A Hybrid Deep Learning and XAI-Driven Framework for‎Accurate Estimation of Battery SOC AND SOH

  • Authors

    • N Sumana Keerthi Department of EEE, Koneru Lakshmaiah Education Foundation, Green Fields ‎Vaddeswaram, India
    • B. Jyothi Department of EEE, Koneru Lakshmaiah Education Foundation, Green Fields ‎Vaddeswaram, India
    • Kalyan D. Department of EEE, Koneru Lakshmaiah Education Foundation, Green Fields ‎Vaddeswaram, India
    • K. V. Govardhan Rao Department of EEE, St. Martin’s Engineering College, Secunderabad, Telangana, India
    • Teerdala Rakesh Department of EEE, St. Martin’s Engineering College, Secunderabad, Telangana, India
    • M. Kiran Kumar Department of EEE, Koneru Lakshmaiah Education Foundation, Green Fields ‎Vaddeswaram, India
    https://doi.org/10.14419/16vk8033

    Received date: November 11, 2025

    Accepted date: December 9, 2025

    Published date: December 16, 2025

  • Hybrid Deep Learning; Recurrent Neural Networks; Bi-directional LSTM; Hybrid LSTM-‎GRU; Machine Learning

  • Abstract

    Understanding battery State of Health (SoH) and State of Charge (SoC) ‎predictions highly ensure reliability, safety, and longevity in energy storage systems, ‎especially for electric vehicles and smart grids. This novel hybrid-type framework ‎enables the successive application of machine learning and deep learning models in ‎SOC and SOH estimations. A one-of-a-kind blend of Linear Regression, XG-Boost, ‎Recurrent Neural Networks (RNN), Bi-directional LSTM, and hybrid LSTM-GRU ‎is suggested to capture as many temporal and non-linear patterns in battery behavior ‎as possible. K-Best feature selection is used to enhance model generalization by ‎keeping only the most important input features. Contrary to the existing ‎unexplainable models, our approach leverages explainable AI methods-SHAP and ‎LIME-to explain model decisions and magnitude of feature impact. Real-world ‎battery datasets weighed experimentally underline the superiority of our approach ‎from both accuracy and interpretability perspectives over traditional means. This ‎paper's novelty lies in a hybrid modeling architecture, an interpretable learning ‎pipeline, and a consideration of both predictive ability and interpretability. This ‎framework has enormous potential to draw the innovations forward in intelligent ‎battery management systems‎.

  • References

    1. Alamin K.S.S., Chen Y., MacIi E., Poncino M., Vinco S. (2022) A Machine Learning-Based Digital Twin for Electric Vehicle Battery Modeling, IEEE Int. Conf. Omni-Layer Intell. Syst., 2022, COINS 2022. https://doi.org/10.1109/COINS54846.2022.9854960.
    2. Bandara T.R., Halgamuge M.N. (2022) Modeling a Digital Twin to Predict Battery Deterioration with Lower Prediction Error in Smart Devices: From the Internet of Things Sensor Devices to Self-Driving Cars, IECON Proc. (Ind. Electron. Conf.), 2022, October, https://doi.org/10.1109/IECON49645.2022.9968677.
    3. Branco C.T.N.M., Fontanela J.M. (2024) A Design Methodology to Employ Digital Twins for Remaining Useful Lifetime Prediction in Electric Ve-hicle Batteries, SAE Tech. Pap., January, https://doi.org/10.4271/2023-36-0132.
    4. K. V. G. Rao et al., “Microgrid with, vehicle-to-grid and grid-to-vehicle technology for DC fast charging topology,” Renew. Energy Plug-In Electr. Veh., pp. 45–57, 2024, https://doi.org/10.1016/B978-0-443-28955-2.00004-4.
    5. Jafari S., Byun Y.C. (2022) Prediction of the Battery State Using the Digital Twin Framework Based on the Battery Management System, IEEE Access, 10, 124685–124696. https://doi.org/10.1109/ACCESS.2022.3225093.
    6. Kim G., Kang S., Park G., Min B.C. (2023) Electric Vehicle Battery State of Charge Prediction Based on Graph Convolutional Network, Int. J. Au-tomot. Technol., 24(6), 1519–1530. https://doi.org/10.1007/s12239-023-0122-6.
    7. K. Venkata Govardhan Rao, M. K. Kumar, B. S. Goud, M. Bajaj, M. Abou Houran, and S. Kamel, “Design of a bidirectional DC/DC converter for a hybrid electric drive system with dual-battery storing energy,” Front. Energy Res., vol. 10, no. November, 2022, https://doi.org/10.3389/fenrg.2022.972089.
    8. Li H., Bin Kaleem M., Chiu I.J., Gao D., Peng J., Huang Z. (2024) An Intelligent Digital Twin Model for the Battery Management Systems of Elec-tric Vehicles, Int. J. Green Energy, 21(3), 461–475. https://doi.org/10.1080/15435075.2023.2199330.
    9. M. Pushkarna et al., “A new-fangled connection of UPQC tailored power device from wind farm to weak-grid,” Front. Energy Res., vol. 12, no. February, pp. 1–19, 2024, https://doi.org/10.3389/fenrg.2024.1355867.
    10. Nair P., et al. (2024) AI-Driven Digital Twin Model for Reliable Lithium-Ion Battery Discharge Capacity Predictions, Int. J. Intell. Syst., 2024, https://doi.org/10.1155/2024/8185044.
    11. K. V. G. Rao and M. K. Kumar, “The harmonic reduction techniques in shunt active power filter when integrated with non-conventional energy sources,” Indones. J. Electr. Eng. Comput. Sci., vol. 25, no. 3, pp. 1236–1245, 2022, https://doi.org/10.11591/ijeecs.v25.i3.pp1236-1245.
    12. Sugashini R., Mangaiyarkarasi S.P. (2023) Hybrid Deep Learning Algorithm for the State of Charge Prediction of the Lithium-Ion Battery for Elec-tric Vehicles, Iran. J. Chem. Chem. Eng., 42(8), 2550–2560.
    13. Qian C., et al. (2023) A CNN-SAM-LSTM Hybrid Neural Network for Multi-State Estimation of Lithium-Ion Batteries, SSRN, https://doi.org/10.2139/ssrn.4574033.
    14. B. N. Reddy et al., “Switched Quasi Impedance-Source DC-DC Network for Photovoltaic Systems,” Int. J. Renew. Energy Res., vol. 13, no. 2, pp. 681–698, 2023, [Online]. Available: https://www.ijrer.org/ijrer/index.php/ijrer/article/view/14097.
    15. Rajesh P.K., Soundarya T., Jithin K.V. (2024) Driving Sustainability – The Role of Digital Twin in Enhancing Battery Performance for Electric Ve-hicles, J. Power Sources, 604, 234464. https://doi.org/10.1016/j.jpowsour.2024.234464.
    16. Renold A.P., Kathayat N.S. (2024) Comprehensive Review of Machine Learning, Deep Learning, and Digital Twin Data-Driven Approaches in Battery Health Prediction of Electric Vehicles, IEEE Access, 12, 43984–43999. https://doi.org/10.1109/ACCESS.2024.3380452.
    17. Vidal C., Malysz P., Kollmeyer P., Emadi A. (2020) Machine Learning Applied to Electrified Vehicle Battery State of Charge and State of Health Estimation: State-of-the-Art, IEEE Access, 8, 52796–52814. https://doi.org/10.1109/ACCESS.2020.2980961.
    18. Simonyan K., Zisserman A. (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition, 3rd Int. Conf. Learn. Represent. (ICLR 2015) – Conf. Track Proc.
    19. Wu B., Widanage W.D., Yang S., Liu X. (2020) Battery Digital Twins: Perspectives on the Fusion of Models, Data, and Artificial Intelligence for Smart Battery Management Systems, Energy AI, 1, 100016. https://doi.org/10.1016/j.egyai.2020.100016.
    20. Zhao Y., Wang Z., Shen Z.J.M., Sun F. (2021) Data-Driven Framework for Large-Scale Prediction of Charging Energy in Electric Vehicles, Appl. Energy, 282. https://doi.org/10.1016/j.apenergy.2020.116175.

  • Downloads

  • How to Cite

    Keerthi, N. S. ., Jyothi , B. ., D., K. ., Rao, K. V. G. ., Rakesh , T. ., & Kumar , M. K. . (2025). A Hybrid Deep Learning and XAI-Driven Framework for‎Accurate Estimation of Battery SOC AND SOH. International Journal of Basic and Applied Sciences, 14(8), 284-301. https://doi.org/10.14419/16vk8033