Fast and accurate fault classification is essential to power system operations. In this paper, in order to classify electrical faults in radial distribution systems, a particle swarm optimization (PSO) based support vector machine (SVM) classifier has been proposed. The proposed PSO based SVM classifier is able to select appropriate input features and optimize SVM parameters to increase classification accuracy. Further, a time-domain reflectometry (TDR) method with a pseudorandom binary sequence (PRBS) stimulus has been used to generate a dataset for purposes of classification. The proposed technique has been tested on a typical radial distribution network to identify ten different types of faults considering 12 given input features generated by using Simulink software and MATLAB Toolbox. The success rate of the SVM classifier is over 97%, which demonstrates the effectiveness and high efficiency of the developed method.
Distribution networks deliver electrical energy from transmission systems to consumers and are important and integral part of all power systems. Once an electrical fault occurs in any distribution feeder, immediate fault classification plays an important role in postfault analysis and power supply restoration. The accuracy of the fault type information assists the fault diagnosis system not only to locate the electrical faults promptly but also to ensure power quality as well as reliability of the system [
A variety of approaches have been developed to build an effective fault classifier in electrical distribution feeders. As the amount of power delivered by a distribution system significantly increases, it is essential to focus on fault classification schemes. The studies of fault classification in distribution feeder can be divided into three separate categories, as follows: (
TDR is rather simple to implement; however, it is not a perfect fault-location method since any single pulse stimulus injected into the electrical line is quickly attenuated along that line, causing fault location and classification to become inaccurate. To overcome this problem, an improved TDR method using incident pseudorandom binary sequence (PRBS) excitation is proposed to locate such faults in [
To build a SVM classifier, the aspect of feature subset selection plays an important role in detecting relevant variables in classification spaces. Principal component analysis (PCA) [
In addition to feature subset selection, the optimal set of SVM parameters also plays an important role in the distribution of samples in a given search space. Vapnik showed that the penalty parameter
In this paper, a novel method based upon PSO techniques is developed to simultaneously optimize input features and SVM parameters in order to classify the fault types found in the distribution network. These fault types can be divided into ten classes, including single phase-to-ground faults (AG, BG, and CG), line-to-line faults (AB, AC, and BC), double line-to-ground faults (ABG, ACG, and BCG), and three-phase short-circuit faults (ABC). Further, this PSO-SVM classifier uses a dataset obtained from TDR analysis with PRBS excitation. Not only is the proposed PSO based encoding technique easy to use, but it also helps to significantly increase the success rate of the SVM classifier.
The remainder of this paper is constructed as follows. In Section
Time-domain reflectometry (TDR) is widely used for fault classification and location of faults in electrical transmission and distribution lines. TDR is based on a single pulse being injected into the given line or cable to be examined. Afterwards, some of the pulse energy is reflected back to source whenever it reaches the point of any discontinuities, such as electrical faults, tee joints, or line terminals. Since the propagation velocity is assumed to be constant, the fault distance can be measured based on the expected pulse transit time. Hence, the reflectometry trace will not only display the desired information of the fault type, but also determine the fault location.
Assume a distribution line is modeled by a lumped-parameter equivalent circuit as shown in Figure
The classical model for a lumped section.
A voltage introduced at the generator will require a certain amount of time to propagate along the line represented in the following equation:
From (
TDR is quite simple to implement, but it is not a perfect technique since the use of single pulse excitation that is quickly attenuated along the line. In addition, the pulse width is one of the factors that affect the accuracy rate of the reflectometry method. TDR method, using incident pseudorandom binary sequence (PRBS) excitation can solve these problems by using cross-correlation (CCR) function between the reflected wave and incident wave given by (
As previously mentioned, a variety of different components exist along electrical distribution lines like transformers, capacitors, tap changers, phase splitters, and so forth so it is not easy to extract fault locations from various reflections observed in the reflectometry trace. In this study, a multilayer SVM classifier is proposed as a supporting technique for the TDR method to provide fault diagnosis in multibranch distribution networks, including single phase-to-ground faults (AG, BG, and CG), line-to-line faults (AB, AC, and BC), double line-to-ground faults (ABG, ACG, and BCG), and three-phase faults (ABC).
A support vector machine (SVM) was first mentioned by Vapnik in 1995, and it has become one of the most optimal techniques for data classification. It has a solid theoretical foundation based on a combination between the structural risk minimization principle and statistical machine learning theory (SLR). The main advantages of SVM are the global optimization and high generalization ability. Further, it overcomes overfitting problems and provides sparse solutions in comparison to existing methods such as artificial neuron network (ANN) and refined genetic algorithm (RGA) in fault classification.
In standard linear classification problem, for example, one should separate the set of training data,
It is to be noted that the nonlinear classifier may be denoted in the input space as
To obtain optimum performance, some SVM parameters need to be select property, including the regularization parameter
Particle swarm optimization (PSO) is inspired by the social and cooperative behavior displayed by various species to fill their needs in the search space. This algorithm is guided by personal experience
The initial population (swarm) of size
In (
The PSO search mechanism
The initial
At iteration
An equivalent model has to be constructed by using Simulink software and MATLAB Toolbox to simulate a typical two-branched distribution feeder shown in Figure
A two-branched distribution line diagram of the sample system.
Two distribution transformers in the sample system are used to reduce the voltage on the distribution line to the level of customers that are distributed along a feeder. Their parameters and connection phases are shown in Table
Parameters and connection phases of distribution transformers in the sample system.
Number | Windings connection | Phases | Secondary voltages (V) | Capacity (kVA) | Impedance ( |
---|---|---|---|---|---|
1 | Delta-Wye-Gnd. | A, B, C | 220 | 500 | 1.89 |
2 | Delta-Delta | A, B, C | 220 | 500 | 1.89 |
Since the TDR technique does not diagnose fault easily in the distribution networks hence it requires to be supported from other intelligent techniques in order to obtain the best results. This paper proposes a PSO based SVM classifier to improve the performance of the TDR method in fault classification in electrical distribution feeders. The overall structure of SVM short-circuit classifier is shown in Figure
Block diagram of the proposed PSO based SVM classifier.
To obtain a suitable dataset for classification process, PRBS disturbance is injected directly into the secondary circuit of the current transformer (CT) 200/5A which is placed at the beginning of the line under test. The primary circuit of the CT is connected to the main feeder; thus the amplified PRBS is propagated along the line to diagnose any faults which may occur.
Once a fault occurs in the distribution feeder, it causes producing a reflected signal that travels between the fault location and the substation. Then, these reflected responses are cross-correlated with the incident impulse by (
For utilization of the reflectometry method, various echo responses are collected, in which some irrelevant data may be confusing to the SVM classifier and subsequently increase the training time. Feature extraction is the best effective method to select appropriate input features in order to improve the speed of training as well as to ensure the success rate of classification. For optimum feature selection in this work, PSO is employed to improve the performance of the SVM classifier. To select optimum features of the given dataset, a binary string has been optimized using PSO where each bit represents a given feature of the dataset. In the binary string, a “0” represents an ignored feature, whereas a “1” represents a selected feature of the dataset. The optimum features are those features taken from the given dataset which correspond to the optimized binary string having its bit as a “1.” For this, a given set of predefined SVM parameters has been used while the selection of features of the given dataset using PSO is made. At the end of feature selection stage, the selected strings provide the information regarding the features needed for optimizing the SVM parameters.
The performance of SVM is susceptible to kernel function parameter
Once the optimized parameters of the SVM are obtained, then it is used for the retraining of the SVM model. After the training phase, the SVM classifier is ready to identify new samples in the testing phase. The testing set is also chosen by means of the above feature selection from the original dataset obtained by the TDR trace. Then, testing patterns are inputted to the trained multilayer SVM classifier which can identify all the 10 types of faults, including single-phase-to-ground faults (AG, BG, and CG), line-to-line faults (AB, AC, and BC), double-line-to-ground faults (ABG, ACG, and BCG), and three-phase faults (ABC).
Detailed experiment procedure for feature extraction and SVM parameter selection using PSO algorithm can be expressed using the following steps: Read complete data and set Initialize positions Initialize sets of SVM parameters within its ranges as particle position and velocity. Form SVM using training dataset and initialized positions of each particle. Evaluate fitness of each particle Select Set iteration count Update velocity and position of each particle using ( Evaluate updated fitness of each particle Update If Update If If Optimum solution obtained: print the results of optimum generation as Retrain SVM with optimum features and parameters; then identify unknown samples on testing dataset.
The experiment procedure can be visualized in Figure
Flowchart of the proposed approach.
In this paper, the fault types are considered by using a 127-bit PRBS stimulus with frequency
Dataset of ten fault types located at distances of 3 km and 4 km from the substation.
|
|
|
|
|
|
cc- |
cc- |
cc- |
cc- |
cc- |
cc- |
|
---|---|---|---|---|---|---|---|---|---|---|---|---|
AG | 1.9197 | −0.3071 | 0.1245 | 4.9815 | −0.7968 | 0.3232 | 0.5941 | −0.0950 | 0.0385 | 0.0502 | −0.0080 | 0.0033 |
0.6990 | −0.1118 | 0.0453 | 1.5998 | −0.2559 | 0.1038 | 3.5687 | −0.5708 | 0.2315 | 3.0765 | −0.4921 | 0.1996 | |
BG | 1.4521 | 0.7277 | 0.5122 | 3.7681 | 1.8884 | 1.3290 | 0.4494 | 0.2252 | 0.1585 | 0.0380 | 0.0190 | 0.0134 |
0.5287 | 0.2650 | 0.1865 | 1.2101 | 0.6064 | 0.4268 | 2.6995 | 1.3528 | 0.9521 | 2.3271 | 1.1662 | 0.8208 | |
CG | 0.4648 | 4.5783 | 3.1718 | 0.0857 | 0.8445 | 0.5851 | 0.0275 | 0.2711 | 0.1878 | 0.0237 | 0.2331 | 0.1615 |
0.0880 | 0.8668 | 0.6005 | 0.2284 | 2.2492 | 1.5582 | 0.0272 | 0.2683 | 0.1858 | 0.0023 | 0.0227 | 0.0157 | |
BCG | −8.2016 | 9.6684 | 16.2648 | −2.5267 | 2.9785 | 5.0107 | −0.1137 | 0.1340 | 0.2254 | −0.1137 | 0.1340 | 0.2254 |
−4.1309 | 4.8697 | 8.1921 | −0.7620 | 0.8983 | 1.5112 | −0.2446 | 0.2884 | 0.4852 | −0.2104 | 0.2480 | 0.4172 | |
ACG | −1.2835 | 2.5576 | 4.8025 | −0.9796 | 1.9519 | 3.6650 | −1.6907 | 3.3688 | 6.3257 | −1.4240 | 2.8375 | 5.3279 |
−1.4241 | 1.7834 | 3.8278 | −1.0868 | 1.3610 | 2.9212 | −1.8757 | 2.3491 | 5.0419 | −1.5799 | 1.9786 | 4.2466 | |
ABG | −1.1327 | 0.0679 | 2.6912 | −2.9393 | 0.1763 | 6.9832 | −0.3506 | 0.0210 | 0.8329 | −0.0296 | 0.0018 | 0.0704 |
−2.0970 | 0.1258 | 4.9821 | −1.6003 | 0.0960 | 3.8021 | −2.7621 | 0.1657 | 6.5623 | −2.3265 | 0.1395 | 5.5272 | |
AB | −7.4589 | −4.8688 | 17.7206 | −1.3759 | −0.8981 | 3.2688 | −0.4417 | −0.2883 | 1.0495 | −0.3798 | −0.2479 | 0.9024 |
−1.4121 | −0.9218 | 3.3549 | −3.6643 | −2.3918 | 8.7055 | −0.4370 | −0.2853 | 1.0383 | −0.0369 | −0.0241 | 0.0877 | |
AC | −1.0143 | −1.2113 | 7.8915 | −0.7741 | −0.9244 | 6.0225 | −1.3360 | −1.5955 | 10.3945 | −1.1253 | −1.3439 | 8.7550 |
−1.5121 | −7.9329 | 40.5259 | −0.4658 | −2.4439 | 12.4847 | −0.0210 | −0.1099 | 0.5616 | −0.0210 | −0.1099 | 0.5616 | |
BC | 2.0444 | −4.2356 | 23.5915 | 0.3771 | −0.7813 | 4.3518 | 0.1211 | −0.2508 | 1.3972 | 0.1041 | −0.2157 | 1.2013 |
0.1409 | −0.2920 | 1.6262 | 0.3225 | −0.6682 | 3.7220 | 0.7195 | −1.4907 | 8.3028 | 0.6203 | −1.2851 | 7.1576 | |
ABC | 0.3508 | −0.3674 | 1.9940 | 0.8029 | −0.8408 | 4.5638 | 1.7911 | −1.8757 | 10.1807 | 1.5440 | −1.6170 | 8.7765 |
1.7837 | −1.8679 | 10.1386 | 1.3612 | −1.4255 | 7.7374 | 2.3494 | −2.4604 | 13.3543 | 1.9788 | −2.0723 | 11.2480 |
AG, BG, and CG are single phase-to-ground faults; BCG, ACG, and ABG are double line-to-ground faults; AB, AC, and BC are line-to-line faults; ABC is three-phase faults;
In this paper, PSO technique is used to select the features and parameters of the SVM classifier. Preliminary experiments also permit this study set population size as 10; inertia weight has been taken into account as between 0.1 and 0.5 (considered randomly at each iteration); and acceleration factors (
Table
Results of SVM classification without and with considering PSO optimization techniques.
SVM classifier | Number of features |
|
|
Classification accuracy (%) | Training time (s) |
---|---|---|---|---|---|
Without PSO | 12 | 181.0193 | 1.1212 | 93.00 | 134.8 |
With PSO | 8 | 15.0381 | 0.0334 | 97.15 | 83.54 |
The convergence characteristic of the proposed PSO is shown in Figure
Convergence characteristic of the proposed PSO.
In this paper, a multilayer support vector machine (SVM) based on optimum parameters optimization and feature selection approach has been developed to classify ten types of faults in radial distribution feeders. Particle swarm optimization (PSO) has been used as an optimizer to improve the performance of SVM classifier by selecting an appropriate feature subset and kernel parameters. Further, time-domain reflectometry (TDR) with pseudorandom binary sequence (PRBS) stimulus has been utilized for generating a fault dataset. In the proposed technique, not only does using PRBS injection overcome the stimulus distortion problem, but it also surmounts the impact of noise to provide a reliable dataset for SVM classifier. The proposed PSO based SVM classifier has been successfully applied to identify all ten types of short-circuit faults in the radial distribution network observed. The achieved high accuracy rate in classifying fault types (over 97%) demonstrates greater effectiveness over existing fault identifiers.
The authors declare that they have no conflicts of interest.