This paper proposes a new belief rule-based (BRB) expert system for fault diagnosis of marine diesel engines. The expert system is the first of its kind that consists of multiple concurrently activated BRB subsystems, in which each subsystem has its distinctive outputs and uses the evidential reasoning approach for inference. This novel modeling approach can be applied to identify fault modes that may co-exist. In essence, the group of BRB subsystems is used to model the nonlinear relationships between the fault features and the fault modes in marine diesel engines. The initial BRB expert system can be established by using expert experience and then optimized by using the data samples accumulated during the operation of marine diesel engines. Due to limitations in knowledge and data collected, ignorance is also considered in some BRB subsystems. The proposed BRB expert system is applied to abnormal wear detection for a kind of marine diesel engine. The performance of the BRB expert system is investigated in comparison with that of artificial neural network (ANN) models, support vector machine (SVM) models, and binary logistic regression model with fivefold cross-validation. The results show that the BRB expert system can be used for fault diagnosis of marine diesel engines in a probabilistic manner, which outperforms the ANN models, SVM models, and the binary logistic regression model in terms of accuracy and stability, and can effectively identify concurrent faults.

Comprised of multiple belief rules that are close to human knowledge representation, the belief rule base (BRB) has the ability to make full use of both data obtained from historic records and experts’ knowledge under uncertainty. When applied in fault diagnosis, the final diagnostic results are inferred by first activating the matching degrees and activation weights, and then integrating the activated rules with the evidential reasoning algorithm. In this study, a novel BRB prediction approach is proposed for concurrent fault diagnosis. In the proposed approach, the indicative factors are modeled as attributes with customized attribute weights to represent their relevance to a known system fault and vice versa. Second, a tradeoff analysis is conducted by comparing the beliefs for different faults. The diagnosed faults with bigger beliefs within a predetermined valve would be considered as concurrent faults. To further improve the prediction accuracy, an optimization approach with the differential evolutionary algorithm as the optimization engine is designed with model constraints reflecting the complex correlations between the indicative factors and concurrent faults. A marine diesel engine fault diagnosis case is studied for validation. Case study results show that: first, both single and concurrent faults can be diagnosed with high accuracy by the proposed BRB prediction approach; second, the BRBs with optimized attributes weights has shown superior performance than with equal and fixed attribute weights; and third, the new BRB prediction approach outperforms the previous approach with multiple sub-BRBs as well as other approaches to achieve a higher modeling accuracy.