Transformer Fault Diagnosis Based on Information Fusion Technology

Transformer faults have many types and fault information is uncertain, in response to these problems, this paper presents evidence theory and neural network integrated fault diagnosis. In order to realize the reasonable assignment of reliability by Dempster combination rule after the information fusion between strong conflict evidence, the concept of a trust coefficient is introduced to correct fusion results and is used in the synthesis of max-min ant system and neural network algorithm which form the body of evidence. The experimental simulation results show that the method can still get better compliance determination conclusions when the results of the initial diagnostic module is seriously differences, and can achieve effective transformer fault diagnosis. Copyright © 2014 IFSA Publishing, S. L.