output in case of line faults are shown below. In case of faults
involving ground, samples of zero sequence current are also considered, as already mentioned.Since the number
of output is only one in this case, it is not possible to present the input in the form of multiple vectors.
7. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 47 | Page
4.1 Generation of Training Data
A fault locator should be able to distinguish between faults occurring at, say, 80% and 85% of the line
which implies that number of training data required for a fault locator will be much more than that required for a
fault classifie, thus, large number of training data have been generated using EMTP, considering fault at 10%,
20%, 30%, 40%, 50%, 60%, 70%, 75%, 80%, 85% and 90% of the line. Fault inception angles of 00
-900
at
intervals of 180
and fault resistances of 0.5, 20, 75 and 150 have been considered. A per phase load
impedance variation of 400-1200 at 0.7-0.9 p. f. lagging has also been considered for the training case.
It has been observed that if two different values of spread are used, one for faults within about 50% of line and
another for faults beyond this range, fault location can be estimated more accurately. Therefore, two different
values of spread are used. By adopting this technique, a reduction in fault location error of up to 2-3% or more is
obtained, which is significant as far as fault location is concerned. As already mentioned, this strategy of
estimating fault location is implemented by using two ANNs: ANN-I and ANN-II for each type of fault, each of
the two ANNs being trained with a different value of spread. The selected values of spread for L-L and L-G
faults in case of Model I and Model II are shown in Table IV. These values of spread are determined after
extensive simulation studies. Table IV also indicates the number of neurons in the hidden layer, the number of
epochs (iterations) required for training and the training time of each ANN.
A comparison of results obtained with the two selected values of spread for some typical fault cases
corresponding to a load impedance of 40036.870
and variations in fault location (), fault resistance (RF)
and fault inception angle (FIA) are presented in Table V and Table VI. Similar results have been obtained for
other load impedance values. As can be seen from Table V, in case of Model I, for L-G faults at 15% of line,
results obtained with spread = 0.7 are more accurate than those obtained with spread = 1.3. From the same
table, it is clear that, for L-G faults at 82% of line for the same model, results obtained with spread =
1.3 are more accurate as compared to those obtained with spread = 0.7. Thus the use of two values of spread is
justified which is also clear from the results shown in Table VI.
For fault location, the accuracy required is more as compared to that required in fault classification. An
output of 0.8 or 0.9 means the same in case of a fault classifier as both indicate a faulty phase, whereas for a
fault locator an output of 0.8 means fault occurring at a distance of 80% of line and an output of 0.9 means fault
occurring at a distance of 90% of line. To ensure high accuracy in fault location an rms error goal of 0.001 has
been considered for all the ANNs of the fault locator.
Table IV: Spreads, number of hidden neurons and training times relating to ANNs of fault locator
Fault Type Network Spread Epochs Number of
hidden neurons
Training time
(min.)
Model-I
L-L
ANN-I 1.5 475 475 40.20
ANN-II 0.7 380 380 68.77
L-G
ANN-I 1.3 521 521 60.79
ANN-II 0.7 451 451 82.55
Model-II
L-L
ANN-I 1.5 422 422 43.91
ANN-II 1.0 391 391 52.89
L-G
ANN-I 0.9 471 471 46.33
ANN-II 1.4 409 409 66.27
Table V: Fault location estimates for different values of spread in case of Model- I
RF
()
FIA
(0
)
Network A-G fault A-B fault
Optimal
spread
e Optimal
spread
e
0.15
0.01
0
ANN-I 1.3 0.1698 1.5 0.1401
ANN-II 0.7 0.1647 0.7 0.1406
90
ANN-I 1.3 0.1593 1.5 0.1321
ANN-II 0.7 0.1432 0.7 0.1382
200
0
ANN-I 1.3 0.1682 1.5 0.1721
ANN-II 0.7 0.1654 0.7 0.1581
90
ANN-I 1.3 0.1323 1.5 0.1842
ANN-II 0.7 0.1498 0.7 0.1702
0.82
0.01
0
ANN-I 1.3 0.8320 1.5 0.8198
ANN-II 0.7 0.8480 0.7 0.8192
90
ANN-I 1.3 0.8197 1.5 0.8190
ANN-II 0.7 0.8012 0.7 0.7986
200 0 ANN-I 1.3 0.8176 1.5 0.8145
8. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 48 | Page
ANN-II 0.7 0.8164 0.7 0.7947
90
ANN-I 1.3 0.8157 1.5 0.8082
ANN-II 0.7 0.7732 0.7 0.7564
e= Estimated fault location as a fraction of total line length
Table VI: Fault location estimates for different values of spread in case of Model- II
RF
()
FIA
(0
)
Network
A-G fault A-B fault
Optimal
spread
e Optimal
spread
e
0.15
0.01
0
ANN-I 0.9 0.1386 1.5 0.1278
ANN-II 1.4 0.1488 1.0 0.1424
90
ANN-I 0.9 0.1485 1.5 0.1348
ANN-II 1.4 0.1505 1.0 0.1387
200
0
ANN-I 0.9 0.1410 1.5 0.1689
ANN-II 1.4 0.1487 1.0 0.1592
90
ANN-I 0.9 0.1378 1.5 0.1645
ANN-II 1.4 0.1465 1.0 0.1524
0.82
0.01
0
ANN-I 0.9 0.8187 1.5 0.8209
ANN-II 1.4 0.8098 1.0 0.8176
90
ANN-I 0.9 0.8094 1.5 0.8187
ANN-II 1.4 0.8654 1.0 0.8082
200
0
ANN-I 0.9 0.8156 1.5 0.8071
ANN-II 1.4 0.8187 1.0 0.7823
90
ANN-I 0.9 0.7824 1.5 0.7995
ANN-II 1.4 0.7654 1.0 0.7582
4.2. Training and Testing of the ANNs
The various ANNs have been trained with the training data as mentioned in section 4.1. The error goals
of all the ANNs were fixed at 0.001. The spreads of various ANNs for location of L-L and L-G faults and their
training times are as indicated in Table IV. As can be seen from the table, the training times are much higher as
compared to those in case of ANN based fault classifier. This is because of the large amount of training data that
are needed to train the ANNs of the fault locator. Fig. 9 - Fig. 12 show the error convergence of the various
ANNs during training.
Figure 9: Error convergence of ANN-I (Model I) for L-G faults in training
9. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 49 | Page
Figure 10: Error convergence of ANN-II (Model I) for L-G faults in training
Figure 11: Error convergence of ANN-I (Model II) for L-L faults in training
10. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 50 | Page
Figure 12: Error convergence of ANN-II (Model II) for L-L faults in training
After the training phase was over, each ANN was tested for different types of faults considering wide
variations in fault location (), fault resistance (RF), fault inception angle (FIA) and load impedance (ZL). Some
representative test results for the two most common types of fault viz. L-L and L-G faults are presented in Table
VII-Table X. Test results corresponding to two values of load impedance viz. 40036.870
and 120045.570
have only been shown. Similar results have been obtained for other loading conditions. The test results
confirm the feasibility of the proposed ANN based fault location scheme.
Table VII: Test Results for A-G Fault for Model-I
e = 15% e = 55% e = 82%
RF
()
ZL () =
40036.870
ZL ()=
120045.570
ZL () =
40036.870
ZL ()=
120045.570
ZL () =
40036.870
ZL () =
120045.570
FIA= 00
0.01 0.1621 0.1452 0.5055 0.5359 0.8489 0.8318
10 0.1308 0.1562 0.5713 0.5453 0.8221 0.8096
50 0.1790 0.1495 0.5588 0.5341 0.8157 0.7989
100 0.1719 0.1482 0.5518 0.5091 0.8120 0.8204
200 0.1796 0.1508 0.5590 0.5297 0.8192 0.8017
FIA=
450
0.01 0.1640 0.1354 0.5383 0.5289 0.8677 0.8267
10 0.1289 0.1543 0.5827 0.5608 0.8232 0.8301
50 0.1711 0.1396 0.5584 0.5503 0.8241 0.8174
100 0.1591 0.1443 0.5284 0.5235 0.8183 0.8199
200 0.1528 0.1459 0.5098 0.5385 0.8063 0.7985
FIA=
900
0.01 0.1411 0.1399 0.5373 0.5509 0.8185 0.8049
10 0.1573 0.1569 0.5327 0.5789 0.8184 0.8093
50 0.1429 0.1376 0.5211 0.4996 0.8138 0.8189
100 0.1484 0.1416 0.5188 0.5178 0.8204 0.8662
200 0.1428 0.1428 0.5186 0.5117 0.8096 0.7987
Table VIII: Test Results for A-B Fault for Model-I
e =15% e =55% e =82%
RF
()
ZL ()=
40036.870
ZL () =
120045.570
ZL ()=
40036.870
ZL () =
120045.570
ZL ()=
40036.870
ZL ()=
120045.5
70
FIA=
00
0.01 0.1401 0.1342 0.5502 0.5507 0.8187 0.8177
10 0.1687 0.1787 0.5720 0.5386 0.8145 0.8198
50 0.1487 0.1423 0.5397 0.5621 0.8013 0.7986
100 0.1504 0.1505 0.5321 0.5732 0.8098 0.7998
200 0.1634 0.1453 0.5643 0.5432 0.8176 0.7992
FIA=
450
0.01 0.1287 0.1376 0.5476 0.5394 0.8165 0.8095
10 0.1545 0.1665 0.5243 0.5238 0.8191 0.8207
50 0.1654 0.1765 0.5721 0.5654 0.8125 0.8197
100 0.1556 0.1785 0.5865 0.5865 0.8654 0.8564
200 0.1609 0.1321 0.5121 0.5138 0.7987 0.7897
FIA= 0.01 0.1298 0.1443 0.5464 0.5523 0.8194 0.8123
11. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 51 | Page
900
10 0.1476 0.1434 0.5518 0.5397 0.8189 0.8297
50 0.1512 0.1509 0.5502 0.5611 0.7976 0.8078
100 0.1445 0.1665 0.5598 0.5776 0.8321 0.8265
200 0.1687 0.1397 0.5521 0.5232 0.8187 0.7988
Table IX: Test Results for A-G Fault for Model-II
e =15% e =55% e =82%
RF
()
ZL ()=
40036.870
ZL ()=
120045.570
ZL ()=
40036.870
ZL ()=
120045.570
ZL ()=
40036.870
ZL ()=
120045.570
FIA= 00
0.01 0.1486 0.1352 0.5981 0.5489 0.8172 0.8226
10 0.1872 0.1623 0.5504 0.5487 0.8256 0.8118
50 0.1506 0.1456 0.5527 0.5397 0.8187 0.7982
100 0.1609 0.1481 0.5566 0.5362 0.8221 0.8118
200 0.1509 0.1497 0.5543 0.5398 0.8176 0.7918
FIA=
450
0.01 0.1263 0.1314 0.5871 0.5681 0.8171 0.8237
10 0.1365 0.1521 0.5874 0.5612 0.8564 0.8325
50 0.1567 0.1398 0.5980 0.5547 0.8121 0.8165
100 0.1441 0.1359 0.5987 0.5655 0.8182 0.7986
200 0.1411 0.1543 0.5547 0.5345 0.7979 0.7863
FIA=
900
0.01 0.1508 0.1432 0.5416 0.5521 0.7989 0.8157
10 0.1783 0.1621 0.6012 0.5944 0.8592 0.8182
50 0.1476 0.1346 0.5425 0.4998 0.8176 0.7976
100 0.1487 0.1383 0.5452 0.5199 0.8118 0.7869
200 0.1465 0.1291 0.5313 0.5545 0.7952 0.7998
Table X: Test Results for A-B Fault for Model-II
e =15% e =55% e =82%
RF
()
ZL () =
40036.870
ZL () =
120045.570
ZL ()=
40036.870
ZL () =
120045.570
ZL () =
40036.870
ZL () =
120045.570
FIA=
00
0.01 0.1393 0.1312 0.5472 0.5456 0.8197 0.8188
10 0.1500 0.1665 0.5500 0.5275 0.8167 0.8089
50 0.1676 0.1485 0.5122 0.5381 0.8011 0.7897
100 0.1286 0.1196 0.5149 0.5228 0.8013 0.7886
200 0.1556 0.1426 0.5287 0.5546 0.7976 0.7898
FIA=
450
0.01 0.1521 0.1408 0.5469 0.5408 0.8232 0.8180
10 0.1385 0.1698 0.5545 0.5326 0.8176 0.8372
50 0.1721 0.1843 0.5350 0.5625 0.8312 0.8193
100 0.1421 0.1657 0.5765 0.5213 0.8221 0.8514
200 0.1724 0.1603 0.5621 0.5233 0.8091 0.8300
FIA=
900
0.01 0.1298 0.1443 0.5454 0.5390 0.8165 0.8098
10 0.1576 0.1424 0.5549 0.5411 0.8207 0.8217
50 0.1243 0.1486 0.5089 0.5416 0.7986 0.7878
100 0.1311 0.1512 0.4976 0.5323 0.8097 0.8162
200 0.1512 0.1213 0.5502 0.5291 0.7987 0.7873
V. Comparison With Some Of The Existing Schemes
The salient features of some of the existing RBF neural network based fault classification and location
schemes and those of the proposed algorithms are described below. The proposed scheme has several
advantages: (a)For classification of faults range of fault resistance RF varies from 0-300 which is high as
compared to that proposed by Song et al.,[21]; Dash et al.[23]; Lin et al.[25] and Mahanty et al.[10] (b)Unlike
Song et al.[21] which require SCR firing angle[21], the proposed one requires only current samples as inputs for
fault classification and voltage and current samples as ANN inputs for fault location (c) filtering of the signals
not required (d)The range of FIA is similar to other schemes (e) Zero sequence currents which have been
considered by Mahanty et al.[10] has been ignored in the proposed scheme. As a result of this, the network size
and training time get reduced without affecting the accuracy for fault classification.For locating faults, although
network is complicated resulting in an increase in number of iterations, accuracy as compare to method
suggested by Mahanty et al.[10] is more.The error is reduced from 6-7% to 2-3%.
12. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 52 | Page
VI. Conclusions
A methodology for classification and location of transmission line faults based on RBF neural network
has been presented. The use of RBFNN has been found to be very effective as it can overcome the deficiencies
associated with BP algorithm. Whereas most of the previous researchers have generally used both voltage and
current samples, the proposed scheme is designed to work with only current samples as inputs for classifying
faults. Unfiltered samples of both currents and voltages of the three phases have been considered as inputs for
ANNs of the fault locator . Both pre-fault and post-fault samples of three phase currents are considered as inputs
in order to be able to distinguish between the current waveforms of healthy and faulty phases. Two separate
ANNs, one for LG & LLG faults and another one for LL & LLL faults in the proposed scheme have been used,
thus making the classification of faults easier. For fault location, two ANNs: one to locate faults occurring
within about 50% of the line and the other one to locate faults occurring beyond this range have been used. For
locating faults, two different values of spread are used for training of ANN’s so as to obtain accurate estimates
of fault location. The proposed scheme has been validated by considering wide variations in operating
conditions such as fault location, fault inception angle, fault resistance and load impedance. The simulation
results confirm the feasibility of the proposed scheme.
References
[1] R. N. Mahanty and P. B. Dutta Gupta, An Improved Method for digital relaying of 1Transmission Lines, Electric Power
Components And Systems 2004, 1013-1030.
[2] S. El. Safty, and A. El-Zonkoly, Applying wavelet entropy prZAZinciple in fault classification, International Journal of Electrical
Power & Energy Systems, 31(10), 2009, 604-607.
[3] Simi. P. Valsan, and K. S. Swarup, Wavelet transform based digital protection for transmission lines, International Journal of
Electrical Power & Energy System, 31(7–8), 2009,.379-388.
[4] J. Upendar, C. P. Gupta , and G. K. Singh, Statistical decision-tree based fault classification scheme for protection of power
transmission lines, International Journal of Electrical Power & Energy Systems, 36(1), 2012, 1-12.
[5] K Saravanababu, P. Balakrishnan, and K. Sathiyasekar, Transmission line faults detection, classification, and location using
Discrete Wavelet Transform, International Conference on Power, Energy and Control, (ICPEC), 2013, 233 – 238.
[6] M.A. Kalam, M.Jamil, and A.Q.Ansari, Wavelet based ANN approach for fault location on a transmission line, Proc. IEEE
Conference on Power Electronics Drives & Energy Systems (PEDES 2010 - Power India), 2010, 1 – 6.
[7] B. Ravindranath Reddy, M.V. Kumar, M. Suryakalavathi, and C. .Prasanth Babu, Fault detection, classification and location on
transmission lines using wavelet transform, IEEE Conference on Electrical Insulation and dielectric phenomena, 2009, 409 – 411.
[8] M. da Silva, M. Oleskovicz, and D.V. Coury, A hybrid fault locator for three-terminal lines based on wavelet transforms, Electric
Power Systems Research, 78(11), 2008, 1980-1988.
[9] A A. Yusuff, C Fei, A.A. Jimoh, and J.L. Munda, Fault location in a series compensated transmission line based on wavelet packet
decomposition and support vector regression, Electric Power Systems Research , 8(7), 2011, 1258-1265.
[10] R. N. Mahanty, and P. B. Dutta Gupta, Application of RBF neural network to fault classification and location in transmission
lines,” IEE Proc-Gener, Transm.,Distrib., 151(2), 2004, 201-211.
[11] E. Koley, A. Jain, A. S. Thoke, and S. Ghosh, Detection and classification of faults on six phase transmission line using ANN,
Proc. IEEE Conf. on Computer and Communication Technology, 2011, 100 – 103.
[12] C. D. S. Ricard,o and C. S. Eduardo, Transmission lines distance protection using artificial neural networks, International Journal of
Electrical Power & Energy Systems, 33(3), 2011, 721-730.
[13] K. Lout and R. K. Aggarwal, A feedforward Artificial Neural Network approach to fault classification and location on a 32kV
transmission line using current signals only, Universities Power Engineering Conference , 2012, 1-6.
[14] D. Thukaram, H. P. Khincha, and H. P. Vijaynarasimha, Artificial Neural Network and Support Vector Machine Approach for
Locating Faults in Radial Distribution System, IEEE Trans. Power Delivery, 20(2), 2005, 710-721.
[15] A.H. Osman, Tamer Abdelazim, and O. P. Malik, Transmission Line Distance Relaying Using On-Line Trained Neural Networks,
IEEE Trans. Power Delivery, 20(2), 2005, 1257-1264.
[16] E.B.M. Tayeb, and O.A.A.A Rhim, Transmission line faults detection, classification and location using artificial neural network,
Proc. IEEE Conf. on International Conference and
Utility Exhibition on Power and Energy Systems: Issues & Prospects for Asia (ICUE), 2011, 1 – 5.
[17] M.M. Ismail, and M.A.M. Hassan, Distance Relay Protection for short and Long Transmission line, Proceedings of International
Conference on Modelling Identification & Control (ICMIC), 2013, 204 – 211.
[18] Youssef and A. S. Omar, A novel fuzzy-logic-based phase selection technique for power system relaying, Electric Power Systems
Research, 68(3), 2004, 175-184.
[19] R. N. Mahanty, and P. B. Dutta Gupta, A fuzzy logic based fault classification approach using current samples only, Electric
Power Systems Research, 77(5-6), 2007, 501-507.
[20] S. R. Samantaray, A systematic fuzzy rule based approach for fault classification in transmission lines. Applied Soft Computing,
Elsevier Science, 13(2), 2013, 928-938.
[21] Y. H. Song, Q. Y. Xuan, and A. T. Johns, Protection scheme for EHV transmission systems with thyristor controlled series
compensation using radial basis function neural networks, Electric Machines and Power Systems, 25,1997, 553-565.
[22] K. G. Narendra, V. K. Sood, K.. Khorasani and R. Patel, Application of radial basis function neural network for fault diagnosis in a
HVDC system, IEEE Trans. Power Systems,,13(1), 1998, 177-183.
[23] P. K. Dash, A. K. Pradhan and G. Panda, Application of radial basis function neural network to distance protection, IEEE Trans.
Power Delivery, 16(1), 2001, 68-74.
[24] A. P. Vaidya, and P. A. Venikar, ANN based distance protection of long transmission lines by considering the effect of fault
resistance, P PROC. IEEE Conf. ON Advances in Engineering, Science and Management, 2012, 590 – 594.
[25] W. Lin, C. Yang, J. Lin, and M. Tsay, A fault classification method by RBF neural network with OLS learning procedure, IEEE
Trans. Power Delivery, 16(4), 2001, 473-477.
13. Artificial Neural Network based Fault Classifier and Locator for Transmission Line Protection
DOI: 10.9790/1676-11114153 www.iosrjournals.org 53 | Page
[26] J. Gracia, A. J. Mazón and I. Zamora, Best ANN Structures for Fault Location in Single and Double-Circuit Transmission Lines,
IEEE Trans. Power Delivery, 20(4), 2005, 2389-2395.
[27] E. A. Mohamed, H. A. Talaat, and E. .A. Khamis, Fault diagnosis system for tapped power transmission lines, Electric Power
Systems Research , 80(5), 2009, 599-613.
[28] M. Joorabian, S. M. A. Taleghani, and R. K. Aggarwal, Accurate fault locator for EHV transmission lines based on radial basis
function neural networks, Electric Power Systems Research, 71(3), 2004, 195-202.
[29] Preeti Gupta and R.N.Mahanty, An Alternative Approach for Location of Transmission Line Faults based on Artificial Neural
Network, IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE, 9(4 ) Ver. III , 2014, 6-15.
[30] H. Demuth and M. Beale, Neural Network Toolbox for use with Matlab. The Mathworks, Inc., USA.,1996