A Semi-Quantitative Information Based Fault Diagnosis Method for the Running Gears System of High-Speed Trains

The proper operation of running gears of a high-speed train is one of the key factors to ensure its safety and reliability. The diagnosis of the state of running gears of a high-speed train is one of the effective ways to improve its reliability. It is difficult to diagnose the running gears of a high-speed train accurately because of the characteristics of its complex-analytic structure, multiple types of monitoring feature data, and lack of effective failure mode data. Therefore, this paper proposes a fault diagnosis method for the running gears of a high-speed train based on a semi-quantitative information model. The relation between the effective data and expert knowledge is studied, and the state of the running gears of a high-speed train is rigorously analyzed. To reduce the data dimension and the diagnostic calculation time of the running gears of a high-speed train, the principal component analysis (PCA) is used to screen its key monitoring features. Then, based on the change of the feature quantity in the working process of the running gears of a high-speed train, the semi-quantitative information model of belief-rule-base (BRB) fault diagnosis is established. In the diagnosis process, the initial model parameters of BRB are determined by expert knowledge and they have certain subjectivity. To improve the accuracy of the model, the constrained covariance matrix adaptive evolutionary strategy (CMA-ES) algorithm is used to optimize the parameters of the initial BRB model to improve the validity and accuracy of the diagnosis. Finally, to verify the effectiveness of the proposed semi-quantitative information model, a set of real data of the running gears of a high-speed train is used as case studies.