Power transformer fault diagnosis based on variable precision rough set

A transformer is one of the most important units in the power networks. Thus a breakdown of a transformer faults can cause costly repairs. In this paper, a new transformer fault diagnosis method based on variable precision rough set is presented. The proposed method transforms the continuous attribute values into the fuzzy values by automatically deriving membership functions from a set of data with similarity clustering. With the concepts of fuzzy similarity relation and fuzzy similarity classes, beta-positive region, beta-negative region and beta-boundary region of rough-fuzzy approximation space are given. Also, a fuzzy rough set learning algorithm is given for inducing rules from quantitative data. The application to fault diagnosis of transformer shows the proposed algorithm can find more objective and effective diagnostic rules from the quantitative data and is a good method in application of fault diagnosis.