Detection of High Impedance Faults in Distribution System

This investigation seeks to present a new method of identifying high impedance faults (HIFs) in the distribution feeder. Discrete wavelet transformations (DWT) and neural networks (NN) have been widely used in power system research. Consequently, this work developed a novel method to distinguish effectively the HIFs by integrating DWT with NN. The proposed scheme has two distinct features. First, the input signal of this algorithm is neutral line current, rather than the traditional currents based on three individual phases. Second, HIFs identification applies the details at levels 2, 3 and 4 and the approximations at level 4 of the neutral line current are employed for. The results of staged fault clearly indicate that the proposed can accurately find the HIFs in the distribution feeder.