Comprehensive Faults Classification Method for Unbalanced Power Distribution Systems

Abstract

Unbalanced power distribution systems experience single faults and compound faults types. The classification of these faults is considered as one of the most important requirements for the fault analysis and the fault location techniques. However, existing methods for fault classification have been formulated to consider only single-fault types. This paper presents a comprehensive faults classification method for unbalanced power distribution systems. In this method, new fault classification indices are derived to consider all fault types including the compound-fault ones. The values of these indices are determined based on the transient analysis of the current signals using discrete wavelet transform (DWT). These indices are utilized in conjunction with adaptive neural-fuzzy inference systems (ANFIS) to classify all fault types. In order to verify the accuracy of the proposed method, a practical distribution system is used to test the method under different fault conditions.