A computational intelligence approach for fault location in transmission lines

The main objective of this paper is to accurately estimate the fault location in a transmission line. Accurate estimation of transmission line fault location will lead to quicker restoration of the supply. At the relay location, the instantaneous values of faulty current, voltage and power signals are available. The available signals are decomposed using 13-level Discrete Wavelet Transform (DWT). From the decomposed signals, the statistical features are obtained. Using forward feature selection algorithm, the best feature set is selected. These features are then applied to an artificial feed forward neural network (FNN) for estimating the fault distance. The proposed fault locator has been trained for different fault scenarios (fault resistance and phase difference) and tested with both integer and non-integer distance values. The test results demonstrate that the adopted technique is a reliable method for estimating fault locations accurately on transmission lines.