Research on thermal runaway warning threshold and machine learning model for large capacity energy storage batteries based on electric-thermal-mechanical-gas coupling

Key Points

• Thermal runaway is effectively predicted, enhancing safety in energy storage systems.
• The model achieved a prediction accuracy of 92% across various battery conditions.
• Observational analysis of electric-thermal-mechanical interactions formed the basis of the predictions.
• The findings indicate an urgent need for improved monitoring in large capacity batteries.