Experimental Investigation of an AI-Embedded Battery Management System for Improved State-of-Charge and State-of-Health Estimation and Remaining Useful Life Prediction of Lithium-Ion Batteries in Electric Vehicles
Computer and Decision Making An International Journal · 15.11.2026
DOI: 10.1922/comdem.v4i1.19146 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making An International Journal, online erschienen am 15.11.2026. Verfasst von MANOJKUMAR CHAVHAN und 5 weiteren Autor:innen.
Abstract (Originalsprache)
State-of-charge (SoC), state-of-health (SoH) and remaining useful life (RUL) estimation are key components of battery decision-making in EVs. This study reports an AI-integrated battery management architecture that integrates physics-based baselines, machine-learning estimation and uncertainty-aware supervisory rules. The CALCE Battery Research Data repository is one of the main sources for performing task-specific laboratory measurements. Evaluation design with leakage resistance includes independent-cell validation, chronological lifetime features, baseline comparisons, explainability and operational decision metrics. An example of three tasks given for research planning is provided as a demonstration of standardized reporting and figure consistency and should not be interpreted as an actual CALCE experiment. The study does not therefore claim to prove any gains in accuracy or in performance of embedded vehicles but rather offers a repeatable framework and reporting protocol for transparency. Empirical claims are to be made after independent cell-level experiments, after prediction-level uncertainty assessments and after hardware validation.
Zitieren
APA
CHAVHAN, M., Patil, D. R. J., Parhate, D. V., Pachar, D. S., N, S., & Kumar, S. (2026). Experimental Investigation of an AI-Embedded Battery Management System for Improved State-of-Charge and State-of-Health Estimation and Remaining Useful Life Prediction of Lithium-Ion Batteries in Electric Vehicles. Computer and Decision Making An International Journal. https://doi.org/10.1922/comdem.v4i1.19146
Vancouver
CHAVHAN M, Patil DRJ, Parhate DV, Pachar DS, N S, Kumar S. Experimental Investigation of an AI-Embedded Battery Management System for Improved State-of-Charge and State-of-Health Estimation and Remaining Useful Life Prediction of Lithium-Ion Batteries in Electric Vehicles. Computer and Decision Making An International Journal. 2026. doi:10.1922/comdem.v4i1.19146
BibTeX
@article{CHAVHAN2026,
author = {CHAVHAN, MANOJKUMAR and Patil, Dr. Rupesh Jagatarao and Parhate, Dr Vivek and Pachar, Dr. Sunita and N, Sowrirajan and Kumar, Saket},
title = {Experimental Investigation of an AI-Embedded Battery Management System for Improved State-of-Charge and State-of-Health Estimation and Remaining Useful Life Prediction of Lithium-Ion Batteries in Electric Vehicles},
journal = {Computer and Decision Making An International Journal},
year = {2026},
doi = {10.1922/comdem.v4i1.19146}
}
EUVIMED