Study on power transformers fault diagnosis based on Fuzzy Kernel C-Means Clustering and Dempster-Shafer theory fusion method

摘要

Because of the compactness characteristics of oil-immersed transformer fault, a model of oil-immersed transformer fault diagnosis is based on the collaborative method of Fuzzy Kernel C-Means Clustering (FKCM) and multi-source information data fusion. The basic idea is that the trained samples are clustered first by using FKCM, then a Dempster-Shafer(D-S) evidential theory Fusion method is used to train the chose samples, the simulation result shows that the above method can effectively diagnose the transformer fault condition. Two kinds of data fusion methods are given in this paper, which are compared in the transformer fault diagnosis.