An accurate fault locator for cable transmission using ANN

This paper presents a new neural network-based transmission cable fault locator module. Different faults on a protected cable should be located correctly. The proposed module uses samples of voltage and current signals to learn the hidden relationship existing in the input patterns. The scheme is insensitive to fault type, fault resistance, fault inception angle and system source configuration. Details of the design procedure and the results of performance studies with the proposed fault locator are given in the paper. Performance studies results show that the proposed algorithm is accurate.