An expert system for transformer fault diagnosis using dissolved gas analysis

A prototype expert system based on the dissolved gas analysis (DGA) technique for diagnosis of suspected transformer faults and their maintenance actions is developed. A synthetic method is proposed to assist the gas ratio method. The uncertainties of key gas analysis, norms threshold, and gas ratio boundaries, are managed by using a fuzzy set concept. The expert system is implemented on a PC-AT using KES with rule-based knowledge representation. The system has been tested to show its effectiveness in transformer diagnosis.<
>