Application of genetic algorithm in artificial neural network for fault classification in parallel transmission lines

A new scheme to enhance the solution of the problems associated with parallel transmission line protection is presented in this paper. This paper demonstrates a novel application of wavelet transform to identify faults in parallel transmission lines. The discrimination scheme which can automatically recognize the type of fault is proposed using GA-ANN. The scheme can be separated into two stages, the time-frequency analysis of transients by wavelet transform and the pattern recognition to identify the type of fault. By using the actual fault data, it is shown that the proposed method provides satisfactory results for identifying the faults. Recently there have been significant research efforts to apply evolutionary computational techniques for determining the neural network weights. Genetic algorithm has been used for finding weights to avoid training of ANN. Test results are matched well with values predicted by ANN and GA-ANN for identifying faults in 33 km line sample system.