The use of multilayer perceptron to classify and locate power transmission line faults

Abstract

This paper investigates the use of multilayer perceptron (MLP) technique for locating and detecting faults in a power transmission line. MLP was used twice in this paper to locate and to detect faults. The experiments were conducted on a 600-km-length, three-phase power transmission line data which include the required faults to detect and locate the fault. Matlab was used to perform the experiments. Results show that MLP achieved high prediction accuracy for fault type detection of 98% and a prediction accuracy of 78% for fault location.