Fault Diagnosis Method for TrainGround Wireless Communication Unit Based on Fusion of Rough Sets and Evidence Theory

Abstract:

Under the condition of inconsistent fault diagnosis information,fault diagnosis reasoning fusion strategy integrating rough sets and evidence theory method for trainground wireless communication unit of communicationbased train control (CBTC) is proposed.By using rough sets,redundant part of characteristic data is eliminated and irrelevant indispensable characters are extracted.Then,a decision network with different reduced levels is constructed to denote the fault diagnosis problems of the trainground wireless communication (TGWC) unit by way of the definition of the rule confidence and coverage degree.Finally,a fault identification mechanism based on evidence theory is presented to process fault data collected by various sensors and exactly match them with diagnosis rules.Results show that with the diagnosis model,the ability of model fault diagnosis is improved with strong practicality.