Application Research on Bayesian Network and D-S Evidence Theory in Motor Fault Diagnosis

Aiming at the inherent uncertain problems in motor fault diagnosis, in this paper we propose a new kind of motor fault diagnosis method, which utilize the parallel Bayesian network and D-S evidence theory based on multi-source information fusion technique. Firstly, the set of motor fault features is divided into multiple fault sub-spaces and each fault sub-space uses different parallel Bayesian network for local diagnostics. Then taking the result of local diagnostic based on the sub Bayesian network as the independent evidence body, and utilizing the D-S evidence theory for the decision level fusion. Through the simulation analysis, we proved that the method can effectively improve the accuracy of motor fault diagnosis and reduce the uncertainty of diagnosis results.