Fault diagnosis model for power transformer based on Bayesian network

Power transformer is very important in power system. In this paper, according to complementary strategy, a new transformer fault diagnosis method based on rough sets theory (RST) and Bayesian network (BN) is present. Through reduction approach of RST information table to simplify expert knowledge and to reduce fault symptoms, the minimal diagnostic rules can be mined. According to the minimal rules, complexity of BN structure and difficulties of fault symptom acquisition are largely decreased. At the same time, probability reasoning can be realized by BN, which can be used to describe changes of fault symptoms and analyze fault reasons of transformer. Finally, the correctness and effectiveness of this method are validated by the result of practical fault diagnosis examples.