Due to the complexity of the aging process, maintaining the state of health (SOH) of lithium-ion batteries is a significant challenge that must be overcome. This study presents a new SOH estimation approach based on hybrid Grey Wolf Optimization (GWO) with Bayesian Regularized Neural Networks (BRNN). The approach utilizes health features (HFs) extracted from the battery charging-discharging process. Selected external voltage and current characteristics from the charging-discharging process serve as HFs to explain the aging mechanism of the batteries. The Pearson correlation coefficient, the Kendall rank correlation coefficient, and the Spearman rank correlation coefficient are then employed to select HFs that have a high degree of association with battery capacity. In this paper, GWO is introduced as a method for optimizing and selecting appropriate hyper-p parameters for BRNN. GWO-BRNN updates the population through mutation, crossover, and screening operations to obtain the globally optimal solution and improve the ability to conduct global searches. The validity of the proposed technique was assessed by examining the NASA battery dataset. Based on the simulation results, the presented approach demonstrates a higher level of accuracy. The proposed GWO-BRNN-based SOH estimation achieves estimate assessment indicators of less than 1%, significantly lower than the estimated results obtained by existing approaches. The proposed framework helps develop electric vehicle battery prognostics and health management for the widespread use of eco-friendly and reliable electric transportation.
Proper management of vehicle structural factors related to public transportation safety is vital to formulate maintenance strategies and to enhance transportation safety. Therefore, this work aims to comprehensively identify potential structural factors, assess their impacts as regards causing public transportation vehicle malfunctions, and understand their cause–effect interrelationships. Maintenance management can be improved based on the analysis outcomes. Multi-Criteria Decision-Making (MCDM) techniques are widely applied to decision-making problems. However, due to the advanced and complex structures of modern vehicles, conventional single-used MCDM techniques encounter limitations in their ability to thoroughly account for all potential failure factors and to systematically manage the causal interrelationships, which makes the analysis results less practically applicable. To overcome these challenges, this article proposes an innovative MCDM framework. Specifically, Failure Tree Analysis (FTA) and the Interval-Valued Pythagorean Fuzzy Analytic Hierarchy Process (IVPF-AHP) are integrated to construct the logical relationships between the failure structural factors from real-world maintenance records. The factors are ranked and selected based on their severity influence and occurrence likelihood influence. Subsequently, the Interval-Valued Pythagorean Fuzzy Decision-Making Trial and Evaluation Laboratory (IVPF-DEMATEL) takes causal diagrams to identify interdependencies between the factors based on the mitigated ambiguity of human assessments. A case study in the public transportation bus domain is conducted to demonstrate the effectiveness of the proposed MCDM framework. The results offer insightful maintenance suggestions for public transportation operators and engineers to save human labor and material resources.