The combination of discrete wavelet transform and self organizing map for identification of fault location on transmission line

In the literature for fault location, Artificial neural networks (ANNs) have been reported. At the present time, unsupervised learning is not well understood. This paper proposes a new algorithm for identifying fault location on transmission lines, using Discrete Wavelet Transform (DWT) and Self-organizing maps (SOMs). The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from these signals. The coefficients of scalel obtained using the DWT are used for training and test processes of the SOMs. After the training process, case studies are varied. The result shows that the average accuracy obtained from combination of DWT and SOMs is satisfactory.