High impedance fault detection in distribution networks using support vector machines based on wavelet transform

Abstract

In this paper a new pattern recognition based algorithm is presented to detect high impedance fault (HIF) in distribution networks. In this method, using wavelet transform (WT), the time-frequency based features of the current waveform up to 6.25 kHz are calculated. To extract the best feature set of the generated time frequency features, two methods including principle component analysis (PCA) and linear discriminant analysis (LDA) are used and then support vector machines (SVM) is used as a classifier to distinguish the HIFs considering with and without broken conductor from other similar phenomena such as capacitor banks switching, no load transformer switching, load switching and harmonic loads considering induction motors, arc furnaces. The results show high accuracy of the proposed method in the detection task.