Ann Based Fault Detection, Classification and Distance Location

Quick detection of fault, classification and fault distance location are desirable features of any protective relaying scheme. Protection of double circuit transmission lines experiences problems due to zero sequence mutual coupling between faulted and healthy circuits. It is affected by network changes such as switching in/out of one of the parallel lines, thus causing under reach/over reach of conventional distance relaying. This book analyses two different approaches based on single and modular artificial neural networks for fault detection/classification and distance location. The proposed method uses the voltages and currents signals available at the local end of line. Effects of variations in power system parameters e.g. fault inception angle, CT saturation, source strengths, fault resistance, type, fault location including the effects of network changes: double circuit and single circuit operation have been investigated extensively on the performance of the neural network based protection scheme.The results of single and modular neural networks indicate that the modular approach detects/classify the faults correctly and estimates the fault distance with more accuracy.