IDENTIFICATION OF TYPE OF FAULTS IN A DISTRIBUTION SYSTEM

Abstract

In this thesis, an artificial neural network based algorithm to identify the type of faults in radial, unbalanced distribution system has been developed. The proposed technique has been proven to accurately identify all eleven types of shunt faults that may occur in an electric power distribution system under different fault types, fault resistance, inception angle and loading levels. All the test results show that the proposed fault identifier is very well suited for identifying fault types in radial, unbalanced distribution system.