A fuzzy expert system for fault diagnosis in electric distribution systems

This paper builds on work toward the simplification of fault diagnosis within electric distribution systems using a fuzzy expert system. Based on the symptom description derived from customers, the developed system draws on the past experience of distribution systems from historical trouble tickets to determine the membership-grade, which indicates the degree to which specific components might be faulty on a prioritized basis. Thus a priority list of suspicious components is the result, if a trouble ticket is given. To demonstrate its effectiveness, the proposed system is implemented in C++ language and applied to practical data which includes 3067 trouble tickets. It is found that the fuzzy expert system can emulate system operators and provide substantial assistance in decision-making with respect to fault diagnosis of distribution systems.<
>