Deep Learning-Based State-of-Health Estimation and Thermal-Aware Battery Management for Electric Vehicle Applications

Author

Dinesh Kumar Saini, Bharat Bhushan Jain

Abstract

 State of Health (SoH) estimation and thermal management are the two long-horizon pillars of an electric-vehicle (EV) Battery Management System (BMS), governing warranty planning, safety margins and end-of-life scheduling. This paper evaluates Deep Neural Network (DNN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) architectures for SoH estimation of lithium-ion cells, using capacity-fade trajectories from the NASA Ames battery ageing dataset (cells B0005-B0007) as ground truth, and situates the estimation task within an integrated thermal-management framework that couples heat-generation modelling with AI-driven risk prediction. Across the four architectures, DNN achieved the lowest SoH estimation error (RMSE = 0.0275), correctly capturing both the slow initial degradation phase and the accelerated capacity fade in later cycles; CNN achieved moderate accuracy (RMSE = 0.055) but over-smoothed cycle-to-cycle fluctuations; LSTM showed the highest error (RMSE = 0.088) due to cumulative drift over long discharge sequences; and XGBoost achieved a lightweight, competitive baseline (expected RMSE in the 0.04-0.05 range). A unified comparison across both SoC and SoH tasks shows that no single architecture dominates both problems: CNN excels at the short-timescale SoC task while DNN is preferable for the long-horizon SoH task, motivating a dual-track or ensemble deployment strategy. The paper further reviews thermal-runaway risk factors in Li-ion cells and discusses how AI-based temperature prediction can be integrated with SoH estimation to support proactive charging-policy adjustment and warranty-relevant degradation forecasting in next-generation EV battery-management systems.

Keywords

State of Health; Battery Degradation; Thermal Management; Electric Vehicle; Deep Neural Network; LSTM; XGBoost; Battery Management System

Full Text:

Download Paper PDF

References

[1] M. A. Hannan, M. S. H. Lipu, A. Hussain, and A. Mohamed, "A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: challenges and recommendations," Renewable and Sustainable Energy Reviews, vol. 78, pp. 834–854, 2017.

[2] B. Saha and K. Goebel, "Battery Data Set," NASA Ames Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA, 2007.

[3] H. Chaoui and C. C. Ibe-Ekeocha, "State of charge and state of health estimation for lithium batteries using recurrent neural networks," IEEE Transactions on Vehicular Technology, vol. 66, no. 10, pp. 8773–8783, 2017.

[4] Z. Ren, C. Du, and Y. Zhao, "A Novel Method for State of Health Estimation of Lithium-Ion Batteries Based on Deep Learning Neural Network and Transfer Learning," Batteries, vol. 9, no. 12, p. 585, 2023.

[5] Y. Xiao, J. Wen, L. Yao, J. Zheng, Z. Fang, and Y. Shen, "A comprehensive review of the lithium-ion battery state of health prognosis methods combining aging mechanism analysis," Journal of Energy Storage, vol. 65, p. 107347, 2023.

[6] M. Kurucan, M. Özbaltan, Z. Yetgin, and A. Alkaya, "Applications of artificial neural network based battery management systems: A literature review," Renewable and Sustainable Energy Reviews, vol. 192, p. 114262, 2024.

[7] T. Bai and H. Wang, "Convolutional transformer-based multiview information perception framework for lithium-ion battery state-of-health estimation," IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–12, 2023.

[8] Z. Wei, X. Sun, J. Wang, W. Liu, C. Rong, and C. Liu, "State of health estimation of lithium-ion batteries based on multihealth features fusion and improved group method of data handling," IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–15, 2024.

[9] T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.

[10] M. M. Haq, I. N. Haq, and J. Pradipta, "State-Of-Health Estimation for Lithium-Ion Batteries Using Supervised Machine Learning: XGBoost," ITB Graduate School Conference, vol. 4, no. 1, 2025.

[11] P. Venugopal and V. T., "State-of-Health Estimation of Li-ion Batteries in Electric Vehicle Using IndRNN under Variable Load Condition," Energies, vol. 12, no. 22, p. 4338, 2019.

[12] D. Zhou, Z. Li, J. Zhu, H. Zhang, and L. Hou, "State of health monitoring and remaining useful life prediction of lithium-ion batteries based on temporal convolutional network," IEEE Access, vol. 8, pp. 53307–53320, 2020.

[13] S. Khaleghi, D. Karimi, S. H. Beheshti, M. S. Hosen, H. Behi, M. Berecibar, and J. Van Mierlo, "Online health diagnosis of lithium-ion batteries based on nonlinear autoregressive neural network," Applied Energy, vol. 282, p. 116159, 2021.

[14] Y. Nandakishora, N. Khayum, C. Patra, P. Kumar, A. Sharma, and A. K. Ansu, "AI driven approaches in battery thermal management systems for prediction and multi objective optimization: a comprehensive literature review," Discover Mechanical Engineering, vol. 5, art. 53, 2026.

[15] J. Kim, J. Oh, and H. Lee, "Review on battery thermal management system for electric vehicles," Applied Thermal Engineering, vol. 149, pp. 192–212, 2019.

[16] M. Ghalkhani and S. Habibi, "Review of the Li-Ion Battery, Thermal Management, and AI-Based Battery Management System for EV Application," Energies, vol. 16, no. 1, p. 185, 2022.

[17] S. Shen, M. Sadoughi, X. Chen, M. Hong, and C. Hu, "A deep learning method for online capacity estimation of lithium-ion batteries," Journal of Energy Storage, vol. 25, p. 100817, 2019.

[18] S. Shen, M. Sadoughi, M. Li, Z. Wang, and C. Hu, "Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries," Applied Energy, vol. 260, p. 114296, 2020.

[19] J. Wei, G. Dong, and Z. Chen, "Remaining useful life prediction and state of health diagnosis for lithium-ion batteries using particle filter and support vector regression," IEEE Transactions on Industrial Electronics, vol. 65, no. 7, pp. 5634–5643, 2018.

[20] K. A. Severson, P. M. Attia, N. Jin, N. Perkins, B. Jiang, Z. Yang, M. H. Chen, M. Aykol, P. K. Herring, D. Fraggedakis, et al., "Data-driven prediction of battery cycle life before capacity degradation," Nature Energy, vol. 4, no. 5, pp. 383–391, 2019.