High-impedance fault detection using multi-resolution signal decomposition and adaptive neural fuzzy inference system

High-impedance faults (HIFs) on distribution systems create unique challenges to protection engineers. HIFs do not produce enough fault current to be detected by conventional overcurrent relays or fuses. A method for HIF detection based on the nonlinear behaviour of current waveforms is presented. Using this method, HIFs can be distinguished successfully from other similar waveforms such as nonlinear load currents, secondary current of saturated current transformers and inrush currents. A wavelet multi-resolution signal decomposition method is used for feature extraction. Extracted features are fed to an adaptive neural fuzzy inference system (ANFIS) for identification and classification. The effect of choice of mother wavelet is also analysed by investigating a large number of wavelet families. Various simulation results, which are obtained using an appropriate model, are summarised and efficiency of the proposed algorithm for dependable and secure HIF detection is determined.

[1]  David C. Yu,et al.  An adaptive high and low impedance fault detection method , 1994 .

[2]  A. T. Johns,et al.  A Novel Fault Detection Techique of High Impedance Arcing Faults in Transmission Lines Using the Wavelet Transform , 2002, IEEE Power Engineering Review.

[3]  B. D. Russell,et al.  Practical High Impedance Fault Detection for Distribution Feeders , 1996, Proceedings of Rural Electric Power Conference.

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

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

[6]  John A. Orr,et al.  High impedance fault arcing on sandy soil in 15 kV distribution feeders: contributions to the evaluation of the low frequency spectrum , 1990 .

[7]  Alexander Mamishev,et al.  Analysis of high impedance faults using fractal techniques , 1995 .

[8]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

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

[10]  Michio Sugeno,et al.  Industrial Applications of Fuzzy Control , 1985 .

[11]  Soon-Ryul Nam,et al.  A modeling method of a high impedance fault in a distribution system using two series time-varying resistances in EMTP , 2001, 2001 Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.01CH37262).

[12]  O.P. Malik,et al.  High impedance fault detection based on wavelet transform and statistical pattern recognition , 2005, IEEE Transactions on Power Delivery.

[13]  D. Sutanto,et al.  High-impedance fault detection using discrete wavelet transform and frequency range and RMS conversion , 2005, IEEE Transactions on Power Delivery.

[14]  Giuseppe Baselli,et al.  An adaptive neuro-fuzzy method (ANFIS) for estimating single-trial movement-related potentials , 2004, Biological Cybernetics.

[15]  Adly A. Girgis,et al.  Analysis of high-impedance fault generated signals using a Kalman filtering approach , 1990 .

[16]  Mark W. White,et al.  A neural network approach to the detection of incipient faults on power distribution feeders , 1990 .

[17]  Dongfeng Wang,et al.  Control of boiler-turbine unit based on adaptive neuro-fuzzy inference system , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).