Transformer fault diagnosis based on improved evidence theory and neural network integrated method

Considering the diversity of the transformer fault types and fault information uncertainty, the paper proposes the fault diagnosis method based on the combination of evidence theory and neural network. 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. Simulation results show that the method can still get better compliance determination result when the results of the initial diagnostic module is seriously divided, so it achieves effective transformer fault diagnosis.