Design and Evaluation a Distance Relay Model Based On Artificial Neural Networks (ANN)

Delivering high-quality electrical power requires an efficient, reliable protective system that can handle failures on transmission lines, which occur due to varies random causes. Detecting, classifying, and locating faults can prevent further damage to electrical supply equipment. The digital technology has brought unquestionable improvements in numerical relay design in terms of criteria signals estimation in a short time, better filtering, self-monitoring features, etc. However, it did not make a breakthrough in power system protection, as far as security, dependability, and speed of operation are concerned. The relaying task, however, can be approached as a pattern recognition problem. To improve the performance of protection, Artificial Neural Networks (ANN) approach has been perceived by researchers in power system protection field. By monitoring the relaying inputs, the relay can be trained using ANN to classify the ongoing signals between faults and all other conditions. Therefore, this paper presents an intelligent method to design an online Simulink model of a distance relay. The Artificial Neural Network ANN, three-layer, Feed-forward networks with backpropagation algorithm for each phase (voltage and current) were selected to achieve this design. The designed relay is composed of fault detection and fault type algorithm block, fault classification algorithm block, and fault location algorithm block, as well as the best network structure for each of the previous blocks, which have been determined. Moreover, the relay was evaluated under approximately all various fault types and different fault locations. The Simulation results show that the ANN method is effective in detecting faults on transmission lines.