Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175766,
        author = {Asvika A P and Nandhakishore M and Pradeep Kumar M},
        title = {Predicting the Battery Health of Lithium-ion Batteries using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {7197-7202},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175766},
        abstract = {Lithium-ion batteries commonly applied in contemporary technologies are a vital source of green energy solutions to a variety of real-time issues owing to their energy density, long-life period and efficiency benefits. Playing its role, it's also required to pay attention to its maintenance, safety and cost of storage to make it useful for different applications. For its attainment, this piece of work emphasizes presenting an ML-based model to make predictions for battery health. This piece of work utilizes ML models including Decision Tree (DT) and Long Short-Term Memory (LSTM) for the purpose of analyzing data and predicting outcomes. Data captured in real-time from Lithium Iron Phosphate (LFP) battery and Lithium Nickel Manganese Cobalt Oxide (NMC) cells with the aid of external support, were pre-processed and divided into training and test datasets. The model design was created to make the best predictions from the data and lead to precise predictions. On testing and training using LFP battery data, the model predictions were measured with results demonstrating that DT registered a higher Mean Absolute Error (MAE) of 0.9375 whereas LSTM indicated a reduced MAE of 0.01575 and therefore is more suitable for battery health prediction. From this performance, data of NMC cells was treated using LSTM model since it highly comprehends sequential data, identifying the long-term dependencies. These outcomes support efficient and effective monitoring, maintenance, safety and restricting storage cost of the Lithium-ion batteries. This work supports comprehension of the prediction power of the ML methods which has a key role in molding the Lithium-ion batteries as sustainable energy source and solution.},
        keywords = {Decision Tree (DT), Lithium-ion Battery, Lithium Nickel Manganese Cobalt Oxide (NMC), Long Short-Term Memory (LSTM), Machine Learning, Remaining Useful Life (RUL), State of Health (SoH).},
        month = {April},
        }