High Impedance Fault detection in radial distribution system using S-Transform and neural network

Abstract

This paper presents a novel S-transform based approach to detect High impedance fault in distribution line. Conventional Distance relays , over current relays and ground fault relays are difficult to apply for High Impedance Fault (HIF) detection in distribution line because of sensitivity, diversity, selectivity issue in case of low value of fault current. As S-Transform (ST) is a very useful tool to analyzing transient fault signal which also provide both time and frequency information unlike Fourier transform, same has been consider for High impedance fault detection. The Features extracted using S-Transform are used to train and test the Artificial Neural Network (ANN) to discriminate the HIF with other transient phenomenon (Load switching, capacitor Switching) and also normal fault and no fault condition. The proposed scheme are fully analyzed with different operating condition by extensive MATLAB simulation studies that clearly revels that the proposed method can detect High impedance Faults in high voltage distribution line with high accuracy)