Remaining useful life prediction for lithium-ion battery based on hybrid machine learning with Wiener process

Yun Qi, Jianping Wang, Huimin Lu, Hongyang Chu, Danyang Chen, Jianli Jin,
Remaining useful life prediction for lithium-ion battery based on hybrid machine learning with Wiener process,
Journal of Energy Storage,
Volume 136,
2025,
118415,
ISSN 2352-152X,
https://doi.org/10.1016/j.est.2025.118415.
(https://www.sciencedirect.com/science/article/pii/S2352152X25031287)
Abstract: Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is essential for ensuring the reliability and safety of battery systems. In this study, we proposed a novel RUL prediction model that integrates machine learning with the Wiener process. This hybrid approach significantly advanced the starting point for prediction while maintaining accuracy. The model leveraged Ensemble Empirical Mode Decomposition (EEMD) to decompose existing health indicators (HIs), followed by the prediction of future HIs using machine learning techniques. The RUL was subsequently derived through the Wiener process based on these predicted HIs. Experimental results demonstrated that the proposed method achieved high precision in RUL estimation, even when the battery had operated for only 25% of its total lifespan. These findings suggest that the model offers substantial improvements in early-stage prognostics for battery health management.
Keywords: Remaining useful life prediction; Deep learning; Wiener process; Lithium-ion batteries; Ensemble empirical mode decomposition