Detection high impedance fault in distribution feeder using wavelet transform and artificial neural networks

Abstract

This work presents a novel analysis method that can simulate the potential effect of high impedance fault (HIF). The proposed method offers a new scheme for protecting the overhead distribution feeder. The wavelet transform (WT) method was successfully applied in many fields. The characteristics of scaling and translation of WT can be used to identify stable and transient signals. Discrete wavelet transforms (DWT) are initially used to extract distinctive features of the voltage and current signals, and are transformed into a series of detailed and approximated wavelet components. The coefficients of variation of the wavelet components are then calculated. This information is introduced into the training artificial neural networks (ANN) to determine an HIF from the operations of the switches. The simulated results clearly reveal that the proposed method can accurately identify the HIF in the distribution feeder.