Fault Diagnosis of High-Speed Train Motors Based on a Multidimensional Belief Rule Base

The safe operation of high-speed rail running gear is crucial, as fault diagnosis can effectively prevent potential risks and ensure the smooth operation of the train. The Belief Rule Base (BRB) method has demonstrated excellent performance in complex system modeling. However, during the optimization process, BRB may lead to a "combinatorial explosion" of rules within the model, resulting in a loss of model interpretability and an increase in complexity. To address this, a Multidimensional Belief Rule Base (MBRB) fault diagnosis method is proposed. By optimizing the structure and parameters, the interpretability of the model is enhanced, and its complexity is reduced. Specifically, the model inputs are decomposed into multiple dimensions for analysis, and then the MBRB rules are updated using the Projection Covariance Matrix Adaption Evolution Strategy (P-CMA-ES), increasing the model's interpretability and accuracy. Finally, the effectiveness of this method is validated through an example of high-speed rail running gear.