A Fault Diagnosis System for Tapped Transmission Lines

Abstract

This paper presents an artificial neural network (ANN) based fault diagnosis system (FDS) for tapped power transmission lines. The proposed system is designed to detect the fault, localize the faulted zone, classify the fault type and finally identify the faulted phase. The FDS consists of three hierarchical levels. In the first level, a preprocessing to input data is performed. An ANN, in the second level, is designed to detect the fault and localize the faulted zone. In the third level, two zone diagnosis systems (ZDS) are designed. Each ZDS is dedicated to one zone and consists of four-parallel ANN's in order to achieve the fault type classification. Each one of the paralleled ANN’s, except the last one, is cascaded with another ANN designed mainly for the selection of the faulted phase.