Physics-Enhanced Deep Learning for Proactive Thermal Runaway Forecasting in Li-Ion Batteries

arXiv cs.LG / 4/23/2026

📰 NewsModels & Research

共有:

Key Points

The study addresses the challenge of accurately forecasting thermal runaway in lithium-ion batteries, noting that purely data-driven models may produce predictions that violate thermodynamic principles.
It proposes a Physics-Informed LSTM (PI-LSTM) that incorporates heat-transfer governing equations into the neural network via a physics-based regularization term in the loss function.
Using multi-feature input sequences (state of charge, voltage, current, mechanical stress, and surface temperature), the model forecasts battery temperature evolution while enforcing thermal diffusion constraints.
Experiments on thirteen battery datasets show large error reductions versus standard LSTM and other baselines (81.9% RMSE reduction and 81.3% MAE reduction), along with improved generalization across operating conditions and elimination of non-physical temperature oscillations.

Abstract

Accurate prediction of thermal runaway in lithium-ion batteries is essential for ensuring the safety, efficiency, and reliability of modern energy storage systems. Conventional data-driven approaches, such as Long Short-Term Memory (LSTM) networks, can capture complex temporal dependencies but often violate thermodynamic principles, resulting in physically inconsistent predictions. Conversely, physics-based thermal models provide interpretability but are computationally expensive and difficult to parameterize for real-time applications. To bridge this gap, this study proposes a Physics-Informed Long Short-Term Memory (PI-LSTM) framework that integrates governing heat transfer equations directly into the deep learning architecture through a physics-based regularization term in the loss function. The model leverages multi-feature input sequences, including state of charge, voltage, current, mechanical stress, and surface temperature, to forecast battery temperature evolution while enforcing thermal diffusion constraints. Extensive experiments conducted on thirteen lithium-ion battery datasets demonstrate that the proposed PI-LSTM achieves an 81.9% reduction in root mean square error (RMSE) and an 81.3% reduction in mean absolute error (MAE) compared to the standard LSTM baseline, while also outperforming CNN-LSTM and multilayer perceptron (MLP) models by wide margins. The inclusion of physical constraints enhances the model's generalization across diverse operating conditions and eliminates non-physical temperature oscillations. These results confirm that physics-informed deep learning offers a viable pathway toward interpretable, accurate, and real-time thermal management in next-generation battery systems.