Fuzzy logic application in DGA methods to classify type of faults in oil transformer / Nur Afiqah Romai Nor

Assessment of power transformer conditions is increasing concern in latest years. Failure of transformer can cause high installation cost and utility will lost. Dissolved gas-in-oil analysis (DGA) is successful technique and provided wealth of diagnosis information to detect incipient faults in oil transformer. The fault gases that considered for evaluation are hydrogen, methane, ethane, ethylene and acetylene. There are various methods developed to . do the inspection of the fault type from the DGA data but only two methods are used in this study which is Roger's Ratio and IEC Ratio. However, there are situations of errors and misleading results occurring due to borderline and multiple faults. This is because the relation between different gases become too complete and cannot match with the actual fault. In order to solve the problem, this study proposes Fuzzy Logic to efficiently classify fault type in oil transformer based on its higher reliability and precision of fault diagnostics. Fuzzy Logic engine is developed using MATLAB to evaluate each DGA method.