Diagnosis of Power Transformer Faults using Fuzzy Logic Techniques Based on IEC Ratio Method

Abstract

Power transformers' failures are often catastrophic and almost always cause irreversible internal damage. To optimize maintenance schedules, various condition monitoring techniques of power transformers have been developed in attempt to reduce operating costs, enhance the reliability of operation, improve power supply and service to customers. DGA is a reliable and very sensitive technique to identify the incipient faults in power transformers. To overcome these limitations, this thesis introduces a new fuzzy logic approach to reduce dependency on expert personnel and to aid in standardizing DGA interpretation techniques. The results indicated that the accuracy of predictions of the FL technique were 95% based on IEC ratio methods.