Transmission Line Fault Classification and Location Using Wavelet Entropy and Neural Network

Abstract The ability to locate the faults as well as to identify the type of fault in overhead transmission lines is of prime importance for the economic operation of modern power systems. An expert system based on an artificial neural network for fault classification and distance estimation is proposed in this article. The power system network has been simulated using EMTP/ATP software, and signal analysis has been performed in MATLAB environment (The MathWorks, Natick, Massachusetts, USA). Various types of faults have been simulated at different locations along the transmission line. The faulty voltage signals have been analyzed through wavelet transform using the Db4 mother wavelet. The entropies of the wavelet decompositions have been fed to the neural networks for classification and fault distance evaluation. The suggested technique is proven to be successful for classification and location of the faults.