Design and Training of Artificial Neural Networks for Locating Low Current Faults in Distribution Systems

Abstract

Artificial Neural Networks constitute a suitable approach for pointing out a fault location in radial distribution feeders, even when the fault current has a small value, near the normal load of the system. Some publications have described successful application of artificial neural networks to the fault location problem, but there are still some difficulties that may limit their applicability to a real system, mainly the complexity of the problem when lateral derivations are included as possible fault locations. There are some inherent aspects in distribution networks that prevent the straightforward application of transmission network methodologies to distribution systems. This paper describes a new approach to the use of Artificial Neural Networks for the solution of the fault location problem in energy distribution systems. The objective is to obtain accurate results and to optimize the training stage, all using only the fundamental frequency component of the currents monitored at the substation.