Fault detection and classification method using DWT and SVM in a power distribution network

Abstract

This paper presents a technique of fault feature extraction, detection and classification of short circuit faults in a power distribution network. A reduced 88 kV power distribution network is modelled in Digsilent Power Factory. Transient fault current signals of various types of faults are then subsequently obtained through an Electromagnetic Transient (EMT) study on the model. A Discrete Wavelet Transform (DWT) is used to extract features from transient fault currents measured at the source terminal of the network. The extracted features are subsequently fed into a Support Vector Machine (SVM) in order to detect and classify various types of faults. The method uses the first two cycles of the transient fault current measured at the source terminal after the fault inception. A hybrid technique using DWT and SVM is thus proposed. The feasibility of the proposed technique is tested using Matlab. The results of the proposed fault feature extraction, detection and classification technique showed that various types of faults in a power distribution network can be detected and classified accurately.