Hybrid XGBoost-LSTM Framework for Accurate SOC, SOH, DOD and Internal Resistance Estimation in Li-ion Cells
DOI:
https://doi.org/10.26877/asset.v8i2.3119Keywords:
battery management system (BMS), hybrid ensemble, time series modelling, battery diagnostics, lithium ion batteries, embedded inference, state of charge estimationAbstract
Accurate estimation of State of Charge (SOC), State of Health (SOH), Depth of Discharge (DOD), and internal resistance is critical for Battery Management Systems (BMS) in electric vehicles and energy storage. Conventional methods fail to capture the nonlinear and temporal dynamics of lithium-ion cells, while existing machine learning approaches lack systematic benchmarking for embedded deployment. This study evaluates three hybrid models XGBoost-LSTM, XGBoost-SVR, and Linear Regression-Random Forest on high-resolution Samsung 30T single-cell data (five cycles, 6,081 timesteps). Models used 35 mutual information-selected features, identical preprocessing, and Bayesian hyperparameter optimization. XGBoost-LSTM achieved superior accuracy: SOC (R²=0.983), SOH (R²=0.985), DOD (R²=0.977), and internal resistance (R²=0.972), outperforming baselines significantly (Wilcoxon p<0.05). Computational profiling showed 15 ms inference latency and 60 MB memory usage, suitable for real-time BMS at 10 Hz. Results indicate that hybrid temporal learning improves battery diagnostics, while further validation across multiple chemistries, extended temperatures, multi-cell setups, and longer cycles is recommended for practical deployment.
References
[1] Zhu B, Jia L, Pan Q, Zhang H. Cross-domain battery SOH and RUL estimation via Domain-Adaptive Transformer. Energy 2025;341. https://doi.org/10.1016/j.energy.2025.139288.
[2] Cao C, Gao H, Liu F, Maysrah M, Zhou Y, Chen L. Early prediction of lithium-ion battery life using a hybrid deep neural network and ensemble learning approach. Computers and Chemical Engineering 2026;205. https://doi.org/10.1016/j.compchemeng.2025.109465.
[3] Park MS, Lee JK, Kim BW. SOH Estimation of Li-Ion Battery Using Discrete Wavelet Transform and Long Short-Term Memory Neural Network. Applied Sciences (Switzerland) 2022;12. https://doi.org/10.3390/app12083996.
[4] Chou JH, Wang FK, Lo SC. Predicting future capacity of lithium-ion batteries using transfer learning method. Journal of Energy Storage 2023;71. https://doi.org/10.1016/j.est.2023.108120.
[5] Severson KA, Attia PM, Jin N, Perkins N, Jiang B, Yang Z, et al. Data-driven prediction of battery cycle life before capacity degradation. Nature Energy 2019;4. https://doi.org/10.1038/s41560-019-0356-8.
[6] Song Z, Zhang H, Jia J. Data-Driven State of Health Interval Prediction for Lithium-Ion Batteries. Electronics (Switzerland) 2024;13. https://doi.org/10.3390/electronics13203991.
[7] Wu X, He T, Zhu W, Liao Y. State of health estimation of lithium-ion battery based on automatic feature extraction and BiLSTM-SA. Ionics 2025;31. https://doi.org/10.1007/s11581-025-06681-8.
[8] Islam S, Namkoong G. High-Fidelity SOH Prediction in Lithium-Ion Batteries Using Hybrid ML Networks. Journal of The Electrochemical Society 2025;172. https://doi.org/10.1149/1945-7111/adf35e.
[9] Lin SL. Deep learning-based state of charge estimation for electric vehicle batteries: Overcoming technological bottlenecks. Heliyon 2024;10. https://doi.org/10.1016/j.heliyon.2024.e35780.
[10] Fan Y, Lin Z, Wang F, Zhang J. A hybrid approach for lithium-ion battery remaining useful life prediction using signal decomposition and machine learning. Scientific Reports 2025;15. https://doi.org/10.1038/s41598-025-92262-8.
[11] Bockrath S, Lorentz V, Pruckner M. State of health estimation of lithium-ion batteries with a temporal convolutional neural network using partial load profiles. Applied Energy 2023;329. https://doi.org/10.1016/j.apenergy.2022.120307.
[12] Tianqi YU, Yongxu ZHU, Xianbin W, Delhi N, Gugulothu N, Tv V, et al. Analysis of degradation in residential battery energy storage systems for rate-based use-cases. Applied Energy 2019;PP.
[13] Li W, Lin C, Hosseininasab S, Bauer L, Pischinger S. Lithium-Ion Battery SOH Estimation Based on a Long Short-Term Memory Model Using Short History Data. IEEE Transactions on Power Electronics 2025;40. https://doi.org/10.1109/TPEL.2025.3532839.
[14] Shi Z, Xu J, Ibrahim AW, He Y, Liu S, Zeng L. Accurate state of health estimation based on the multi-feature extracted and improved MHA assisted CNN-BiGRU model for lithium-ion batteries. Journal of Energy Storage 2025;131. https://doi.org/10.1016/j.est.2025.117598.
[15] Ogundana AS, Terala PK, Amarasinghe MY, Xiang X, Foo SY. Electric Vehicle Battery State of Charge Estimation with an Ensemble Algorithm Using Central Difference Kalman Filter (CDKF) and Non-Linear Autoregressive with Exogenous Input (NARX). IEEE Access 2024;12. https://doi.org/10.1109/ACCESS.2024.3371883.
[16] Yang Y, Chen S, Chen T, Huang L. State of Health Assessment of Lithium-ion Batteries Based on Deep Gaussian Process Regression Considering Heterogeneous Features. Journal of Energy Storage 2023;61. https://doi.org/10.1016/j.est.2023.106797.
[17] Wang Z, Liu Y, Wang F, Wang H, Su M. Capacity and remaining useful life prediction for lithium-ion batteries based on sequence decomposition and a deep-learning network. Journal of Energy Storage 2023;72. https://doi.org/10.1016/j.est.2023.108085.
[18] Kim SW, Oh KY, Lee S. Novel informed deep learning-based prognostics framework for on-board health monitoring of lithium-ion batteries. Applied Energy 2022;315. https://doi.org/10.1016/j.apenergy.2022.119011.
[19] Xu J, Liu B, Zhang G, Zhu J. State-of-health estimation for lithium-ion batteries based on partial charging segment and stacking model fusion. Energy Science and Engineering 2023;11. https://doi.org/10.1002/ese3.1338.
[20] Yuan H, Liu J, Zhou Y, Pei H. State of Charge Estimation of Lithium Battery Based on Integrated Kalman Filter Framework and Machine Learning Algorithm. Energies 2023;16. https://doi.org/10.3390/en16052155.
[21] Fei C, Lu Z, Jiang W, Zhao L, Zhang F. Research on Lithium-Ion Battery State of Health Prediction Based on XGBoost–ARIMA Joint Optimization. Batteries 2025;11. https://doi.org/10.3390/batteries11060207.
[22] Alsuwian T, Ansari S, Ammirrul Atiqi Mohd Zainuri M, Ayob A, Hussain A, Hossain Lipu MS, et al. A review of expert hybrid and co-estimation techniques for SOH and RUL estimation in battery management system with electric vehicle application. Expert Systems with Applications 2024;246. https://doi.org/10.1016/j.eswa.2023.123123.
[23] Xiao Z, Jiang B, Zhu J, Wei X, Dai H. State of Health Estimation for Lithium-Ion Batteries Using an Explainable XGBoost Model with Parameter Optimization. Batteries 2024;10. https://doi.org/10.3390/batteries10110394.
[24] Wang D, Bao Y, Shi J. Online lithium-ion battery internal resistance measurement application in state-of-charge estimation using the extended kalman filter. Energies 2017;10. https://doi.org/10.3390/en10091284.
[25] Wang J, Zhang C, Meng X, Zhang L, Li X, Zhang W. A Novel Feature Engineering-Based SOH Estimation Method for Lithium-Ion Battery with Downgraded Laboratory Data. Batteries 2024;10. https://doi.org/10.3390/batteries10040139.
[26] University of Maryland. Center for Advanced Life Cycle Engineering. School of Engineering 2019.
[27] Ali S, Bianchi V, De Munari I. A Microcontroller Based Optimized Framework for the State of Charge Estimation of a Lithium Ion Battery. 2025 IEEE International Workshop on Metrology for Automotive, MetroAutomotive 2025 - Proceedings, 2025. https://doi.org/10.1109/MetroAutomotive64646.2025.11119267.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Advance Sustainable Science Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
