Experimental Investigation of Mechanical Vibration Effects on Lithium-Ion Battery State-of-Charge Estimation Using Ensemble Machine Learning Models

Accurate state-of-charge (SoC) estimation is a critical requirement for reliable battery management systems in electric vehicles. While data-driven and machine learning approaches have demonstrated high estimation accuracy, most existing studies assume ideal operating conditions and neglect the influence of mechanical disturbances. In practical automotive environments, lithium-ion batteries are continuously exposed to mechanical vibration, which may affect electrical signals and estimation reliability. In this study, the impact of mechanical vibration on SoC estimation accuracy is experimentally investigated using standardized vibration tests conducted in accordance with IEC ۶۲۶۶۰-۲. A cylindrical ۱۸۶۵۰ lithium-ion cell is subjected to random vibration along three orthogonal axes during charge–discharge cycles. Four ensemble-based machine learning models—Random Forest, Extra Trees, Gradient Boosting, and LightGBM—are developed and evaluated under vibration-free and vibration-exposed conditions. Quantitative results based on RMSE and MAE metrics demonstrate that mechanical vibration leads to a noticeable degradation in SoC estimation accuracy for all models. However, the degree of sensitivity varies among algorithms. Extra Trees and LightGBM exhibit superior robustness to vibration-induced disturbances compared to Random Forest and Gradient Boosting. The findings highlight the importance of considering mechanical operating conditions when designing data-driven SoC estimation algorithms for real-world applications.

کلیدواژه ها:

Lithium-ion battery ، Mechanical vibration ، State-of-charge estimation ، Ensemble learning ، Battery management system ، Experimental study