Faults classification in series compensated lines based on wavelet entropy and neural network

Abstract

A precise and advanced approach based on combined wavelet transform and artificial intelligence technique for analysis of the type fault and the faulty phase in a series compensated transmission line is presented in this paper. In proposed algorithm, samples of fault current signals are used for fault diagnosis and wavelets transform (WT) applied for feature extraction from the signals. The faulty current signals are decomposed using Db5 mother wavelet. Features of faulty signals are extracted in terms of norm entropy value of the wavelet coefficients. Those extracted features have been fed to PNN (Probabilistic neural network) for classification of faults category. The accuracy and practicability of the proposed algorithm has been assessed on a 400 KV, 300 km series compensated network for all types of faults using MATLAB simulation. The results acquired, suggested that the proposed approach is creditable and have good accuracy in classifying the faults in compensated transmission network. © 2016 IEEE.