Signal processing technique based fault location of a distribution line

Hybrid signal processing technique is discussed in this paper to sense the fault in a 11 kV, 30 km distribution line with R-L load placed at the receiving end. The proposed method uses 1 cycle post fault voltage and current signal wave form sending end of the system under study. Further preprocessing of the collected signal is done by wavelet packet transform and discrete wavelet transform which includes decomposition of the signal and feature extraction. Thereafter from the total feature set, redundant features are removed and best features are selected by genetic algorithm based feature selection method to get better accuracy and reduce computational difficulty. To simulate the model accurately, sampling frequency taken is 30 kHz. Train and test data set are generated by considering various operating conditions which are made entirely different in order to make the suggested method insensitive to parameter variations. Artificial neural network /Support vector machine is used for prediction purpose. Then optimal features are fed to artificial neural network/ support vector machine to detect the fault location. It was observed from the simulation outcomes that the suggested method is quite accurate and fast as compared to schemes investigated by other researchers.