A COMPARATIVE STUDY OF MACHINE LEARNING MODELS FOR BATTERY STATE-OF-HEALTH PREDICTION: XGBOOST, RANDOM FOREST AND DEEP LEARNING

Details

Hits: 72

Volume 8, Article e2026.04, 2026, Pages 1-8

Turker Tuncer¹, Sengul Dogan¹ and Rashid Aliyev²

¹Department of Digital Forensics Engineering, College of Technology, Firat University, Türkiye, Elazig, This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it.,

² Azerbaijan State Oil and Industry University, Azerbaijan, Baku, This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Accurate State-of-Health (SoH) estimation is critical for ensuring the safety, reliability, and longevity of lithium-ion batteries in electric vehicles (EVs). This study presents a comprehensive comparative analysis of three machine learning approaches — XGBoost, Random Forest, and Deep Learning (LSTM-based) — applied to real-world EV battery datasets for SoH prediction. Features extracted from electrochemical measurements including voltage, current, temperature, capacity fade, and impedance data are used as model inputs. Performance is evaluated using RMSE, MAE, and R² metrics under both static and dynamic load conditions. Results indicate that the LSTM model achieves the highest accuracy (RMSE = 0.81%) under dynamic conditions, while XGBoost demonstrates superior computational efficiency with competitive accuracy (RMSE = 1.04%). Random Forest provides strong baseline performance and interpretability. These findings offer practical guidelines for selecting appropriate ML models for onboard battery management systems (BMS) in EVs.

Keywords:

State of Health, Lithium-Ion Battery, XGBoost, Random Forest, LSTM, Electric Vehicle, Battery Management System, Machine Learning

DOI: doi.org/10.32010/26166127.2026.04

Reference 

Aliev, A. R., Ismayilova, N. T., & Ismayilov, E. A. (2023). Use of machine learning methods for analysis of factors affecting ICT contribution to different countries development. In International Conference on Theory and Applications of Fuzzy Systems and Soft Computing. Springer

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of KDD 2016 (pp. 785–794).

Dubarry, M., Truchot, C., & Liaw, B. Y. (2012). Synthesize battery degradation modes via a diagnostic and prognostic model. Journal of Power Sources, 219, 204–216.

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.

Hu, X., Xu, L., Lin, X., & Pecht, M. (2020). Battery lifetime prognostics. Joule, 4(2), 310–346.

Ismayilov, E., & Mammadova, N. (2024). Optimizing deep learning model training with cyclic data parallelism: A distributed computing approach. In International Conference on Data Science and Management (pp. 209–216).

Lipu, M. S. H., et al. (2018). A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations. Journal of Cleaner Production, 205, 115–133.

Lu, L., Han, X., Li, J., Hua, J., & Ouyang, M. (2013). A review on the key issues for lithium-ion battery management in electric vehicles. Journal of Power Sources, 226, 272–288.

Patil, M. A., Tagade, P., Hariharan, K. S., Kolake, S. M., Song, T., Yeo, T., & Doo, S. (2015). A novel multistage support vector machine based approach for Li-ion battery remaining useful life estimation. Applied Energy, 159, 285–297.

Richardson, R. R., Osborne, M. A., & Howey, D. A. (2017). Gaussian process regression for forecasting battery state of health. Journal of Power Sources, 357, 209–219.

Saha, B., & Goebel, K. (2007). Battery data set. NASA Prognostics Center of Excellence Data Set Repository.

Saha, B., Goebel, K., Poll, S., & Christophersen, J. (2009). Prognostics methods for battery health monitoring using a Bayesian framework. IEEE Transactions on Instrumentation and Measurement, 58(2), 291–296.

Severson, K. A., et al. (2019). Data-driven prediction of battery cycle life before capacity degradation. Nature Energy, 4(5), 383–391.

Shen, S., Sadoughi, M., Li, M., Wang, Z., & Hu, C. (2020). Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries. Applied Energy, 260, Article 114296.

Vetter, J., et al. (2005). Ageing mechanisms in lithium-ion batteries. Journal of Power Sources, 147(1–2), 269–281.

Zhang, Y., Xiong, R., He, H., & Pecht, M. G. (2018). Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries. IEEE Transactions on Vehicular Technology, 67(7), 5695–5705.