EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Ridge Regression-based Approach for Estimate of Remaining Life Prediction of Lithium Battery

Olof Andersson, Linnea Gustafsson, Erik Nilsson

Optimizations in Applied Machine Learning · 2025

DOI: 10.71070/oaml.v5i1.128 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optimizations in Applied Machine Learning, 2025. Verfasst von Olof Andersson und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the context of lithium battery performance prediction, this paper addresses the critical need for accurately estimating the remaining life of the battery to optimize its utilization. Despite existing research efforts, challenges persist in achieving precise predictions due to factors like non-linear degradation mechanisms and limited data availability. To overcome these obstacles, our study proposes a novel Ridge Regression-based approach that integrates machine learning techniques with physics-based models. This innovative method not only improves prediction accuracy but also enhances model interpretability. By combining empirical data with theoretical insights, our research contributes to advancing the field of lithium battery prognostics.

Zitieren

APA

Andersson, O., Gustafsson, L., & Nilsson, E. (2025). Ridge Regression-based Approach for Estimate of Remaining Life Prediction of Lithium Battery. Optimizations in Applied Machine Learning. https://doi.org/10.71070/oaml.v5i1.128

Vancouver

Andersson O, Gustafsson L, Nilsson E. Ridge Regression-based Approach for Estimate of Remaining Life Prediction of Lithium Battery. Optimizations in Applied Machine Learning. 2025. doi:10.71070/oaml.v5i1.128

BibTeX
@article{Andersson2025,
  author = {Andersson, Olof and Gustafsson, Linnea and Nilsson, Erik},
  title = {Ridge Regression-based Approach for Estimate of Remaining Life Prediction of Lithium Battery},
  journal = {Optimizations in Applied Machine Learning},
  year = {2025},
  doi = {10.71070/oaml.v5i1.128}
}
Kostenlos starten →