A Comprehensive Review of Thermal Runaway Detection, Prognostics, and Intelligent Safety Management for Lithium-Ion Batteries

Abstract

Lithium-ion battery technology is the most common energy storage technology for electric vehicles, portable electronics and energy storage systems. The electrochemical performance, long-cycle life, and high energy density make them ideal. The widespread use of high energy battery systems, however, raises the concern of the risk of thermal runaway (TR), which is one of the most significant safety challenges in the case of LIBs. A thermal runaway is an electrochemical chain reaction. They generate heat in a rapid manner, create toxic gases, spread a fire and eventually fire hazard. The conventional battery management system mainly relies on the voltage and temperature monitoring based on a threshold. This hardly gives any prior warning before catastrophic failure. Recently, the battery safety diagnosis and prognosis have been greatly implemented using various sensing technologies, machine learning, hybrid physics-informed modelling, and digital twin frameworks. The aim of this review article is to present early thermal runaway detection and prognostic safety management research in lithium-ion battery system. In the start of the article we have explained key mechanisms for thermal runaway initiation and propagation which are self-heating reactions, internal short circuits (ISC), thermal criticality, abuse condition and fire hazards. This review contains a brief summary of the Li-ion battery and the lithium-ion battery failure mechanisms. The next diagnostic techniques are analysed, electron microscopy, spectroscopy, scattering and X-ray, neutron and magnetic resonance imaging. A systematic review of early-warning signals and sensing technologies follows which includes voltage and current anomalies, embedded temperature sensing, gas evolution sensing, swelling, and force sensing, fibre-optic sensing, multimodal sensor fusion strategies. The review evaluates AI and ML modelling strategies for prognosis acceleration and uses such as conventional ML, deep learning, hybrid AI–physics, transfer learning and digital twin-enabled diagnosis. The final assessment addresses smart battery designs, IoT-enabled oversight, intelligent thermal management frameworks, and upcoming battery safety systems. The future of battery safety systems will be increasingly sophisticated, with safety measures evolving from passive threshold-based protection to intelligent, self-adaptive, and prognostic safety systems capable of predicting runaway initiation conditions with sufficient warnings. Emerging developments in embedded multidimensional sensing, uncertainty-aware machine learning, digital twins, and state-of-safety methodologies are expected to play a central role in next-generation EV battery safety systems.

Introduction

Lithium-ion batteries (LIBs) are widely used in electric vehicles and energy storage due to their high energy density and long cycle life, but they pose serious safety risks, especially thermal runaway—a self-accelerating reaction where internal heat builds up faster than it can be dissipated, potentially leading to fire, explosion, and toxic gas release. The text explains that thermal runaway is a complex, multi-stage process involving electrochemical, thermal, and mechanical reactions, and can be triggered by thermal, electrical (overcharge/over-discharge), or mechanical abuse (impact, crushing, penetration). Once initiated, it can propagate across battery packs, making large-scale fires in EVs and storage systems particularly dangerous.

To improve safety, researchers are developing early-warning systems that go beyond traditional voltage and surface temperature monitoring, which often fail to detect internal degradation in time. Advanced approaches include embedded temperature sensors, gas sensing, strain and pressure monitoring, and multimodal sensor fusion, which provide earlier and more accurate detection of failure conditions. In parallel, artificial intelligence and machine learning—along with physics-informed models and digital twins—are increasingly used for battery prognostics and fault diagnosis.

The review highlights that while many studies focus separately on sensing methods or AI-based prediction, there is still a gap in integrated systems that combine sensing technologies, intelligent algorithms, and physics-based modeling into unified safety frameworks.

Conclusion

The main conclusions of this extensive review are as listed below: 1) Thermal runaway remains one of the most critical safety challenges associated with lithium-ion battery systems. Conventional threshold-based protection strategies are increasingly insufficient for modern high-energy battery applications because they frequently provide limited warning time before catastrophic failure. 2) Recent advances in sensing technologies, machine learning, hybrid AI–physics frameworks, and digital twin architectures have significantly improved the capability for early thermal runaway detection and prognostic safety assessment. 3) Gas sensing, swelling diagnostics, embedded sensing, and multimodal sensor fusion have demonstrated strong potential for improving early-warning reliability. Simultaneously, machine-learning and deep-learning frameworks are transforming battery safety diagnostics by enabling predictive and adaptive safety management. 4) Future battery safety systems are expected to progressively transition toward intelligent, autonomous, and prognostic safety ecosystems integrating embedded multidimensional sensing, physics-informed artificial intelligence, digital twins, and cloud-edge battery management frameworks. 5) The continued development of reliable, interpretable, and scalable prognostic safety systems will be essential for ensuring the safe large-scale deployment of electric vehicles and next-generation energy storage technologies.

References

[1] Jingyuan Zhao, Xuning Feng, Quanquan Pang, Michael Fowler, Yubo Lian, Minggao Ouyang, Andrew F. Burke, \"Battery safety: Machine learning-based prognostics\", Progress in Energy and Combustion Science, Volume 102, 2024, 101142, ISSN 0360-1285, https://doi.org/10.1016/j.pecs.2023.101142. [2] Xuning Feng, Minggao Ouyang, Xiang Liu, Languang Lu, Yong Xia, Xiangming He, \"Thermal runaway mechanism of lithium ion battery for electric vehicles: A review\", Energy Storage Materials, Volume 10, 2018, Pages 246-267, ISSN 2405-8297, https://doi.org/10.1016/j.ensm.2017.05.013. [3] Huaibin Wang, Hui Xu, Zelin Zhang, Qinzheng Wang, Changyong Jin, Changjun Wu, Chengshan Xu, Jinyuan Hao, Lei Sun, Zhiming Du, Yang Li, Junli Sun, Xuning Feng, \"Fire and explosion characteristics of vent gas from lithium-ion batteries after thermal runaway: A comparative study\", eTransportation, Volume 13, 2022, 100190, ISSN 2590-1168, https://doi.org/10.1016/j.etran.2022.100190. [4] Dongsheng Ren, Xuning Feng, Lishuo Liu, Hungjen Hsu, Languang Lu, Li Wang, Xiangming He, Minggao Ouyang, \"Investigating the relationship between internal short circuit and thermal runaway of lithium-ion batteries under thermal abuse condition\", Energy Storage Materials, Volume 34, 2021, Pages 563-573, ISSN 2405-8297, https://doi.org/10.1016/j.ensm.2020.10.020. [5] Binbin Mao, Peifeng Huang, Haodong Chen, Qingsong Wang, Jinhua Sun, \"Self-heating reaction and thermal runaway criticality of the lithium ion battery\", International Journal of Heat and Mass Transfer, Volume 149, 2020, 119178, ISSN 0017-9310, https://doi.org/10.1016/j.ijheatmasstransfer.2019.119178.. [6] Perrine Ribiere, Sylvie Grugeon, Mathieu Morcrette, Simeon Boyanov, Stephane Laruellea, “Investigation on the fire-induced hazards of Li-ion battery cells by fire calorimetry”, Energy Environ. Sci., 2012, 5, 5271, DOI: 10.1039/c1ee02218k [7] Dean Anthony, Derek Wong, David Wetz, Ankur Jain, \"Non-invasive measurement of internal temperature of a cylindrical Li-ion cell during high-rate discharge\", International Journal of Heat and Mass Transfer, Volume 111, 2017, Pages 223-231, ISSN 0017-9310, https://doi.org/10.1016/j.ijheatmasstransfer.2017.03.095. [8] Chengshan Xu, Xuning Feng, Wensheng Huang, Yongkang Duan, Tianyu Chen, Shang Gao, Languang Lu, Fachao Jiang, Minggao Ouyang, \"Internal temperature detection of thermal runaway in lithium-ion cells tested by extended-volume accelerating rate calorimetry\", Journal of Energy Storage, Volume 31, 2020, 101670, ISSN 2352-152X, https://doi.org/10.1016/j.est.2020.101670. [9] Y. Fernandes, A. Bry, S. de Persis, \"Identification and quantification of gases emitted during abuse tests by overcharge of a commercial Li-ion battery\", Journal of Power Sources, Volume 389, 2018, Pages 106-119, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2018.03.034. [10] Ting Cai, z Anna G. Stefanopoulou and Jason B. Siegel, “Modeling Li-Ion Battery Temperature and Expansion Force during the Early Stages of Thermal Runaway Triggered by Internal Shorts” , Journal of The Electrochemical Society, 166 (12) A2431-A2443 (2019). [11] Gang Yang, Catia Leitão, Yuhong Li, João Pinto, Xuefan Jiang, \"Real-time temperature measurement with fiber Bragg sensors in lithium batteries for safety usage, Measurement\", Volume 46, Issue 9, 2013, Pages 3166-3172, ISSN 0263-2241, https://doi.org/10.1016/j.measurement.2013.05.027. [12] Hengyi Zhang, Xiaoshan Zhang, Wenwu Wang and Ping Yu, “Detection and Prediction of the Early Thermal Runaway and Control of the Li-Ion Battery by the Embedded Temperature Sensor Array,” Sensors 2023, 23, 5049, https://doi.org/10.3390/s23115049. [13] Manh-Kien Tran and Michael Fowler, “A Review of Lithium-Ion Battery Fault Diagnostic Algorithms: Current Progress and Future Challenges” Algorithms 2020, 13, 62; doi:10.3390/a13030062. [14] Chen, Q.; He, Y.; Fang, N.;Yu, G. “A Combined Data-Driven and Model-Based Algorithm for Accurate Battery Thermal Runaway Warning.” Sensors 2024, 24, 4964. https://doi.org/10.3390/s24154964. [15] Jinho Jeong, Eunji Kwak, Jun-hyeong Kim, Ki-Yong Oh, \"Prediction of thermal runaway for a lithium-ion battery through multiphysics-informed DeepONet with virtual data\", eTransportation, Volume 21, 2024, 100337, ISSN 2590-1168, https://doi.org/10.1016/j.etran.2024.100337. [16] Gu, X., Shang, Y., Li, J. et al. Early warning of thermal runaway based on state of safety for lithium-ion batteries. Commun Eng 4, 106 (2025). https://doi.org/10.1038/s44172-025-00442-1. [17] Xuning Feng, Minggao Ouyang, Xiang Liu, Languang Lu, Yong Xia, Xiangming He, Thermal runaway mechanism of lithium ion battery for electric vehicles: A review, Energy Storage Materials, Volume 10, 2018, Pages 246-267, ISSN 2405-8297, https://doi.org/10.1016/j.ensm.2017.05.013. [18] Hossein Maleki, Guoping Deng,* Anaba Anani, and Jason Howard, Thermal Stability Studies of Li-Ion Cells and Components, Journal of The Electrochemical Society, 146 (9) 3224-3229 (1999). [19] Qingsong Zhang, Tiantian Liu, Qiong Wang, Experimental study on the influence of different heating methods on thermal runaway of lithium-ion battery, Journal of Energy Storage, Volume 42, 2021, 103063, ISSN 2352-152X, https://doi.org/10.1016/j.est.2021.103063. [20] Chunpeng Zhao, Tinghua Wang, Zheng Huang, Jingyun Wu, Hongwei Zhou, Mina Ma, Jiajia Xu, Zhaoyu Wang, Huang Li, Jinhua Sun, Qingsong Wang, Experimental study on thermal runaway of fully charged and overcharged lithium-ion batteries under adiabatic and side-heating test, Journal of Energy Storage, Volume 38, 2021, 102519, ISSN 2352-152X, https://doi.org/10.1016/j.est.2021.102519. [21] Jialong Liu, Zonghou Huang, Jinhua Sun, Qingsong Wang, Heat generation and thermal runaway of lithium-ion battery induced by slight overcharging cycling, Journal of Power Sources, Volume 526, 2022, 231136, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2022.231136. [22] Joshua Lamb, Christopher J. Orendorff, Evaluation of mechanical abuse techniques in lithium ion batteries, Journal of Power Sources, Volume 247, 2014, Pages 189-196, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2013.08.066. [23] Haodong Chen, Jonathan E.H. Buston, Jason Gill, Daniel Howard, Rhiannon C.E. Williams, Chandra M. Rao Vendra, Ashish Shelke, Jennifer X. Wen, An experimental study on thermal runaway characteristics of lithium-ion batteries with high specific energy and prediction of heat release rate, Journal of Power Sources, Volume 472, 2020, 228585, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2020.228585. [24] Choi, S.; Lee, K.; Kim, J.; Oh, S.; Joo, J.; Bae, E.; Lee, H.; Kim, M. Early Detection and Suppression of Thermal Runaway in Large-Format Lithium-Ion Batteries: Insights from Experimental Analysis. Energies 2025, 18, 155. https://doi.org/10.3390/en18010155. [25] Zhongbao Wei, Jiyun Zhao, Hongwen He, Guanglin Ding, Haoyong Cui, Longcheng Liu, Future smart battery and management: Advanced sensing from external to embedded multi-dimensional measurement, Journal of Power Sources, Volume 489, 2021, 229462, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2021.229462. [26] Zhang X, Chen S, Zhu J, Gao Y. A Critical Review of Thermal Runaway Prediction and EarlyWarning Methods for Lithium-Ion Batteries. Energy Mater. Adv. 2023;4:Article 0008. https://doi. org/10.34133/energymatadv.0008. [27] Zhe Li, Jianbo Zhang, Bin Wu, Jun Huang, Zhihua Nie, Ying Sun, Fuqiang An, Ningning Wu, Examining temporal and spatial variations of internal temperature in large-format laminated battery with embedded thermocouples, Journal of Power Sources, Volume 241, 2013, Pages 536-553, ISSN 0378-7753, https://doi.org/10.1016/j.jpowsour.2013.04.117. [28] Pu, Z.; Yang, M.; Jiao, M.; Zhao, D.; Huo, Y.;Wang, Z. Thermal RunawayWarning of Lithium Battery Based on Electronic Nose and Machine Learning Algorithms. Batteries 2024, 10, 390. https://doi.org/10.3390/batteries10110390. [29] Joohyung Bang, Byungkwon Chun, Minhyeok Kim, Jaeyoung Lim, Yongha Han, Hongyun So, Rapid thermal runaway detection of lithium-ion battery via swelling-based state-of-charge monitoring using piezoresistive sponge sensor, eTransportation, Volume 24, 2025, 100404, ISSN 2590-1168, https://doi.org/10.1016/j.etran.2025.100404. [30] Micael Nascimento, Marta S. Ferreira, João L. Pinto, Temperature fiber sensing of Li-ion batteries under different environmental and operating conditions, Applied Thermal Engineering, Volume 149, 2019, Pages 1236-1243, ISSN 1359-4311, https://doi.org/10.1016/j.applthermaleng.2018.12.135. [31] Ao Li, Jingwen Weng, Anthony Chun Yin Yuen, Wei Wang, Hengrui Liu, Eric Wai Ming Lee, Jian Wang, Sanghoon Kook, Guan Heng Yeoh, Machine learning assisted advanced battery thermal management system: A state-of-the-art review, Journal of Energy Storage, Volume 60, 2023, 106688, ISSN 2352-152X, https://doi.org/10.1016/j.est.2023.106688. [32] Chen K, Luo L, Lei W, Lv P and Zhang L (2024) Design and implementation of online battery monitoring and management system based on the internet of things. Front. Energy Res. 12:1454398. doi: 10.3389/fenrg.2024.1454398. [33] Cheng, YM., Gao, DX., Zhao, FM. et al. Early warning method for charging thermal runaway of electric vehicle lithium-ion battery based on charging network. Sci Rep 15, 7895 (2025). https://doi.org/10.1038/s41598-025-92738-7. [34] A. Athanasopoulos, M. Mihal´ak and M. Pietrasik,“Deep Learning Methods for Detecting Thermal Runaway Events in Battery Production Lines,” 2025 IEEE 8th International Conference on Industrial Cyber-Physical Systems (ICPS), Emden, Germany, 2025, pp. 1-6, doi: 10.1109/ICPS65515.2025.11087884. [35] Liwen Zhang, Peng Zhao, Meng Xu, Xia Wang, Computational identification of the safety regime of Li-ion battery thermal runaway, Applied Energy, Volume 261, 2020, 114440, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2019.114440. [36] Masalkovait?, K., Gasper, P. & Finegan, D.P. Predicting the heat release variability of Li-ion cells under thermal runaway with few or no calorimetry data. Nat Commun 15, 8399 (2024). https://doi.org/10.1038/s41467-024-52653-3. [37] Dunan Hu, Sheng Huang, Zhen Wen, Xiuquan Gu, Jianguo Lu, A review on thermal runaway warning technology for lithium-ion batteries, Renewable and Sustainable Energy Reviews, 2024, 114882, ISSN 1364-0321, https://doi.org/10.1016/j.rser.2024.114882. [38] G. Krishna, R. Singh, A. Gehlot, V. A. Shaik, B. Twala, and N. Priyadarshi, “IoT-based real-time analysis of battery management system with long range communication and FLoRa,” Results in Engineering, vol. 23, pp. 102770, 2024, doi: 10.1016/j.rineng.2024.102770. [39] Wang, L.;Wang, C.; Lu, X.; Ping, D.; Jiang, S.;Wang, X.; Zhang, J. A Design for a Lithium-Ion Battery Pack Monitoring System Based on NB-IoT-ZigBee. Electronics 2023, 12, 3561. https://doi.org/10.3390/electronics12173561. [40] Mahdy, O.S., Ali, A.B.M., Mostafa, L. et al. Quantitative evaluation of thermal runaway in lithium-ion batteries under critical heating conditions to enhance safety. Sci Rep 15, 24004 (2025). https://doi.org/10.1038/s41598-025-07824-7.

Copyright

Copyright © 2026 Ronak Rana, Dr. Ritula Thakur. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.