Resilience evaluation of train control on-board system considering component failure correlations: Based on Apriori-Multi Layer-Copula Bayesian Network model

The failure of complex system components is an important factor affecting system resilience, and it is not only affected by their own basic life parameters, but may also be affected by the failure of other components. In order to investigate the impact of component failure correlations on the resilience evaluation of Train Control on Board System (TCOBS), we propose the Apriori-Multi Layer-Copula Bayesian Network (AMLCBN) model. Firstly, the definition and evaluation function of TCOBS component resilience are provided. Then, build a TCOBS Bayesian Network and perform hierarchical processing on the network to clarify the position of Copula functions in the Bayesian Network. The Copula function is used to evaluate the correlations among component failures, and the Copula Bayesian Network is used to infer TCOBS resilience. We use Apriori to calculate the correlation coefficient matrix in the Copula function. Finally, a case study is conducted by taking CTCS-3OBS as an example, the results show that among the components of TCOBS, BTM Ant has low resilience and high importance. Considering the correlation among component failures, the TCOBS resilience evaluation results will increase, and those components with higher importance will become more important, while those with lower importance will become less important.