Research of transformer fault diagnosis based on Bayesian network classifiers

In power systems, the power transformer is seen to be the core equipment, so the fault diagnosis has been subject to the academic and engineering concern. It is very important to find incipient faults as early as possible. Due to the randomness and uncertainty of power transformer fault diagnosis data, Bayesian network satisfactory capacity of knowledge representation and strong solving ability to deal with uncertain facts, represent knowledge flexibility and it has strong advantage of dealing with uncertainty and associated problems, in this paper transformer fault diagnosis method based on Bayesian network classifiers is proposed. In the paper, a variety of Bayesian classifiers have been studied separately, and the corresponding models have been established, then their advantages and disadvantages have been described. The experimental results show that the methods improve the accuracy of the transformer fault diagnosis.