A review of early warning methods based on force-gas-temperature signals for thermal runaway in lithium-ion batteries

Lithium-ion batteries (LIBs) offer high performance for energy storage but pose safety risks, especially thermal runaway. To enable early warning, battery condition can be inferred indirectly and incompletely from three parameters: mechanical stress-strain, temperature, and gas composition. These three signals differ fundamentally in their physical origins, resulting in distinct timing, sensitivity, and reliability. Although temperature directly reflects the cell’s thermal state and surface temperature monitoring is mature and robust, heat-transfer delays make it suitable only as a final indicator. Expansion force responds quickly, providing minutes of lead time, yet is vulnerable to mechanical noise. Characteristic gases such as H₂ and CO originate from very early side reactions, including solid electrolyte interphase (SEI) decomposition and electrolyte evaporation, offering tens of minutes of lead time. However, gas detection suffers from dilution, adsorption, and sensor cross-sensitivity, limiting accuracy and cost-effectiveness. No single signal can simultaneously achieve ultra-early, reliable, and low-cost warning. This paper reviews most existing thermal runaway warning mechanisms based on the force-gas-temperature triplet and presents several new predictive approaches. Moreover, the impact of machine learning on the spatiotemporal accuracy and generalization ability of thermal runaway early warning techniques is highlighted. We further propose that a force-gas-temperature multi-modal strategy—leveraging the complementarity of the three signals—is essential for practical deployment. Finally, future perspectives are specified in three directions: sensing technology to improve gas sensor selectivity, reduce drift, and enable low-cost distributed sensing; algorithm fusion to develop adaptive multi-signal frameworks that handle signal timing and noise characteristics; and engineering application to validate the force-gas-temperature chain under real operating conditions and achieve low-cost on-board or on-site implementation.