A Review of State-of-Health Estimation and Prediction Methods for Lithium-Ion Traction Batteries in Vehicular Applications: Task Definition, Benchmark Evaluation, and Deployment Challenges

Main Article Content

Haozhe Gao
School of Technology, Beijing Forestry University, Beijing 100083, China

DOI: https://doi.org/10.70267/cai.v3n6.7892

Keywords

lithium-ion traction battery, state-of-health estimation, state-of-health prediction, deep learning, on-board usability, data splitting protocol

Abstract

The state of health (SOH) of traction batteries is a common basis for safety warning, residual value assessment, and second-life utilization of electric vehicles, but a gap exists between the laboratory accuracy of existing deep learning methods and their on-board usability. This paper reviews the relevant research progress using on-board usability as the screening criterion. SOH estimation, SOH prediction, and remaining useful life (RUL) prediction are distinguished according to label source and evaluation protocol, and the limits on the comparability of error values are explained. Existing methods are grouped into six categories by modeling mechanism and evaluated category by category using four on-board questions: input availability, cross-domain generalization validation, uncertainty output, and edge-computing resource constraints. Six models are compared on the CALCE CS2 dataset under random splitting, temporal extrapolation, and cell-level holdout protocols. Under random splitting, the mean absolute errors of all six models do not exceed 0.0150. Under temporal extrapolation, they range from 0.0204 to 0.1392, and the R² values of three neural networks become negative. Under cell-level holdout, they range from 0.0254 to 0.0378. Under the CALCE CS2 dataset and the settings of this paper, protocol selection changes both the error level and the model ranking.

Abstract 62 | PDF Downloads 34

References

  • [1]Ouyang, M. (2021). Innovation and development of new energy vehicles for carbon neutrality. Scientific Chinese, (11), 26-31. (in Chinese)
  • [2]Xiong, R. (2019). Core algorithms of power battery management systems. China Machine Press. (in Chinese)
  • [3]Zhao, X., Li, M., Yu, Q., Ma, J., & Wang, S. (2023). State estimation of power lithium batteries for electric vehicles: A review. China Journal of Highway and Transport, 36(6), 254-283. https://doi.org/10.19721/j.cnki.1001-7372.2023.06.021 (in Chinese)
  • [4]Ye, S., Wang, Y., Pang, T., Wang, K., Liu, Q., Fan, G., & Zhang, X. (2025). A review of safety-oriented intelligent management methods for lithium-ion batteries. Drive System Technique, 39(2), 3-14, 22. (in Chinese)
  • [5]Song, X., Yu, Z., Xiao, Y., Wang, D., Yuan, Q., Li, X., & Zheng, J. (2025). Research progress on the performance changes of lithium-ion batteries after aging. Journal of Jilin University (Engineering and Technology Edition), 55(6), 1817-1833. https://doi.org/10.13229/j.cnki.jdxbgxb.20240763 (in Chinese)
  • [6]Ma, Z., Li, Y., Zhan, Z., Song, Y., Zhang, Z., & Qiu, Z. (2025). A review of state-of-health estimation methods for lithium-ion batteries. Journal of Chongqing University of Technology (Natural Science), 39(12), 1-10. (in Chinese)
  • [7]Hu, X., Guo, Y., & Zhang, R. (2022). Review of state-of-health estimation methods for lithium-ion batteries. Journal of Power Supply, 20(1), 126-133. https://doi.org/10.13234/j.issn.2095-2805.2022.1.126 (in Chinese)
  • [8]Tang, K., Luo, B., Chen, D., Wang, C., Chen, L., Li, F., Cao, Y., & Wang, C. (2025). The State of Health Estimation of Lithium-Ion Batteries: A Review of Health Indicators, Estimation Methods, Development Trends and Challenges. World Electric Vehicle Journal, 16(8), 429. https://doi.org/10.3390/wevj16080429
  • [9]Yao, L., Xu, S., Tang, A., Zhou, F., Hou, J., Xiao, Y., & Fu, Z. (2021). A Review of Lithium-Ion Battery State of Health Estimation and Prediction Methods. World Electric Vehicle Journal, 12(3), 113. https://doi.org/10.3390/wevj12030113
  • [10]Luo, K., Chen, X., Zheng, H., & Shi, Z. (2022). A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries. Journal of Energy Chemistry, 74, 159-173. https://doi.org/10.1016/j.jechem.2022.06.049
  • [11]Noura, N., Boulon, L., & Jemeï, S. (2020). A Review of Battery State of Health Estimation Methods: Hybrid Electric Vehicle Challenges. World Electric Vehicle Journal, 11(4), 66. https://doi.org/10.3390/wevj11040066
  • [12]Wang, Z., Feng, G., Zhen, D., Gu, F., & Ball, A. (2021). A review on online state of charge and state of health estimation for lithium-ion batteries in electric vehicles. Energy Reports, 7, 5141-5161. https://doi.org/10.1016/j.egyr.2021.08.113
  • [13]Xie, Y., Wang, S., Zhang, G., Takyi-Aninakwa, P., Fernandez, C., & Blaabjerg, F. (2024). A review of data-driven whole-life state of health prediction for lithium-ion batteries: Data preprocessing, aging characteristics, algorithms, and future challenges. Journal of Energy Chemistry, 97, 630-649. https://doi.org/10.1016/j.jechem.2024.06.017
  • [14]Yao, J., & Kowal, J. (2025). Towards a smarter battery management system: A critical review on deep learning-based state of charge estimation of lithium-ion batteries. Energy and AI, 21, 100585. https://doi.org/10.1016/j.egyai.2025.100585
  • [15]Alsuwian, T., Ansari, S., Ammirrul Atiqi Mohd Zainuri, M., Ayob, A., Hussain, A., Hossain Lipu, M. S., Alhawari, A. R. H., Almawgani, A. H. M., Almasabi, S., & Taher Hindi, A. (2024). 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, 246, 123123. https://doi.org/10.1016/j.eswa.2023.123123
  • [16]Sui, X., He, S., Vilsen, S. B., Meng, J., Teodorescu, R., & Stroe, D. I. (2021). A review of non-probabilistic machine learning-based state of health estimation techniques for Lithium-ion battery. Applied Energy, 300, 117346. https://doi.org/10.1016/j.apenergy.2021.117346
  • [17]Li, C., Wang, C., Wang, G., Lu, Z., & Ma, C. (2022). Technology of lithium-ion battery state-of-health assessment based on data-driven methods. Electric Power, 55(8), 73-86, 95. https://doi.org/10.11930/j.issn.1004-9649.202202012 (in Chinese)
  • [18]Dai, Y., & Yu, A. (2022). Combined CNN-LSTM and GRU based health feature parameters for lithium-ion battery SOH estimation. Energy Storage Science and Technology, 11(5), 1641-1649. https://doi.org/10.19799/j.cnki.2095-4239.2021.0623 (in Chinese)
  • [19]Li, S., Dauletiyarova, A. B., Zhao, X., Zhang, K., & Jiao, Z. (2026). SOH estimation method for lithium-ion batteries based on partial charging voltage features. Automotive Engineering, 48(1), 113-126. https://doi.org/10.19562/j.chinasae.qcgc.2026.01.011 (in Chinese)
  • [20]Tian, J., Xiong, R., Shen, W., Lu, J., & Sun, F. (2022). Flexible battery state of health and state of charge estimation using partial charging data and deep learning. Energy Storage Materials, 51, 372-381. https://doi.org/10.1016/j.ensm.2022.06.053
  • [21]Yang, B., Liu, S., Feng, X., Rao, Z., Liu, J., & Wu, W. (2025). Thermal state of lithium-ion batteries: Definition, detection, and estimation. Scientia Sinica Technologica, 55(2), 187-212. https://doi.org/10.1360/sst-2024-0124 (in Chinese)
  • [22]Deng, Z., Hu, X., Li, P., Lin, X., & Bian, X. (2022). Data-Driven Battery State of Health Estimation Based on Random Partial Charging Data. IEEE Transactions on Power Electronics, 37(5), 5021-5031. https://doi.org/10.1109/tpel.2021.3134701
  • [23]Hu, J., Fu, P., Wei, Z., Huang, Y., Early, J., Fly, A., & Zhang, Y. (2026). Early prediction of lithium-ion battery degradation with a generative pre-trained transformer. Nature Communications, 17(1), 126. https://doi.org/10.1038/s41467-025-66819-0
  • [24]Zhu, Z., Yang, Q., Liu, X., & Gao, D. (2022). Attention-based CNN-BiLSTM for SOH and RUL estimation of lithium-ion batteries. Journal of Algorithms & Computational Technology, 16, 17483026221130598. https://doi.org/10.1177/17483026221130598
  • [25]Qu, J., Liu, F., Ma, Y., & Fan, J. (2019). A Neural-Network-Based Method for RUL Prediction and SOH Monitoring of Lithium-Ion Battery. IEEE Access, 7, 87178-87191. https://doi.org/10.1109/access.2019.2925468
  • [26]Severson, K. A., Attia, P. M., Jin, N., Perkins, N., Jiang, B., Yang, Z., Chen, M. H., Aykol, M., Herring, P. K., Fraggedakis, D., Bazant, M. Z., Harris, S. J., Chueh, W. C., & Braatz, R. D. (2019). Data-driven prediction of battery cycle life before capacity degradation. Nature Energy, 4(5), 383-391. https://doi.org/10.1038/s41560-019-0356-8
  • [27]Liu, H., Li, C., Hu, X., Li, J., Zhang, K., Xie, Y., Wu, R., & Song, Z. (2025). Multi-modal framework for battery state of health evaluation using open-source electric vehicle data. Nature Communications, 16(1), 1137. https://doi.org/10.1038/s41467-025-56485-7
  • [28]Song, L., Zhang, K., Liang, T., Han, X., & Zhang, Y. (2020). Intelligent state of health estimation for lithium-ion battery pack based on big data analysis. Journal of Energy Storage, 32, 101836. https://doi.org/10.1016/j.est.2020.101836
  • [29]Gong, Q., Wang, P., & Cheng, Z. (2022). An encoder-decoder model based on deep learning for state of health estimation of lithium-ion battery. Journal of Energy Storage, 46, 103804. https://doi.org/10.1016/j.est.2021.103804
  • [30]Zhao, X., Dong, Z., Zhou, H., Lin, H., & Ji, X. (2026). A lithium-ion battery state-of-health prediction network integrating Kolmogorov-Arnold representation theory. Acta Physica Sinica, 75(3), 030809. https://doi.org/10.7498/aps.75.20251359 (in Chinese)
  • [31]Liao, Y., Deng, J., & Hu, Y. (2026). Unified Explicit–Implicit Degradation Dynamics with Physics-Informed Kolmogorov–Arnold Networks for Lithium-Ion Battery SOH Estimation and RUL Prediction Under Different Charging Protocols. Energies, 19(16), 3742. https://doi.org/10.3390/en19163742
  • [32]Liu, Z., Ye, S., Cui, F., & Ma, Y. (2025). Physical Information-Guided Kolmogorov–Arnold Networks for Battery State of Health Estimation. Energies, 18(22), 5865. https://doi.org/10.3390/en18225865
  • [33]Liu, C., Li, H., Li, K., Wu, Y., & Lv, B. (2025). Deep Learning for State of Health Estimation of Lithium-Ion Batteries in Electric Vehicles: A Systematic Review. Energies, 18(6), 1463. https://doi.org/10.3390/en18061463
  • [34]Bockrath, S., Lorentz, V., & Pruckner, M. (2023). State of health estimation of lithium-ion batteries with a temporal convolutional neural network using partial load profiles. Applied Energy, 329, 120307. https://doi.org/10.1016/j.apenergy.2022.120307
  • [35]Xu, Z., Chen, Z., Yang, L., & Zhang, S. (2024). State of health estimation for lithium-ion batteries based on incremental capacity analysis and Transformer modeling. Applied Soft Computing, 165, 112072. https://doi.org/10.1016/j.asoc.2024.112072
  • [36]Xiao, H., He, X., Liang, J., & Li, C. (2022). A lithium battery life-prediction method based on mode decomposition and machine learning. Energy Storage Science and Technology, 11(12), 3999-4009. https://doi.org/10.19799/j.cnki.2095-4239.2022.0341 (in Chinese)
  • [37]Zhang, C., Luo, L., Yang, Z., Du, B., Zhou, Z., Wu, J., & Chen, L. (2024). Flexible method for estimating the state of health of lithium-ion batteries using partial charging segments. Energy, 295, 131009. https://doi.org/10.1016/j.energy.2024.131009
  • [38]Yang, N., Song, Z., Hofmann, H., & Sun, J. (2022). Robust state-of-health estimation of lithium-ion batteries using a convolutional neural network and random forest. Journal of Energy Storage, 48, 103857. https://doi.org/10.1016/j.est.2021.103857
  • [39]Lin, M., Wu, J., Meng, J., et al. (2023). State-of-health estimation with an attentional long short-term memory network for lithium-ion batteries. Energy, 268, 126706. https://doi.org/10.1016/j.energy.2023.126706
  • [40]Tang, A., Jiang, Y., Yu, Q., & Zhang, Z. (2023). A hybrid neural network model with attention mechanism for state-of-health estimation of lithium-ion batteries. Journal of Energy Storage, 68, 107734. https://doi.org/10.1016/j.est.2023.107734
  • [41]Guirguis, J., & Ahmed, R. (2024). Transformer-based deep learning models for state of charge and state of health estimation of Li-ion batteries: A survey study. Energies, 17(14), 3502. https://doi.org/10.3390/en17143502
  • [42]Zhao, H., Chen, Z., Shu, X., Shen, J., Lei, Z., & Zhang, Y. (2023). State of health estimation for lithium-ion batteries based on hybrid attention and deep learning. Reliability Engineering & System Safety, 232, 109066. https://doi.org/10.1016/j.ress.2022.109066
  • [43]Gao, J., Yang, D., Wang, S., Li, Z., Wang, L., & Wang, K. (2023). State of health estimation of lithium-ion batteries based on Mixers-bidirectional temporal convolutional neural network. Journal of Energy Storage, 73, 109248. https://doi.org/10.1016/j.est.2023.109248
  • [44]Wei, Y., & Wu, D. (2023). Prediction of state of health and remaining useful life of lithium-ion batteries using a graph convolutional network with dual attention mechanisms. Reliability Engineering & System Safety, 230, 108947. https://doi.org/10.1016/j.ress.2022.108947
  • [45]Mazzi, Y., Ben Sassi, H., & Errahimi, F. (2024). Lithium-ion battery state of health estimation using a hybrid model based on a convolutional neural network and bidirectional gated recurrent unit. Engineering Applications of Artificial Intelligence, 127, 107199. https://doi.org/10.1016/j.engappai.2023.107199
  • [46]Li, Z., Zhang, X., & Gao, W. (2024). State of health estimation of lithium-ion battery during fast charging process based on BiLSTM-Transformer. Energy, 311, 133418. https://doi.org/10.1016/j.energy.2024.133418
  • [47]He, T., & Gong, Z. (2024). State of health estimation for lithium-ion batteries using a hybrid neural network model with Multi-scale Convolutional Attention Mechanism. Journal of Power Sources, 609, 234680. https://doi.org/10.1016/j.jpowsour.2024.234680
  • [48]Yang, L., He, M., Ren, Y., Gao, B., & Qi, H. (2025). Physics-informed neural network for co-estimation of state of health, remaining useful life, and short-term degradation path in Lithium-ion batteries. Applied Energy, 398, 126427. https://doi.org/10.1016/j.apenergy.2025.126427
  • [49]Tian, A., He, L., Ding, T., Dong, K., Wang, Y., & Jiang, J. (2025). A generic physics-informed neural network framework for lithium-ion batteries state of health estimation. Energy, 332, 137215. https://doi.org/10.1016/j.energy.2025.137215
  • [50]Luo, Y., Ju, S., Li, P., & Zhang, H. (2025). A method for estimating lithium-ion battery state of health based on physics-informed hybrid neural network. Electrochimica Acta, 525, 146110. https://doi.org/10.1016/j.electacta.2025.146110
  • [51]Ye, J., Xie, Q., Lin, M., & Wu, J. (2024). A method for estimating the state of health of lithium-ion batteries based on physics-informed neural network. Energy, 294, 130828. https://doi.org/10.1016/j.energy.2024.130828
  • [52]Hofmann, T., Hamar, J., Rogge, M., Zoerr, C., Erhard, S., & Philipp Schmidt, J. (2023). Physics-Informed Neural Networks for State of Health Estimation in Lithium-Ion Batteries. Journal of The Electrochemical Society, 170(9), 090524. https://doi.org/10.1149/1945-7111/acf0ef
  • [53]Jarraya, I., Ben Atitallah, S., Alahmed, F., Abdelkader, M., Driss, M., Abdelhadi, F., & Koubaa, A. (2025). SOH-KLSTM: A hybrid Kolmogorov-Arnold Network and LSTM model for enhanced Lithium-ion battery Health Monitoring. Journal of Energy Storage, 122, 116541. https://doi.org/10.1016/j.est.2025.116541
  • [54]Lu, J., Xiong, R., Tian, J., Wang, C., & Sun, F. (2023). Deep learning to estimate lithium-ion battery state of health without additional degradation experiments. Nature Communications, 14(1), 2760. https://doi.org/10.1038/s41467-023-38458-w
  • [55]Wang, R., Duan, B., Zhao, G., Shen, J., & Liu, S. (2026). Meta-learning driven small-sample lithium-ion battery state of health estimation based on Kolmogorov–Arnold Network and Long Short-Term Memory Network. Journal of Energy Storage, 163, 122207. https://doi.org/10.1016/j.est.2026.122207
  • [56]Zhang, W., Feng, H., Ren, M., Liu, K., & Yan, G. (2026). LLM-MSIformer: A method for lithium-ion battery state of health estimation based on a large language model and multi-time scale interval transformer. Energy, 342, 139417. https://doi.org/10.1016/j.energy.2025.139417
  • [57]Ding, H., & Yan, S. (2026). Lithium battery state-of-health prediction method combining a Transformer with diffusion. Electrical Measurement & Instrumentation, 63(5), 140-151. https://doi.org/10.19753/j.issn1001-1390.2026.05.015 (in Chinese)
  • [58]Guo, Y., Fan, X., Shi, L., et al. (2026). Large-language-model-driven method for lithium-ion battery SOH prediction. Journal of Harbin Institute of Technology, 58(8), 227-239. (in Chinese)
  • [59]Liang, C., Tao, S., Huang, X., Wang, Y., Xia, B., & Zhang, X. (2025). Stochastic state of health estimation for lithium-ion batteries with automated feature fusion using quantum convolutional neural network. Journal of Energy Chemistry, 106, 205-219. https://doi.org/10.1016/j.jechem.2025.02.030
  • [60]Lin, M., Xiao, P., Meng, J., Wang, W., & Wu, J. (2026). State of Health Estimation for Battery Packs Based on Ensemble Bayesian Neural Networks Integrating Uncertainty Quantification and Calibration. IEEE Transactions on Transportation Electrification, 12(4), 6188-6199. https://doi.org/10.1109/tte.2026.3683737
  • [61]Wang, J. (2025). Research progress and development trends in battery remaining useful life prediction methods. Drive System Technique, 39(4), 52-58. (in Chinese)

Article Sidebar

Full Text
PDF
Information
Copy Publication Information
Published
Nov 5, 2026
Issue
Vol. 3 No. 6 (2026)
Section
Research Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Gao, H. (2026). A Review of State-of-Health Estimation and Prediction Methods for Lithium-Ion Traction Batteries in Vehicular Applications: Task Definition, Benchmark Evaluation, and Deployment Challenges. Computers and Artificial Intelligence, 3(6), 78-92. https://doi.org/10.70267/cai.v3n6.7892