An Application of DWT and RBFNN for Fault Location for Single Line to Ground Fault on Hvac Transmission Line

This article demonstrates a technique for diagnosis of fault location on overhead transmission lines for single line to ground fault. The proposed method is based on discrete wavelet transform (DWT) and radial basis function neural network (RBFNN). A number of features have been extracted from faulty signal using DWT and are used for training of RBFNN for fault detection. It has been found that fault locator based on discrete wavelet transform and RBFNN neural network can accurately locate the fault with an average accuracy 2.31%. From the result it can be concluded that the proposed method for fault location estimation for a single line to ground fault (LG fault) is capable of giving results with acceptable accuracy.