Applying pattern recognition in distance protection

This paper demonstrates the use of artificial neural networks (ANNs) as a pattern classifier for power system distance relay operation. The implemented neural network should capture the knowledge for the correct relay operation facing different network conditions. The approach utilizes the magnitudes of the three phase voltage and current phasors (including the zero sequence) as inputs. Alternative Transient Program (ATP) software is used to generate data for the transmission line in a faulted condition both for the training process and the tests. An improvement concerning the use of ANNs for protection purposes was found.