Research On Safety And Reliability Of High-speed Train Running Gear Based On Belief Rule Base

For ensuring the safety and reliability of high-speed trains,fault diagnosis(FD)and health status assessment techniques play an important role.Benefiting from the rapid developments of artificial intelligence,research on the reliability and safety of equipments has obtained much attention in the field of academics and applications,where belief rule base(BRB)is an advanced intelligent method.BRB-based models can effectively combine measurement data and qualitative knowledge to complete the equipment safety and reliability tasks.Even in the case of a small number of abnormal-state samples,BRB can still obtain high-precision results with the help of knowledge.On the other hand,BRB-based methods make the model interpretable due to consider domain knowledge.This paper has developed two types of schemes to ensure the safe of running gear systems from both FD and assessment aspects.We will address three topics:(1)This chapter proposes a fault diagnosis method based on BRB with mixed reliability(BRB-mr).Different from the traditional BRB,this method considers two kinds of interference factors that affect the observation data in engineering practice,including the performance of sensors and the influence of external environment,and we quantify them as static reliability and dynamic reliability of attributes in BRB.In order to integrate two kinds of reliability factors into the reasoning of BRB,a discount method is developed based on Dempster-Shafer theory(D-S theory),which is helpful for more accurate diagnosis.In this chapter,the effectiveness of the method is verified by a single fault of running gear systems,and the numerical simulation verifies its feasibility in multi-fault diagnosis.Then the model is compared with traditional methods.The result shows BRB-mr model has stronger diagnostic ability to identify faults and it has a certain reference value to be extended to other complex system FD tasks.(2)This chapter proposes a health status assessment method based on the standard BRB for high-speed train running gear systems.First,a failure mechanism is analyzed to confirm the fault characteristics,which can represent the status of the system.Second,to avoid the limitations of a single sensor acquisition,such as a lack of comprehensiveness and robustness,singular value decomposition is used to achieve multisensory information fusion.The fused features are used as the input to the BRB model.Data fusion is a way to improve the precision in the model input.Then,this BRB model is established using the fault data and expert knowledge.During the assessment procedure,the subjectivity of experts makes the initial BRB imprecise,so a projection constrained covariance matrix adaptive evolution strategy algorithm is needed to optimize the initial parameters and improve the accuracy of the proposed model.Finally,a case study for running gear systems is carried out to verify the effectiveness and accuracy of the proposed model.The results show that the proposed model can help to provide the accurate results.(3)Based on the standard BRB assessment method in(2),this chapter proposes the multi-discounted BRB(MBRB)for health status assessment of running gear systems.The system characteristics like its complexity of structures and failure mechanisms result in the difficulty to evaluate its health status with certainty.In general,three factors contribute to the uncertainty in assessment procedures: monitoring uncertainty,environmental uncertainty,and cognitive uncertainty.In the proposed approach,the above three-source uncertainties are characterized simultaneously,and the use of evidence discount theory can incorporate the effect of three-source uncertainties into health status assessment.Compared with the standard BRB method,an alternative approach,the so-called MBRB,significantly enhances the evaluated performance.The presented MBRB scheme is finally applied to running gear systems in high speed trains,and its results verify the effectiveness of the proposed method.