Fuzzy approaches for fault diagnosis of transformers

Dissolved gas analysis has been used as a diagnostic method to determine the conditions of transformers for a long time. The criteria used in dissolved gas analysis are based on crisp value norms. Due to the dichotomous nature of crisp criteria, transformers with similar gas-in-oil conditions may lead to very different conclusions of diagnosis especially when the gas concentrations are around the crisp norms. To deal with this problem, gas-in-oil data of failed transformers were collected and treated in order to obtain the membership functions of fault patterns using a fuzzy clustering method. All crisp norms are fuzzified to linguistic variables and diagnostic rules are transformed into fuzzy rules. A fuzzy system originally proposed by Takagi and Sugeno is used to combine the rules and the fuzzy conditions of transformers to obtain the final diagnostic results. It is shown that the diagnosing results from the combination of several simple fuzzy approaches are much better than traditional methods especially for transformers which have gas-in-oil conditions around the crisp norms.