An artificial neural network based directional discriminator for protecting transmission lines

This paper describes a directional discriminator that uses an artificial neural network (ANN) for protecting transmission lines. The proposed discriminator uses various attributes to reach a decision and tends to emulate the conventional pattern classification problem. An equation of the boundary describing such a classification is embedded in the multilayer feedforward neural network (MFNN) by training through the use of an appropriate learning algorithm and suitable training data. The discriminator uses instantaneous values of voltage and current signals to reach a decision. Simulation results showing the performance of the ANN-based discriminator are presented