Uncertainty-Aware Quantile-GBRT Modeling and Robust Optimization of a Hybrid Air–Liquid Battery Thermal Management System

Year 2026, Volume: 13 Issue: 1 , 242 - 268 , 31.03.2026

Merve Akkuş , Ferhat Akkuş

https://doi.org/10.54287/gujsa.1831336

https://izlik.org/JA92DN93KF

Abstract

In recent years, with the advancement of technology and industry, electric vehicles have become widely used. These vehicles have evolved with the goals of environmental sustainability and energy efficiency, increasing demand for lithium-ion battery technologies that offer high energy density and long life. In this study, the maximum temperature and temperature increase of a lithium-ion battery module in a 4-series 3-parallel configuration were analyzed using experimental air and hybrid (air+water) battery thermal management system (BTMS) data with an artificial intelligence-based uncertainty modeling approach. Going beyond traditional deterministic regressions, quantile-based GBRT models were applied, and q10–q50–q90 probability bands were created for each experimental configuration. Thus, the system's temperature behavior was evaluated not only through average predictions but also with uncertainty intervals. Robust Pareto optimization conducted under the condition q90(Tmax) ≤ 30°C revealed safe design points that minimize both maximum temperature and temperature difference. The Pareto analysis determined the optimal region to be around q90(Tmax) ≈ 28.8°C and q90(ΔT) ≈ 2.1°C; even in this case, the temperature difference remained below 2.5°C. Explainable artificial intelligence tools such as SHAP and PDP analyses showed that air and refrigerant flow rates play a dominant role in the temperature response, and that hybrid cooling provides a significant improvement in both Tmax and ΔT values compared to air cooling. In conclusion, the study presents an uncertainty-aware and data-driven BTMS design framework that integrates quantile modeling, robust optimization, and explainable artificial intelligence approaches, contributing to the development of safe and efficient electric vehicle battery systems.

Keywords

Battery Thermal Management Systems , Hybrit Cooling , Uncertainty-Aware Modeling , Gradient Boosting Regressor , Robust Optimization

References

• Acar, E., Jain, N., Ramu, P., Hwang, C., & Lee, I. (2024). A survey on design optimization of battery electric vehicle components, systems, and management. Structural and Multidisciplinary Optimization. https://doi.org/10.1007/s00158-024-03737-7
• Ait Mouloud, L., Kheldoun, A., Oussidhoum, S., Alharbi, H., Alotaibi, S., Alzahrani, T., & Agajie, T. F. (2025). Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-12797-8
• Akkuş, F., & Işık, M. Z. (2023). Elektrikli araçlarda kullanılan lityum iyon bataryaların hava, sıvı ve ısı borulu termal yönetim sistemlerinin incelenmesi. Batman Üniversitesi Yaşam Bilimleri Dergisi, 13(2), 36–54. https://doi.org/10.55024/buyasambid.1339607
• Alcántara, A., Galván, I. M., & Aler, R. (2023). Deep neural networks for the quantile estimation of regional renewable energy production. Applied Intelligence, 53(7), 8318–8353. https://doi.org/10.1007/s10489-022-03958-7
• Alcibar, J., Aizpurua, J. I., Zugasti, E., & Peñagarikano, O. (2025). A hybrid probabilistic battery health management approach for robust inspection drone operations. Engineering Applications of Artificial Intelligence, 146, 110246. https://doi.org/10.1016/j.engappai.2025.110246
• Billert, A. M., Erschen, S., Frey, M., & Gauterin, F. (2022). Predictive battery thermal management using quantile convolutional neural networks. Transportation Engineering, 10, 100150. https://doi.org/10.1016/j.treng.2022.100150
• Fu, Z., Zhang, J., & Peng, Q. (2022). Robust design for the cooling performance of the battery pack fire extinguishing system. In Proceedings of CAD Conference (pp. 107–112). https://doi.org/10.14733/cadconfP.2022.107-112
• Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024). Interpreting black-box models: A review on explainable artificial intelligence. Cognitive Computation. https://doi.org/10.1007/s12559-023-10179-8
• Khiari, J., & Olaverri-Monreal, C. (2022). Uncertainty-aware prediction of battery energy consumption for hybrid electric vehicles. In Proceedings of the IEEE Intelligent Vehicles Symposium (pp. 1005–1010). https://doi.org/10.1109/IV51971.2022.9827458
• Kisomi, M. K. (2022). Thermal management of lithium-ion batteries: A comparative study of phase change materials and air-cooling systems equipped with fins (MSc Thesis).
• Kim, J., Yoo, Y. S., Yang, H. S., & Choi, H. S. (2024). Robust uncertainty-aware control of energy storage systems using biased renewable energy forecast. Applied Energy, 367, 123309. https://doi.org/10.1016/j.apenergy.2024.123309
• Li, S., Zhang, C., Zhao, Y., Offer, G. J., & Marinescu, M. (2023). Effect of thermal gradients on inhomogeneous degradation in lithium-ion batteries. Communications Engineering, 2(1). https://doi.org/10.1038/s44172-023-00124-w
• Li, W., Wang, N., Garg, A., & Gao, L. (2023). Multi-objective optimization of an air cooling battery thermal management system considering battery degradation and parasitic power loss. Journal of Energy Storage, 58, 106382. https://doi.org/10.1016/j.est.2022.106382
• Liang, B., Liu, H., Cressey, E. L., Xu, C., Shi, L., Wang, L., Dai, J., Wang, Z., & Wang, J. (2023). Uncertainty of partial dependence relationship between climate and vegetation growth calculated by machine learning models. Remote Sensing, 15(11), 2920. https://doi.org/10.3390/rs15112920
• Liu, S., Wang, Y., Liu, Q., Panchal, S., Zhao, J., Fowler, M., Fraser, R., & Yuan, J. (2024). Thermal equalization design for the battery energy storage system (BESS) of a fully electric ship. Energy, 312, 133611. https://doi.org/10.1016/j.energy.2024.133611
• Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. http://arxiv.org/abs/1705.07874
• Molnar, C., Casalicchio, G., & Bischl, B. (2020). Interpretable machine learning: A brief history, state-of-the-art and challenges. In Explainable AI. Springer. https://doi.org/10.1007/978-3-030-65965-3_28
• Pirotta, M., Parisi, S., & Restelli, M. (2014). Multi-objective reinforcement learning with continuous Pareto frontier approximation. http://arxiv.org/abs/1406.3497
• Ponce‐Bobadilla, A. V., Schmitt, V., Maier, C. S., Mensing, S., & Stodtmann, S. (2024). Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development. Clinical and Translational Science, 17(11). https://doi.org/10.1111/cts.70056
• Sarıkurt, T., & Balıkçı, A. (2018). Elektrikli araç uygulamalarında kullanılan lityum bataryalar için göreceli kapasite tahmin yöntemi. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 24(5), 809–816.
• Sukkam, N., Katongtung, T., Suttakul, P., Mona, Y., Achariyaviriya, W., Tippayawong, K. Y., & Tippayawong, N. (2024). Machine learning prediction of a battery’s thermal-related health factor in a battery electric vehicle using real-world driving data. Information, 15(9), 553. https://doi.org/10.3390/info15090553
• Tai, L. D., & Lee, M. Y. (2025). Advances in the battery thermal management systems of electric vehicles for thermal runaway prevention and suppression. Batteries. https://doi.org/10.3390/batteries11060216
• Wu, S., Li, D., Xing, W., & Liu, Y. (2025). Quantitative prediction model for lithium-ion battery life uncertainty based on DAE-CNN-BiGRU quantile regression. Journal of Energy Storage, 123, 116771. https://doi.org/10.1016/j.est.2025.116771
• Xu, L., Wang, S., Xi, L., Li, Y., & Gao, J. (2024). A review of thermal management and heat transfer of lithium-ion batteries. Energies, 17(16). https://doi.org/10.3390/en17163873
• Yang, T., Liu, H., Zhang, W., Ding, A., & Wu, M. (2025). Multi-objective topology optimization of the cooling plate for battery thermal management. Batteries, 11(11), 406. https://doi.org/10.3390/batteries11110406
• Ye, L., Li, C., Wang, C., Zheng, J., Zhong, K., & Wu, T. (2024). A multi-objective optimization approach for battery thermal management system based on BP neural network prediction and NSGA-II algorithm. Journal of Energy Storage, 99, 113212. https://doi.org/10.1016/j.est.2024.113212
• Zhang, Q., Cao, G., & Zhang, X. (2023). Study of wet cooling flat heat pipe for battery thermal management application. Applied Thermal Engineering, 219, 119407. https://doi.org/10.1016/j.applthermaleng.2022.119407
• Zhang, Z., & Jung, C. (2019). GBDT-MO: Gradient boosted decision trees for multiple outputs. arXiv. http://arxiv.org/abs/1909.04373
• Zhang, Y., Tian, J., Guo, Z., Fu, Q., & Jing, S. (2025). Uncertainty-Aware Economic Dispatch of Integrated Energy Systems with Demand-Response and Carbon-Emission Costs. Processes, 13(6). https://doi.org/10.3390/pr13061906
• Zhou, X., Guo, W., Shi, X., She, C., Zheng, Z., Zhou, J., & Zhu, Y. (2024). Machine learning assisted multi-objective design optimization for battery thermal management system. Applied Thermal Engineering, 253, 123826. https://doi.org/10.1016/j.applthermaleng.2024.123826