主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2025, Vol. 44 ›› Issue (2): 163-167.

• • 上一篇    下一篇

基于数字孪生的隧道火灾实时量化、预测与风险评估技术

张小宁1，2, 吴西强3, 黄鑫炎1   

  1. （1.香港理工大学 建筑环境与能源工程学系，中国 香港 999077；2.鹏城实验室，广东 深圳 518000；3.东南大学 交通学院，江苏 南京 211189）
  • 收稿日期:2024-10-15 修回日期:2024-10-26 出版日期:2025-02-15 发布日期:2025-02-15
  • 作者简介:张小宁，男，香港理工大学建筑环境及能源工程系助理研究员，鹏城实验室博士后，主要从事隧道消防安全、人工智能及数字孪生方面的研究，中国香港特别行政区九龙漆咸道南181号，999077。
  • 基金资助:
    香港主题研究计划（T22-505/19-N）；国家自然科学基金资助项目（52108480）

Real-time tunnel fire quantification, prediction and risk assessment technology based on digital twin

Zhang Xiaoning1, 2, Wu Xiqiang2, Huang Xinyan1   

  1. (1. Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, China; 2. Pengcheng Laboratory, Shenzhen Guangdong 518000, China; 3. School of Transportation, Southeast University, Nanjing Jiangsu 211189, China)
  • Received:2024-10-15 Revised:2024-10-26 Online:2025-02-15 Published:2025-02-15

摘要： 隧道一旦发生火灾，可能会导致严重人员伤亡和经济损失。本文提出一种基于数字孪生的隧道火灾量化、预测与风险评估技术，用于提高隧道的消防韧性、应急处置效率和智能化水平。首先，基于数字孪生框架提出隧道火灾的量化预测方法、日常情况下的火灾风险评估方法。接着，分别介绍了隧道消防物联网技术、基于人工智能的火灾识别与量化技术、火灾蔓延与发展预测技术以及基于计算机视觉的隧道火灾风险评估方法。最后，通过试验或模拟数据对所提出的火灾监测、预测和风险评估方法进行了验证。结果表明，所提出的模型和方法都表现出了较高的预测精确度，可以满足隧道消防安全实践要求。

关键词: 数字孪生, 隧道消防安全, 人工智能, 火灾量化与预测, 火灾风险评估

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