An artificial neural network for directional comparison relaying of transmission lines

The design and testing of an artificial neural network for the directional comparison protection of power transmission lines are presented in this paper. Training patterns were generated using voltage and current samples for faults at various locations along a transmission line. The faults were simulated using an electromagnetic transient program and a sample three-phase power system. The performance of the proposed discriminator was checked using data simulated for testing and the fault data recorded from 240 kV and 500 kV lines. Some of the test results are also included