Fuzzy Logic Expert System for Incipient Fault Diagnosis of Power Transformers

Condition monitoring of power transformers improves the security and reliability of an electrical power system. It protects the transformers from failures, and avoids huge revenue loss to utilities and customers. The fault diagnosis of transformers is carried out by concentrations of several dissolved gasses. An accurate fault diagnosis of transformers has been a critical problem for diagnostic experts of transformers. In this article, a novel fuzzy logic model has been proposed to determine the transformer incipient faults. It incorporates the information obtained from dissolved gas analysis test. Further, the proposed model also incorporates conventional fault diagnosis methods viz. Duval Triangle, Doernenburg, Rogers, and IEC ratio code methods. The proposed fuzzy logic models short out the problems occur in the conventional fault diagnosis methods of transformers.