Dynamic Fatigue Reliability Prediction Approach of Fuel Cell Vehicle Based on Usage Scenario

Fuel cell vehicles (FCVs) are an important direction for sustainable development of the automobile industry in the future. Still, the reliability and durability of FCVs are key technical problems affecting marketization. This study focused on fatigue reliability of FCVs under complex driving conditions. A dynamic analysis approach for fatigue reliability is proposed based on a dynamic Bayesian network and fracture mechanics (DBN-FM). According to the load spectrum data collected by an FCV on typical roads, a DBN model for the fatigue reliability of an FCV was established considering the randomness of variables in crack propagation. The practical application of the developed model is demonstrated through a case study. The results show that the DBN-FM approach can be used to predict the failure probability of FCVs under different driving distances. In addition, the weak parts of the FCV were identified, which provided theoretical guidance for its inspection and maintenance.