Advanced Battery State-of-Health and Remaining Useful Life Prediction Using Ensemble Machine Learning
Keywords:
Battery health monitoring, Battery Management System (BMS), CatBoost, Ensemble learning, Gradient boosting, LSTM, Machine learning, Neural networks, Predictive maintenance, Random Forest, Real-time prediction, Regression models, Remaining Useful Life (RUL), State of Health (SOH), XGBoostAbstract
Estimates of battery health and a correct forecast of Remaining Useful Life (RUL) play a vital role in the safety, efficiency, and reliability of battery-based systems, including electric vehicles and portable electronics. In this project, two machine learning solutions are proposed based on both regression and ensemble learning models to forecast the State of Health (SOH) and RUL of lithium-ion batteries. Features, including discharge time, cycle index, and SOH, were calculated using the raw battery cycle data through preprocessing to extract more features. Several models, linear regression model, random forest, gradient boosting, XGBoost, CatBoost, and deep neural and network models, such as LSTM models and feed-forward neural networks, have been trained and assessed according to such metrics as MAE, RMSE, and R 2 score. An ensemble voting regressor was used to tame the insight of the individual models to achieve more accuracy. The findings indicate that, as opposed to standalone models, ensemble learning considerably enhances the performance of prediction. It is possible to extrapolate such a system to real-time applications, which are battery management systems that allow early fault and proactive maintenance. Flask/Streamlit was also used to develop a simple user-interactive web-based interface to enable interaction and real-time SOH and RUL prediction.
References
S. C. L, C. Sekhar, N. Chinna Alluraiah, Dhanamjayulu C, Harish Kumar Pujari, and B. Khan, “An overview of remaining useful life prediction of battery using deep learning and ensemble learning algorithms on data‐dependent models,” International Transactions on Electrical Energy Systems, vol. 2025, no. 1, Jan. 2025, doi: https://doi.org/10.1155/etep/2242749
Weidong Huang, Tong Zhou, Jiahuai Ma, and Xiaoyang Chen, “An ensemble model based on fusion of multiple machine learning algorithms for remaining useful life prediction of lithium battery in electric vehicles,” Innovations in Applied Engineering and Technology, pp. 1–12, Mar. 2025, doi: https://doi.org/10.62836/iaet.v4i1.319
V. S. Naresh, P N S Gayathri, P Baby Tejaswi, P Induja, C. R. Reddy, and Y Sai Sudheer, “Optimizing electric vehicle battery health monitoring: A resilient ensemble learning approach for state-of-health prediction,” Sustainable Energy Grids and Networks, pp. 101655–101655, Feb. 2025, doi: https://doi.org/10.1016/j.segan.2025.101655
M. Ahwiadi and W. Wang, “Battery health monitoring and remaining useful life prediction techniques: A review of technologies,” Batteries, vol. 11, no. 1, p. 31, Jan. 2025, doi: https://doi.org/10.3390/batteries11010031
C. C. Daniel, J. Z. Dib, J. Vidal Alonso-Secades, and A. J. López, “Advanced machine learning and deep learning approaches for estimating the remaining life of EV batteries—A review,” Batteries, vol. 11, no. 1, pp. 17–17, Jan. 2025, doi: https://doi.org/10.3390/batteries11010017
Y. Fan, Z. Lin, F. Wang, and J. Zhang, “A hybrid approach for lithium-ion battery remaining useful life prediction using signal decomposition and machine learning,” Scientific Reports, vol. 15, no. 1, Mar. 2025, doi: https://doi.org/10.1038/s41598-025-92262-8
K. Kamişli and İ. Çetin Taş, “Estimation of battery remaining life-time with deep learning methods,” International Journal of New Findings in Engineering, Science and Technology, vol. 3, no. 1, pp. 32–43, Mar. 2025, doi: https://doi.org/10.61150/ijonfest.2025030104
F. Josephin J.S., A. Sonthalia, T. Subramanian, F. Aloui, D. Bhatt, and E. G. Varuvel, “Early prediction of the remaining useful life of lithium‐ion cells using ensemble and non‐ensemble algorithms,” Energy Storage, vol. 7, no. 1, Feb. 2025, doi: https://doi.org/10.1002/est2.70133
C. R. Babu, Thalla Swapna, R. Siva, A. D. Sankar, and B. Naga, “A novel approach for enhancing battery reliability in the market using machine learning-based RUL Prediction,” Springer Proceedings in Business and Economics, pp. 229–244, Jan. 2025, doi: https://doi.org/10.1007/978-981-96-2548-2_12
M. Li et al., “State of health estimation and battery management: A review of health indicators, models and machine learning,” Materials, vol. 18, no. 1, pp. 145–145, Jan. 2025, doi: https://doi.org/10.3390/ma18010145
Santoso, B., Muhlis, D., and Purwanto, R. “Predicting the remaining useful life of lithium-ion batteries for vehicles using machine learning algorithms”. International Journals of Industrial Engineering (IJIE), 1(1), 1-13. Available: https://ecogreenjournals.com/ijie/article/view/26
J. Zhao, X. Qu, Y. Li, J. Nan, and A. F. Burke, “Real-time prediction of battery remaining useful life using hybrid-fusion deep neural networks,”Energy, vol. 328, p. 136618, Aug. 2025, doi: https://doi.org/10.1016/j.energy.2025.136618
M. Lin, L. Ke, J. Meng, W. Wang, J. Wu, and F. Wang, “Health status estimation of lithium-ion battery under arbitrary charging voltage information using ensemble learning framework,” Reliability Engineering & System Safety, pp. 110782–110782, Dec. 2024, doi: https://doi.org/10.1016/j.ress.2024.110782
M. Safitri, T. B. Adji, and A. I. Cahyadi, “Enhanced early prediction of Li-ion battery degradation using multicycle features and an ensemble deep learning model,” Results in Engineering, vol. 25, p. 104235, Feb. 2025, doi: https://doi.org/10.1016/j.rineng.2025.104235
L. Zhou, H. Wang, and S. Xu, “An adaptive multi-scale spatial-temporal graph attention ensemble network with physical guidance for remaining useful life prediction of multi-sensor equipment,” Reliability Engineering & System Safety, pp. 111152–111152, Apr. 2025, doi: https://doi.org/10.1016/j.ress.2025.111152
C. Rincón-Maya, D. Acosta-González, F. Guevara-Carazas, F. Hernández-Barajas, C. Patino-Rodríguez, and O. Usuga-Manco, “Predictive modeling of electric bicycle battery performance: Integrating real-time sensor data and machine learning techniques,” Sensors, vol. 25, no. 5, p. 1392, Feb. 2025, doi: https://doi.org/10.3390/s25051392
T. Hu, X. Zhang, J. Sun, and J. Wang, “Physics-informed deep learning with multi-resolution for ensemble prediction of lithium-ion battery health status,” Measurement Science and Technology, vol. 36, no. 2, p. 025019, Jan. 2025, doi: https://doi.org/10.1088/1361-6501/ada849
D. Zheng, Y. Zhang, X. Guo, Y. Ning, and R. Wei, “Research on the remaining useful life prediction method for lithium-ion batteries based on feature engineering and CNN-BiGRU-AM model,” Ionics, Apr. 2025, doi: https://doi.org/10.1007/s11581-025-06293-2
S. Zhao, D. Sun, Y. Liu, and Y. Liang, “Remaining useful life prediction for lithium-ion batteries based on hybrid ensembles allied with data-driven approach,” Energies, vol. 18, no. 5, pp. 1114–1114, Feb. 2025, doi: https://doi.org/10.3390/en18051114
Y. Li, C. Fu, T. Liu, Z. Hu, and G. Song, “Two-stage remaining useful life prediction method across operating conditions based on small samples and novel health indicators,” Reliability Engineering & System Safety, pp. 111290–111290, May 2025, doi: https://doi.org/10.1016/j.ress.2025.111290
