Abstract

Lithium-ion batteries are paramount energy storage devices used in modern electric vehicles because of its favourable energy density, light weight and environmental benefits. However, issues related to ageing, degrade mechanism, long term reliability and safety remain critical, particularly under variable operating conditions. Reliable estimation of Remaining Useful Life (RUL), State of Charge (SOC) and State of Health (SOH) is therefore required to support efficient energy management and prevent premature battery failure in electric vehicle applications. Recent years, machine learning algorithms have been increasingly adopted for battery state estimation. Nevertheless, systematic comparison of commonly used algorithms for simultaneously predicting RUL, SOC and SOH are still limited. In this work five machine learning models-Decision Tree (DT), Random Forest (RF), Bagging Regressor (BR), XG Boost (XGB) and an ensemble voting regressor combining Random Forest and XG Boost are implemented and evaluated using Hawaii Natural Energy Institute (HNEI) data set comprising capacity, voltage, temperature and cycle life features. Model performance is assessed using Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE) and R-Square (R2). Ensemble model consistently achieves lower prediction error and improved stability with less computational time compared to individual learners across all estimation tasks. The results indicate that combining tree-based models with gradient boosting improves generalization performance while maintain computational feasibility, making the proposed approach suitable for practical battery management systems deployment in electric vehicles.

Keywords

Battery Management Systems, Lithium-Ion, Ensemble Machine Learning, Grid Search Cross Validation, Voting Regressor, Performance Evaluation Metrics,

Downloads

Download data is not yet available.

References

  1. M.A. Hannan, M.M. Hoque, A. Hussain, Y. Yusof, P.J. Ker, State of-the-art and energy management system of lithium-ion batteries in electric vehicle applications: Issues and recommendations. IEEE Access, 6, (2018) 19362-19378. https://doi.org/10.1109/ACCESS.2018.2817655
  2. S. Pan, L.M. Fulton, A. Roy, J. Jung, Y. Choi, H.O. Gao, Shared use of electric autonomous vehicles: Air quality and health impacts of future mobility in the United States. Renewable and Sustainable Energy Reviews, 149, (2021) 111380. https://doi.org/10.1016/j.rser.2021.111380
  3. N.H. Paulson, J. Kubal, L. Ward, S. Saxena, W. Lu, S.J. Babinec, Feature engineering for machine learning enabled early prediction of battery lifetime. Journal of Power Sources, 527, (2022) 231127. https://doi.org/10.1016/j.jpowsour.2022.231127
  4. C.L. Sravanthi, J.N. Chandra Sekhar, Advances in Nano Metal Oxides and Nanotechnology for Lithium-Ion Batteries in EV: A Comprehensive Review. Journal of Modern Technology, 2(01), (2025) 254-263. https://doi.org/10.71426/jmt.v2.i1.pp254-263
  5. M. Elmahallawy, T. Elfouly, A. Alouani, A.M. Massoud, A comprehensive review of lithium-ion batteries modeling, and state of health and remaining useful lifetime prediction. Ieee Access, 10, (2022) 119040-119070. https://doi.org/10.1109/ACCESS.2022.3221137
  6. C.L. Sravanthi, J.N. Chandra Sekhar, N.C. Alluraiah, C. Dhanamjayulu, H. Kumar Pujari, B. Khan, An Overview of Remaining Useful Life Prediction of Battery Using Deep Learning and Ensemble Learning Algorithms on Data-Dependent Models, International Transactions on Electrical Energy Systems, 2025(10), (2025) 2242749. https://doi.org/10.1155/etep/2242749
  7. A. Haraz, K. Abualsaud, A. Massoud, State-of-health and state-of-charge estimation in electric vehicles batteries: a survey on machine learning approaches. IEEE Access, 12, (2024) 158110 – 158139. https://doi.org/10.1109/ACCESS.2024.3486989
  8. M.F. Ng, J. Zhao, Q. Yan, G.J. Conduit, Z.W. Seh, Predicting the state of charge and health of batteries using data-driven machine learning. Nature Machine Intelligence, 2(3), (2020) 161-170. https://doi.org/10.1038/s42256-020-0156-7
  9. D. Obuli Pranav, P.S. Babu, V. Indragandhi, B. Ashok, S. Vedhanayaki, C. Kavitha, Enhanced SOC estimation of lithium-ion batteries with RealTime data using machine learning algorithms. Scientefic Reports 14, (2024) 16036. https://doi.org/10.1038/s41598-024-66997-9
  10. V. Chandran, C.K. Patil, A. Karthick, D. Ganeshaperumal, R. Rahim, A. Ghosh, State of Charge Estimation of Lithium-Ion Battery for Electric Vehicles Using Machine Learning Algorithms. World Electric Vehicle Journal, 12(1), (2021) 38. https://doi.org/10.3390/wevj12010038
  11. H. Rauf, M. Khalid, N. Arshad, Machine learning in state of health and remaining useful life estimation: Theoretical and technological development in battery degradation modelling. Renewable and Sustainable Energy Reviews, 156, (2022) 111903. https://doi.org/10.1016/j.rser.2021.111903
  12. L.B. Chilakapati, G.T. Manohar, Power Quality Improvement in a Grid Connected Solar-PV System With Adaptive Neuro-Fuzzy Controller Based UPQC”. International Research Journal of Multidisciplinary Technovation 7(1), (2025) 264-279. https://doi.org/10.54392/irjmt25118
  13. C. Zhang, S. Zhao, Z. Yang, Y. Chen, A reliable data-driven state-of-health estimation model for lithium-ion batteries in electric vehicles. Frontiers in Energy Research, 10, (2022) 1013800. https://doi.org/10.3389/fenrg.2022.1013800
  14. H. Meng, Y.F. Li, A review on prognostics and health management (PHM) methods of lithium-ion batteries. Renewable and Sustainable Energy Reviews, 116, (2019) 109405. https://doi.org/10.1016/j.rser.2019.109405
  15. Y. Muratoglu, A. Alkaya, Unscented Kalman Filter based State of Charge Estimation for the Equalization of Lithium-ion Batteries on Electrical Vehicles. Engineering, Technology & Applied Science Research. 9, (2019) 4876–4882. https://doi.org/10.48084/etasr.3111
  16. C. Shan, C.S. Chin, V. Mohan, C. Zhang, Review of Various Machine Learning Approaches for Predicting Parameters of Lithium-Ion Batteries in Electric Vehicles. Batteries 10, (2024) 181. https://doi.org/10.3390/batteries10060181
  17. X. Li, D. Yu, V.S. Byg, S.D. Ioan, The development of machine learning-based remaining useful life prediction for lithium-ion batteries. Journal of Energy Chemistry, 82, (2023) 103-121. https://doi.org/10.1016/j.jechem.2023.03.026
  18. M. Zhang, D. Yang, J. Du, H. Sun, L. Li, L. Wang, K. Wang, A review of SOH prediction of Li-ion batteries based on data-driven algorithms. Energies, 16(7), (2023) 3167. https://doi.org/10.3390/en16073167
  19. L. Ren, J. Dong, X. Wang, Z. Meng, L. Zhao, M.J. Deen, A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life. IEEE transactions on industrial informatics, 17(5), (2020) 3478-3487. https://doi.org/10.1109/TII.2020.3008223
  20. D. Aloisio, G. Campobello, S.G. Leonardi, F. Sergi, G. Brunaccini, M. Ferraro, V. Antonucci, A. Segreto, N. Donato, Comparison of machine learning techniques for SoC and SoH evaluation from impedance data of an aged lithium ion battery. Acta IMEKO, 10(2), (2021) 80-87. https://doi.org/10.21014/acta_imeko.v10i2.1043
  21. S. Jafari, Y.C. Byun, S. Ko, A novel approach for predicting remaining useful life and capacity fade in lithium-ion batteries using hybrid machine learning. IEEE Access, 11, (2023) 131950-131963. https://doi.org/10.1109/ACCESS.2023.3329508
  22. S. Jafari, Z. Shahbazi, Y.C. Byun, S.J. Lee, Lithium-ion battery estimation in online framework using extreme gradient boosting machine learning approach. Mathematics, 10(6), (2022) 888. https://doi.org/10.3390/math10060888
  23. K. Akbar, Y. Zou, Q. Awais, M.J.A. Baig, M. Jamil, A machine learning-based robust state of health (SOH) prediction model for electric vehicle batteries. Electronics, 11(8), (2022) 1216. https://doi.org/10.3390/electronics11081216
  24. S. Song, C. Fei, H. Xia, Lithium-ion battery SOH estimation based on XGBoost algorithm with accuracy correction. Energies, 13(4), (2020) 812. https://doi.org/10.3390/en13040812
  25. S. Jo, S. Jung, T. Roh, Battery State-of-Health Estimation Using Machine Learning and Preprocessing with Relative State-of-Charge. Energies 14, (2021) 7206. https://doi.org/10.3390/en14217206
  26. S. Jafari, Y.C. Byun, Optimizing battery RUL prediction of lithium-ion batteries based on Harris hawk optimization approach using random forest and LightGBM. IEEE Access, 11, (2023) 87034-87046. https://doi.org/10.1109/ACCESS.2023.3304699
  27. J.C. Sekhar, B. Domathoti, E.D. Santibanez Gonzalez, Prediction of battery remaining useful life using machine learning algorithms. Sustainability, 15(21), (2023) 15283. https://doi.org/10.3390/su152115283
  28. V.T. Ha, P.T. Giang, Experimental study on remaining useful life prediction of lithium-ion batteries based on three regression models for electric vehicle application. Applied Sciences, 13(13), (2023) 7660. https://doi.org/10.3390/app13137660
  29. C.L. Sravanthi, J.N. Chandra sekhar, Predicting Remaining Useful Life of Lithium-Ion Batteries for Electric Vehicles Using Machine Learning Regression Models. ITEGAM-JETIA. 11(51), (2025) 143-150. https://doi.org/10.5935/jetia.v11i51.1267
  30. K. Karthick, S. Ravivarman, R. Priyanka, Optimizing Electric Vehicle Battery Life: A Machine Learning Approach for Sustainable Transportation. World Electric Vehicle Journal, 15(2), (2024) 60. https://doi.org/10.3390/wevj15020060
  31. G. dos Reis, C. Strange, M. Yadav, S. Li, Lithium-ion battery data and where to find it. Energy and AI, 5, (2021) 100081. https://doi.org/10.1016/j.egyai.2021.100081
  32. Dataset Link. Available online: https://www.kaggle.com/datasets/ignaciovinuales/battery-remaining-useful-life-rul.
  33. M.Z. Naser, A.H. Alavi, Error Metrics and Performance Fitness Indicators for Artifcial Intelligence and Machine Learning in Engineering and Sciences. Architecture, Structures and Construction, 3, (2021) 499–517. https://doi.org/10.1007/s44150-021-00015-8