Fault Diagnosis Based on Fault Tree and Bayesian Network for Pure Electric Trucks

Aiming at the problem of insufficient experience in maintenance of pure electric trucks, this paper presents a fault diagnosis method based on the Bayesian network which has been improved by subjective Bayesian method. Firstly, the causal relationship between failure and symptom was considered to the establishment of Bayesian network. Then the probability of the corresponding fault symptom was determined by the probability scale, and the confidence coefficient of the corresponding fault was obtained by Bayesian network inference. Finally, this paper presents a diagnostic decision-making method, which can be used for data mining through diagnostic records and be the auxiliary decision of the diagnosis result and can be used to assist in decision making.