Strategic assessment of lithium-ion battery degradation: a data-driven optimization approach
-
Lijuan Wang
und
Zhengyang Wang
Abstract
The performance and lifespan of energy storage systems, including those used for renewable energy storage and electric vehicles, are significantly hampered by the capacity degradation of lithium-ion batteries. For the best battery management, lowest associated maintenance costs, and longest battery life, an accurate estimation of this degradation is required. In this study, in order to improve performance through hyperparameter tuning, the Lichtenberg Optimization Algorithm (LOA) is used to estimate the capacity degradation of lithium-ion batteries using machine learning (ML) techniques. To choose the best, the different ML models were compared using various performance metrics. Among the models, the LOA-XGBoost with the highest values of R2 (0.9384) and lowest values of MAE (0.0163), MSE (0.0041), RMSE (0.0640), and ME (0.8709) on testing database is the most efficient. The sensitivity analysis also demonstrated that environmental factors, such as the temperature of ambient and battery identification features like battery ID and test ID, contributed the most to degradation, while charge transfer resistance (Rct), traceable database reference (UID), and internal resistance (Re) contributed the least. This study shows how new optimization techniques, such as the Lichtenberg Optimization Algorithm, can be used to improve machine learning models and estimate battery capacity degradation more precisely.
Funding source: Henan College of Transportation 2024 College-Level Scientific Research Projects
Acknowledgments
Henan College of Transportation 2024 College-Level Scientific Research Projects 2024-ZDXM-021 Research and Practice on the New-Format E-Textbook Intelligent Connected Whole Vehicle Testing Technology.
-
Research ethics: Research involving Human Participants and Animals: The observational study conducted on medical staff needs no ethical code. Therefore, the above study was not required to acquire ethical code.
-
Informed consent: This option is not neccessary due to that the data were collected from the references.
-
Author contributions: All authors contributed to the study’s conception and design. Data collection, simulation and analysis were performed by “Lijuan Wang and Zhengyang Wang”. Also, the first draft of the manuscript was written by Lijuan Wang. Zhengyang Wang commented on previous versions of the manuscript.
-
Use of Large Language Models, AI and Machine Learning Tools: During the preparation of this work, the authors used Large Language Models, AI, and Machine Learning tools for tasks such as language refinement, data analysis, or figure generation, with all outputs being reviewed and validated by the authors to ensure accuracy and originality. After using these tools/services, the authors reviewed and edited the content and take full responsibility for the content of the published article.
-
Conflict of interest: The authors declare no competing of interests.
-
Research funding: This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.
-
Data availability: The authors do not have permissions to share data.
Nomenclature
- CatBoost
-
Categorical boosting
- CCM
-
Coulomb counting method
- EFB
-
Exclusive feature bundling
- EV
-
Electric vehicles
- GB
-
Gradient boosting
- GOSS
-
Gradient-based one-sided sampling
- HGB
-
Histogram gradient boosting
- ID
-
Identifier
- IQR
-
Interquartile range
- LIB
-
Lithium-ion battery
- LighGBM
-
Light gradient boosting machine
- LOA
-
Lichtenberg optimization algorithm
- MAE
-
Mean absolute error
- ME
-
Maximum error
- ML
-
Machine learning
- MSE
-
Mean squared error
- R2
-
Coefficient of determination
- Rct
-
Charge transfer resistance
- Re
-
Internal resistance
- RF
-
Random forest
- RMSE
-
Root mean squared error
- SOC
-
State of charge
- XGBoost
-
Extreme gradient boosting
References
1. Wang, S, Fan, Y, Jin, S, Takyi-Aninakwa, P, Fernandez, C. Improved anti-noise adaptive long short-term memory neural network modeling for the robust remaining useful life prediction of lithium-ion batteries. Reliab Eng Syst Saf 2023;230:108920. https://doi.org/10.1016/j.ress.2022.108920.Suche in Google Scholar
2. Chandran, V, Patil, CK, Karthick, A, Ganeshaperumal, D, Rahim, R, Ghosh, A. State of charge estimation of lithium-ion battery for electric vehicles using machine learning algorithms. World Elec Veh J 2021;12:38. https://doi.org/10.3390/wevj12010038.Suche in Google Scholar
3. Hannan, MA, Lipu, MSH, Hussain, A, Ker, PJ, Mahlia, TMI, Mansor, M, et al.. Toward enhanced state of charge estimation of lithium-ion batteries using optimized machine learning techniques. Sci Rep 2020;10:4687. https://doi.org/10.1038/s41598-020-61464-7.Suche in Google Scholar PubMed PubMed Central
4. Jafari, S, Yang, J-H, Byun, Y-C. Optimized XGBoost modeling for accurate battery capacity degradation prediction. Results Eng 2024;24:102786. https://doi.org/10.1016/j.rineng.2024.102786.Suche in Google Scholar
5. Sepasiahooyi, S, Abdollahi, F. Fault detection of new and aged lithium-ion battery cells in electric vehicles. Green Energy and Intell Transport 2024:100165. https://doi.org/10.1016/j.geits.2024.100165.Suche in Google Scholar
6. Talluri, MT, Murugesan, S, Karthikeyan, V, Pragaspathy, S. The capacity estimation of Li–Ion battery using ML-based hybrid model. Electr Eng 2025;107:1695–705. https://doi.org/10.1007/s00202-024-02608-0.Suche in Google Scholar
7. Barcellona, S, Codecasa, L, Colnago, S, Cannelli, L, Laurano, C, Maroni, G. Capacity estimation of Lithium-ion batteries through a machine learning approach. Math Comput Simul 2026;239:391–402. https://doi.org/10.1016/j.matcom.2025.05.022.Suche in Google Scholar
8. Xue, Q, Li, J, Xu, P. Machine learning based swift online capacity prediction of lithium-ion battery through whole cycle life. Energy 2022;261:125210. https://doi.org/10.1016/j.energy.2022.125210.Suche in Google Scholar
9. Chemali, E, Kollmeyer, PJ, Preindl, M, Emadi, A. State-of-charge estimation of Li-ion batteries using deep neural networks: a machine learning approach. J Power Sources 2018;400:242–55. https://doi.org/10.1016/j.jpowsour.2018.06.104.Suche in Google Scholar
10. Li, W, Limoge, DW, Zhang, J, Sauer, DU, Annaswamy, AM. Estimation of potentials in lithium-ion batteries using machine learning models. IEEE Trans Control Syst Technol 2021;30:680–95. https://doi.org/10.1109/tcst.2021.3071643.Suche in Google Scholar
11. Korkmaz, M. SoC estimation of lithium-ion batteries based on machine learning techniques: a filtered approach. J Energy Storage 2023;72:108268. https://doi.org/10.1016/j.est.2023.108268.Suche in Google Scholar
12. Zhang, C, Tu, L, Yang, Z, Du, B, Zhou, Z, Wu, J, et al.. A CMMOG-based lithium-battery SOH estimation method using multi-task learning framework. J Energy Storage 2025;107:114884. https://doi.org/10.1016/j.est.2024.114884.Suche in Google Scholar
13. Chen, L, Xie, S, Lopes, AM, Li, H, Bao, X, Zhang, C, et al.. A new SOH estimation method for lithium-ion batteries based on model-data-fusion. Energy 2024;286:129597. https://doi.org/10.1016/j.energy.2023.129597.Suche in Google Scholar
14. Liu, G, Deng, Z, Xu, Y, Lai, L, Gong, G, Tong, L, et al.. Lithium-ion battery state of health estimation based on CNN-LSTM-Attention-FVIM algorithm and fusion of multiple health features. Appl Sci 2025;15:7555. https://doi.org/10.3390/app15137555.Suche in Google Scholar
15. Nie, P, Roccotelli, M, Fanti, MP, Ming, Z, Li, Z. Prediction of home energy consumption based on gradient boosting regression tree. Energy Rep 2021;7:1246–55. https://doi.org/10.1016/j.egyr.2021.02.006.Suche in Google Scholar
16. Singh, U, Rizwan, M, Alaraj, M, Alsaidan, I. A machine learning-based gradient boosting regression approach for wind power production forecasting: a step towards smart grid environments. Energies (Basel) 2021;14:5196. https://doi.org/10.3390/en14165196.Suche in Google Scholar
17. Toharudin, T, Caraka, RE, Pratiwi, IR, Kim, Y, Gio, PU, Sakti, AD, et al.. Boosting algorithm to handle unbalanced classification of PM 2.5 concentration levels by observing meteorological parameters in Jakarta-Indonesia using AdaBoost, XGBoost, CatBoost, and LightGBM. IEEE Access 2023;11:35680–96. https://doi.org/10.1109/access.2023.3265019.Suche in Google Scholar
18. Hancock, JT, Khoshgoftaar, TM. CatBoost for big data: an interdisciplinary review. J Big Data 2020;7:94. https://doi.org/10.1186/s40537-020-00369-8.Suche in Google Scholar PubMed PubMed Central
19. Liang, J, Bu, Y, Tan, K, Pan, J, Yi, Z, Kong, X, et al.. Estimation of stellar atmospheric parameters with light gradient boosting machine algorithm and principal component analysis. Astron J 2022;163:153. https://doi.org/10.3847/1538-3881/ac4d97.Suche in Google Scholar
20. Deng, S, Su, J, Zhu, Y, Yu, Y, Xiao, C. Forecasting carbon price trends based on an interpretable light gradient boosting machine and Bayesian optimization. Expert Syst Appl 2024;242:122502. https://doi.org/10.1016/j.eswa.2023.122502.Suche in Google Scholar
21. Le, NK, Liu, Y, Nguyen, QM, Liu, Q, Liu, F, Cai, Q, et al.. Fedxgboost: privacy-preserving xgboost for federated learning. arXiv preprint arXiv:2106.10662, 2021.Suche in Google Scholar
22. Amjad, M, Ahmad, I, Ahmad, M, Wróblewski, P, Kamiński, P, Amjad, U. Prediction of pile bearing capacity using XGBoost algorithm: modeling and performance evaluation. Appl Sci 2022;12:2126. https://doi.org/10.3390/app12042126.Suche in Google Scholar
23. Biau, G. Analysis of a random forests model. J Mach Learn Res 2012;13:1063–95.Suche in Google Scholar
24. El Mrabet, Z, Sugunaraj, N, Ranganathan, P, Abhyankar, S. Random forest regressor-based approach for detecting fault location and duration in power systems. Sensors 2022;22:1–19. https://doi.org/10.3390/s22020458.Suche in Google Scholar PubMed PubMed Central
25. Li, S. Estimating stock market prices with histogram-based gradient boosting regressor: a case study on alphabet inc; 2024. Available from: www.ijacsa.thesai.org.10.14569/IJACSA.2024.0150553Suche in Google Scholar
26. Nhat-Duc, H, Van-Duc, T. Comparison of histogram-based gradient boosting classification machine, random forest, and deep convolutional neural network for pavement raveling severity classification. Autom Constr 2023;148:104767. https://doi.org/10.1016/j.autcon.2023.104767.Suche in Google Scholar
27. Pereira, JLJ, Francisco, MB, Diniz, CA, Oliver, GA, Cunha, SSJr, Gomes, GF. Lichtenberg algorithm: a novel hybrid physics-based meta-heuristic for global optimization. Expert Syst Appl 2021;170:114522. https://doi.org/10.1016/j.eswa.2020.114522.Suche in Google Scholar
28. Pereira, JLJ, Francisco, MB, da Cunha, SSJr, Gomes, GF. A powerful lichtenberg optimization algorithm: a damage identification case study. Eng Appl Artif Intell 2021;97:104055.10.1016/j.engappai.2020.104055Suche in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
