1 October 2023 in Information Sciences
6 November 2023 in Energy Science & Engineering
State‐of‐health (SOH) estimation methods for Li‐ion batteries are important for the safe operation of the entire system. However, it is often challenging due to the uncertainty within the batteries and the criteria for model interpretability. Belief rule base (BRB) is a rule‐based expert system that has certain advantages for both aspects. However, several problems with BRB interpretability need to be solved urgently. First, expert knowledge credibility is often given subjectively, while objective information is neglected to be considered. Second, BRB interpretability is easily ignored or corrupted in the optimization process. Third, expert knowledge is assumed to be completely reliable information to be used as interpretability evaluation criterion. Therefore, a new SOH estimation method for Li‐ion batteries based on interpretable BRB with expert knowledge credibility (IBRB‐c) is proposed. In the IBRB‐c, the calculation method of expert knowledge credibility is given. Then, an optimization algorithm with interpretability strategies is used. Finally, the concept of the fuzzy interpretable interval is proposed to design the interpretable evaluation criterion. The effectiveness of the proposed method is verified by using the experiment of NASA Li‐ion battery as a case study.
28 August 2023 in IEEE Access
Fault diagnosis plays a critical role in system health management. However, practical fault diagnosis encounters several challenges such as limited observational information, system complexity, and environmental disturbances. Belief rule base with attribute reliability (BRB-r) provides a valuable solution to these problems. In BRB-r, the reliability of the input information directly affects the reliability of the observed metrics and subsequently the accuracy of the output belief degree. To strike a balance between the reliability and accuracy of fault diagnosis models, a new fault diagnosis method for BRB-r considering multi-fault features (BRB-mr) is introduced. In the BRB-mr model, the reliability calculation method for attributes considering multi-fault features is proposed. The obtained attribute reliability is then introduced into the calculation of the matching degree, which ultimately reduces the interference of unreliable information to obtain more accurate and reliable diagnostic results. In addition, an optimization model is used to mitigate the effect of uncertainty in expert knowledge. The effectiveness of the method is validated by a case study of diesel engine fault diagnosis.
17 June 2026 in Neurocomputing