High-speed transmission line relaying using artificial neural networks

A novel feedforward neural network that indicates whether a fault is within or outside the protection zone (fault indicator) of a transmission line is presented. The same technique has been extended to locate the distance of the fault (fault locator). The proposed scheme utilizes the frequency spectrum of the voltages and currents to make a decision. Data obtained from the electromagnetic transient program for single-line-to-ground faults and three-phase faults have been tested and the results are found to be accurate. Using this neural network the relaying decision is obtained within a cycle after the fault inception. The performance of the trained neural network shows promise and has the potential for implementation in a digital relay for transmission line protection. (C) 2000 Elsevier Science S.A. All rights reserved.