Real-time reliability evaluation method for train-ground communication subsystem based on dynamic Bayesian networks

Abstract

T rain-ground communication subsystem is a key subsystem in high-speed train control system and plays an important role during the operation of high-speed train. So the reliability of train-ground communication subsystem should be studied in depth. The dynamic fault tree model for train-ground communication subsystem that is modeled based on the structure chart of the subsystem is transformed to Dynamic Bayesian networks. After this, probability of the top event can be obtained by inference algorithm of Bayesian network, and the probability of sub-equipment's failure under the premise of system's failure will be obtained through reverse inference algorithm, which can provide reference information for fault location. The simulations reveal that the reliability of train-ground communication subsystem at any time can be obtained by Dynamic Bayesian Networks method, so we can perform real-time reliability evaluation on train-ground communication subsystem.