A fuzzy logic tool for transformer fault diagnosis

Abstract

Transformers have complicated winding structures and are subject to electrical, thermal and mechanical stresses. During the last few years, there has been a trend of continuous increase of transformer failures. It is therefore vital to correctly diagnose their incipient faults for safety and reliability of an electrical network. Various faults could occur in a transformer such as overheating, partial discharge and arcing, which can generate various fault-related gases. From dissolved gas analysis, the faults may be determined. The conventional interpretation methods such as IEC codes cannot determine the fault in many cases, especially if there is more than one type of fault existing in a transformer. This paper presents a fuzzy logic tool that can be used to diagnose multiple faults in a transformer and monitor the trend. It has been proved to be a very useful tool for transformer diagnosis and maintenance planning.