Continuous wavelet transform and artificial neural network based fault diagnosis in 52 bus hybrid distributed generation system

An Artificial Neural Network (ANN) based approach is carried out for power system unsymmetrical fault classification and localization using Continuous Wavelet Transform (CWT) in Hybrid Distributed Generation (HDG) System. In this study, CWT is used as a signal processing tool to extract features of HDG System current signals captured from distribution substation. The extracted features are applied to ANN for fault classification and localization. The simulation results shows a superiority of proposed time frequency domain analysis with CWT which provides a robust and accurate method for detecting and localizing different types of unsymmetrical fault as all faults are correctly classified in this process and the average error in localization is nearly 10.09m.