Power transformer fault diagnosis based on chaos immune evolutionary clustering algorithm

This paper researches the advantages and shortcomings of Fuzzy C-Means (FCM) algorithm which applied to transformer fault diagnosis firstly, then combine the FCM algorithm with the chaos immune evolutionary algorithm to propose a new method of transformer fault diagnosis - chaos immune evolutionary clustering algorithm. Theoretical analysis and simulation results show that the algorithm not only effectively overcome the traditional FCM clustering algorithm falling into local minimum of the shortcomings, but also effectively suppress the immune evolution process produced the "degradation" phenomenon.