Abstract: Fires in tunnel usually will cause serious casualties and economic losses. In the present study, we proposed digital twin-enabled tunnel fire quantification, prediction and risk assessment methods to improve the fire resilience, emergency response efficiency and intelligence level of tunnels. First, the tunnel fire quantification and prediction methods for fires response, and fire risk assessment methods for daily management based on digital twin framework are proposed. Then, the Internet of Things technologies for tunnel fires, AI-based fire identification and quantification technology, fire spread and development prediction technology, and computer vision-based tunnel fire risk assessment method are introduced respectively. Finally, the proposed monitoring, prediction and risk assessment methods are verified by experimental or simulation data. The results show that the proposed models and methods have shown high prediction accuracy and can meet the requirements of tunnel fire safety practice.

Key words: digital twin, tunnel fire safety, artificial intelligence, fire quantification and prediction, fire risk assessment