An expert system for transformer fault diagnosis using dissolved gas analysis

A prototype of an expert system based on the dissolved gas analysis (DGA) technique for diagnosis of a suspected transformer faults and their maintenance actions is developed. The synthetic method is proposed to assist the popular gas ratio method. Moreover, the uncertainty of key gas analysis, norms threshold and gas ratio boundaries are managed by using a fuzzy set concept. Incorporation of the norms method, the gas ratio method, the synthetic method, a data base of Taiwan Power Company’s (TPC) transformer gas records, and TPC’s expertise for diagnosis and maintenance increases the performance capability and reduces the operational limitations. This expert system is implemented into PC-AT by using KES with rule-based knowledge representation. The designed expert system has been tested for TPC's transformers gas records to show its effectiveness in transformer diagnosis.