Integration of neural network and distance relay to improve the fault localization on transmission lines

Abstract

Power transmission lines are integral and very important components of power systems. Because of the length of these lines and the complexity of the power grids, the lines may encounter various incidents such as lightning strike, shortage, and breakage. When an incident or a fault occurs, a fast process of identification, localization, and isolation of the fault is desired. An accurate fault localization would have a great impact in reducing the restoration time of the system. One of the most popular solutions for fault detection and localization is the distance relays using the impedance-based algorithms. However, these relays are still not perfect with nonzero errors of the fault locations. This paper will present a new approach using the neural networks in addition to a distance relays to correct the fault location estimation of the relay. The solution will be based only on the voltage and current signals measured at the beginning of the lines. The training samples’ signals of the transient states on the lines are generated using ATP/EMTP, and then regenerated into the relay tester Omicron CMC-356 to test with the real Siemens 7SA522 relay to improve its fault location results. The numerical results will show that the solution had helped to reduce the average fault location error from 0.92% to 0.42% for 4 types of shortage faults on the lines.