For ensuring the safety and reliability of high-speed trains, fault diagnosis (FD) technique plays an important role. Benefiting from the rapid developments of artificial intelligence, intelligent FD (IFD) strategies have obtained much attention in the field of academics and applications, where the qualitative approach is an important branch. Therefore, this survey will present a comprehensive review of these qualitative approaches from both theoretical and practical aspects. The primary task of this paper is to review the current development of these qualitative IFD techniques and then to present some of the latest results. Another major focus of our research is to introduce the background of high-speed trains, like the composition of the core subsystems, system structure, etc., based on which it becomes convenient for researchers to extract the diagnostic knowledge of high-speed trains, where the purpose is to understand how to use these types of knowledge. By reasonable utilization of the knowledge, it is hopeful to address various challenges caused by the coupling among subsystems of high-speed trains. Furthermore, future research trends for qualitative IFD approaches are also presented.

Fault diagnosis is a key way to improve the efficient, safe and stable operation of high-speed trains. This paper proposes a fault diagnosis method based on belief rule base with mixed reliability (BRB-mr). Different from the traditional BRB, this method considers two kinds of interference factors that affect the observation data in engineering practice, including the performance of sensors and the influence of external environment, and we quantify them as static reliability and dynamic reliability of attributes in BRB. In order to integrate two kinds of reliability factors into the reasoning of BRB, a discount method is developed based on Dempster-Shafer theory (D-S theory), which is helpful for more accurate diagnosis. In this paper, the effectiveness and practicability of the method are verified by a single fault of the running gear, and the supplementary numerical data verified its feasibility in multiple fault mode diagnosis. Then this method is compared with traditional methods. The result shows BRB-mr model has stronger diagnostic ability to identify faults and it has a certain engineering application value to be extended to other complex system fault diagnosis.

The emergence of large-scale engineering and macro engineering promotes the development of large-scale complex electromechanical systems (LCESs). The LCES complexity of structures and failure mechanisms makes it difficult to achieve the aim of health management and fault diagnosis of such systems. One of the reasons is lacking detailed consideration of various uncertainties from the process of system assessment. Belief rule base (BRB) shows advantages in modeling nonlinear complex systems under the uncertainty environment. However, the current BRB-based work only focuses on optimizing the initial parameters to deal with the impact of cognitive uncertainty, and issues, such as monitoring and environmental uncertainties, are not considered. Thus, this article proposes the multidiscounted BRB (MBRB) to evaluate the health status of LCESs. Different from traditional BRB, MBRB can reduce the negative influence of cognitive uncertainties on system assessment from another perspective, the so-called expert reliability discount model. In addition, monitoring and environmental uncertainties are also considered in MBRB modeling. Three uncertainties can be quantified by statistical models, and they can be integrated into MBRB by combining with evidence discount theory. Due to the treatment of these uncertainties, MBRB can provide accurate results. In comparison with traditional methods, the proposed method shows superior performance in the health assessment of high-speed trains.

The running gear is a vital component of a high-speed train to ensure operation safety. To accurately predict 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 a running gear system. First, 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 (SVD) 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 (P-CMA-ES) algorithm is needed to optimize the initial parameters and improve the accuracy of the proposed model. Lastly, a case study for a 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 accurately predict the health status of the running gear system.

The health status of the running gear in high-speed trains changes dynamically with time in a complete life cycle. Running gear systems composed of many coupled components are complex, and health statuses of which are difficult to predict in real time through a traditional health status prediction scheme. Lately, belief rule base (BRB), which is able to combine quantitative information and expert knowledge, has shown excellent expression in modeling complex systems. In the procedure of health status prediction, expert expertise can sufficiently enhance the accuracy and efficiency of this model. Therefore, this paper puts forwards a real-time health status prediction framework based on a multi-layer BRB with priority scheduling strategies for running gears. In the first-layer BRB, a time-series prediction model of multiple module BRB considering complete features is established. In the second-layer model, grey relation analysis (GRA) is employed in priority scheduling strategies of features. The third-layer BRB is used for assessing the health status of running gears by combining the features. In addition, the initial parameters of all module BRB given by experts may not be precise. Accordingly, the initial parameters in the BRB are updated by the recursive algorithm online. Finally, the proposed method is tested on the testing platform in running gears. The results make it clear the proposed method can predict the health status of running gears with much accuracy in real time.

In order to ensure the safe and efficient operation of dynamic system in engineering practice, solve the common problems such as nonlinearity, timeliness and uncertainty in realtime status tracking during system operation. This paper studies a status assessment model for dynamic system based on cloud evidence reasoning. Based on the traditional evidence reasoning model, cloud model is introduced to enhance the description ability of expert knowledge in the model. Considering the operating environment of dynamic system in engineering practice, the uncertainty information in operating process is described and quantified by defining static reliability and dynamic reliability. Finally, the effectiveness and correctness of the method are verified by the High-Speed train running gear system.