Data-Driven Failure Characteristics and Reliability Analysis for Train Control On-Board Subsystem

Abstract

The train control on-board subsystem (TC-OBS) plays an important role in the safety and efficiency of the high-speed train's operation. Therefore, there is an urgent demand for the analysis of failure characteristics and the reliability of TC-OBS. In this paper, a specific data model is built for the TC-OBS operational and failure data based on data cubes. This model analyzed the failure distribution characteristics of TC-OBS from the combined angles of System Identification, Time and Operation Attribute through the operations of data cubes. Thus, the representative units and systems can be the research objects of the reliability evaluation. With these representative units and systems, this paper uses Bayesian estimation combined with Markov Chain Monte Carlo (MCMC) to estimate the parameters of the time between failures (TBF) distribution model and the reliability is analyzed. Simulation results show that the data model based on data cubes can offer an efficient and convenient method to analyze the failure characteristics and reliability of TC-OBS.