Combined EKF and SVM based High Impedance Fault detection in power distribution feeders

The paper presents an intelligent technique for High Impedance Fault (HIF) detection using combined Extended Kalman Filter and Support Vector Machine. The proposed approach uses magnitude and phase change of fundamental, 3<sup>rd</sup>, 5<sup>th</sup>, 7<sup>th</sup>, 11<sup>th</sup> and 13<sup>th</sup> harmonic component as feature inputs to the SVM. The Gaussian kernel based SVM is trained with input sets each consists of ‘12’ features with corresponding target vector ‘1’ for HIF detection and ‘−1’ for non-HIF condition. The magnitude and phase change are estimated using Extended Kalman Filter. The proposed approach is trained with 300 data sets and tested for 200 data sets including wide variations in operating conditions and provides excellent results in noisy environment. Thus the proposed method is found to be fast, accurate and robust for HIF detection in distribution feeders.

[1]  Samy Bengio,et al.  SVMTorch: Support Vector Machines for Large-Scale Regression Problems , 2001, J. Mach. Learn. Res..

[2]  A.M. Sharaf,et al.  Novel alpha-transform distance relaying scheme , 1996, Proceedings of 1996 Canadian Conference on Electrical and Computer Engineering.

[3]  B. Don Russell,et al.  Detection of Distribution High Impedance Faults Using Burst Noise Signals near 60 HZ , 1987, IEEE Transactions on Power Delivery.

[4]  A. F. Sultan,et al.  Detecting arcing downed-wires using fault current flicker and half-cycle asymmetry , 1994 .

[5]  B. D. Russell,et al.  Behaviour of low frequency spectra during arcing fault and switching events , 1988 .

[6]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[7]  Gavin C. Cawley,et al.  Fast exact leave-one-out cross-validation of sparse least-squares support vector machines , 2004, Neural Networks.

[8]  S. Osowski,et al.  Accurate fault location in the power transmission line using support vector machine approach , 2004, IEEE Transactions on Power Systems.

[9]  S.M. Rovnyak,et al.  Decision tree-based methodology for high impedance fault detection , 2004, IEEE Transactions on Power Delivery.

[10]  Christopher J. C. Burges,et al.  Geometry and invariance in kernel based methods , 1999 .

[11]  Q. S. Yang,et al.  Microprocessor-based algorithm for high-resistance earth-fault distance protection , 1985 .

[12]  Fábio Gonçalves Jota,et al.  Fuzzy detection of high impedance faults in radial distribution feeders , 1999 .

[13]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[14]  B. D. Russell,et al.  A digital signal processing algorithm for detecting arcing faults on power distribution feeders , 1989 .

[15]  Hong-Tzer Yang,et al.  A de-noising scheme for enhancing wavelet-based power quality monitoring system , 2001 .

[16]  Olivier Chapelle,et al.  Model Selection for Support Vector Machines , 1999, NIPS.

[17]  Jesper Salomon,et al.  Support Vector Machines for Phoneme Classification , 2001 .

[18]  G. Swift,et al.  Detection of high impedance arcing faults using a multi-layer perceptron , 1992 .

[19]  Dana Ron,et al.  Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-Validation , 1997, Neural Computation.

[20]  Matti Lehtonen,et al.  Characteristics of earth faults in electrical distribution networks with high impedance earthing , 1998 .

[21]  Dana Ron,et al.  Algorithmic Stability and Sanity-Check Bounds for Leave-one-Out Cross-Validation , 1997, COLT.

[22]  Om P. Malik,et al.  Soft computing applications in high impedance fault detection in distribution systems , 2005 .