Artificial neural network based fault diagnostic system for electric power distribution feeders

This paper describes the development of a fast, efficient, artificial neural network (ANN) based fault diagnostic system (FDS) for distribution feeders. The principal functions of this diagnostic system are: (i) detection of fault occurrence, (ii) identification of faulted sections, and (iii) classification of faults into types, e.g. HIFs (high impedance faults) or LIFs (low impedance faults). This has been achieved through a cascaded, multilayer ANN structure using the back-propagation (BP) learning algorithm. This paper shows that the FDS accurately identifies HIFs, which are relatively difficult to identify with other methods. Test results are generated using the Manitoba Hydro 24 kV distribution feeder. These results amply demonstrate the capacibility of the FDS in terms of accuracy and speed with respect to detection, localization, and classification of distribution feeder faults.