Wavelet Transform and Support Vector Machine Approach for Fault Location in Power Transmission Line

� Abstract—This paper presents a wavelet transform and Support Vector Machine (SVM) based algorithm for estimating fault location on transmission lines. The Discrete wavelet transform (DWT) is used for data pre-processing and this data are used for training and testing SVM. Five types of mother wavelet are used for signal processing to identify a suitable wavelet family that is more appropriate for use in estimating fault location. The results demonstrated the ability of SVM to generalize the situation from the provided patterns and to accurately estimate the location of faults with varying fault resistance. CCURATE fault location on power transmission line is important for both protection and maintenance purposes. Conventional fault location methods use the fault steady state components of voltage and current measured at one or more points along the transmission line. The fault distance can be estimated from the measured impedance of the transmission line at the power system frequency. The impedance is assumed to be proportional to the fault distance. The impedance measurement used in distance protection schemes is too inaccurate for precise fault location as the error in the estimated fault location can be as high as 10% of line length. Fault location based on reactance is a well known technique that has been used to improve the estimation of fault location (1)-(3). The technique is based on linear relation between the reactance, estimated from the voltage and current of the fault, and the fault location. In most cases, the error in estimating the fault location using these techniques varies between 1% to 6%. The use of travelling waves to detect and locate faults on such line is another feasible alternatives (4)-(5). The schemes are all based on determining the time needed for a wave to travel between the local end and the fault location. However, travelling wave schemes have problems with faults close to the bus and faults with close-to-zero incidence angle. Algorithms based only on local terminal current and voltage data need some simplifying hypothesis to allow the fault distance

[1]  L.C. Zanetta,et al.  Fault location in transmission lines using one-terminal postfault voltage data , 2004, IEEE Transactions on Power Delivery.

[2]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[3]  Bernhard Schölkopf,et al.  Kernel Methods and Support Vector Machines , 2003 .

[4]  Jean Claude Maun,et al.  Artificial neural network approach to single-ended fault locator for transmission lines , 1997 .

[5]  M. S. Sachdev,et al.  A technique for estimating transmission line fault locations from digital impedance relay measurements , 1988 .

[6]  Michel Meunier,et al.  Prony's method: an efficient tool for the analysis of earth fault currents in Petersen-coil-protected networks , 1995 .

[7]  P. G. McLaren,et al.  Travelling wave distance protection-problem areas and solutions , 1988 .

[8]  Tahar Bouthiba,et al.  Fault location in EHV transmission lines using artificial neural networks , 2004 .

[9]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[10]  M. M. Morcos,et al.  ANN-based techniques for estimating fault location on transmission lines using Prony method , 2001 .

[11]  H. P. Khincha,et al.  Intelligent Approach for Fault Diagnosis in Power Transmission Systems Using Support Vector Machines , 2007 .

[12]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[13]  Adly A. Girgis,et al.  Fault location techniques for radial and loop transmission systems using digital fault recorded data , 1992 .

[14]  M. T. Schilling,et al.  Fault location in electrical power systems using intelligent systems techniques , 2001 .

[15]  G. Ancell,et al.  Maximum likelihood estimation of fault location on transmission lines using travelling waves , 1994 .

[16]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[17]  Ali Abur,et al.  Fault location using wavelets , 1998 .

[18]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[19]  Ganapati Panda,et al.  Application of minimal radial basis function neural network to distance protection , 2001 .

[20]  T. Takagi,et al.  Development of a New Type Fault Locator Using the One-Terminal Voltage and Current Data , 1982, IEEE Power Engineering Review.

[21]  Milenko B. Djurić,et al.  Distance protection and fault location utilizing only phase current phasors , 1998 .