Health Status Prediction Based on Belief Rule Base for High-Speed Train Running Gear System

• Main Authors: Chao Cheng, Jiuhe Wang, Wanxiu Teng, Mingliang Gao, Bangcheng Zhang, Xiaojing Yin, Hao Luo
• Format: Article
• Language: English
• Published: IEEE 2019-01-01
• Series: IEEE Access
• Subjects: Belief rule base; projection constrained covariance matrix adaptive evolution strategy; fatal degree; singular value decomposition; health status prediction
• Online Access: https://ieeexplore.ieee.org/document/8579136/

The running gear is a vital component of a high-speed train to ensure operation safety. Accurately predicting the future health status of the running gear is significant to keep the reliability and safety of trains. It is difficult to predict the future health status based on the analytical model of the running gear system because of its complexity and coupling. Moreover, the fault data are a minor part of tremendous data in the running and monitoring process of a high-speed train, which obstructs accurately predicting the health status based on a data-driven method. To solve the above problems, this paper proposes a health status prediction method based on the belief rule base (BRB) for the running gear system. First, a failure mechanism is analyzed to confirm the fault characteristics, which can represent the health status of the running gear system. Second, in order to avoid the limitations of a single sensor acquisition, such as a lack of comprehensiveness and robustness, singular value decomposition is used to achieve multisensory information fusion. The fused features are used as the input to the health status prediction model. Data fusion is a way to improve the precision of the health status prediction in the model input. Then, this model based on the BRB is established using the fault data and expert knowledge. During the process of prediction, the subjectivity of experts makes the initial BRB imprecise, so a projection constrained covariance matrix adaptive evolution strategy algorithm is needed to optimize the initial parameters and improve the accuracy of the proposed model. Finally, a case study for the running gear system is carried out to verify the effectiveness and accuracy of the proposed model. The results show that the proposed model can help to accurately predict the health status of the running gear system.