| 229 | 0 | 8 |
| Downloads | Citas | Reads |
[Significance] In tunnel fire safety prevention and control, artificial intelligence(AI) has gradually become a key means of accurate monitoring and intelligent warning of tunnel fires because of its ability to solve problems of traditional monitoring, such as long response delays, long prediction times, and high false alarm rates. Prediction models based on empirical formulas take minutes to calculate, failing to meet the needs of early intervention. Therefore, using AI to accurately predict fire development trends(such as smoke spread and temperature distribution) is crucial for formulating emergency plans and ensuring safety. In particular, fire monitoring and intelligent early warning methods based on AI have become an important research direction in tunnel fire safety research.[Progress] Applications of AI to tunnel fires include the development of few-shot and self-supervised learning methods to enhance model generalization ability. They also involve promoting system integration and standardization to realize platform-based collaborative management. In multisource data collection, multi-sensor fusion adopts an improved hierarchical architecture based on D–S evidence theory. It integrates temperature, smoke, and gas data, thereby improving fire identification reliability by 45% in complex environments. Video monitoring relies on CNN(convolutional neural network) and YOLOv8 algorithms, combined with tunnel CCTV(closed-circuit television) systems, to analyze flame and smoke characteristics. It achieves 96% recognition accuracy and reduces the false alarm rate by 30%. Edge computing has achieved up to 96% accuracy and supports real-time alarms. At the platform level, AI-based disaster prevention and response systems(e.g., Shanghai's intelligent system) enable real-time visualization of fire locations and temperatures. They automatically trigger coordinated control of ventilation and sprinkler systems, reducing response delays by more than 50% compared with manual operation. In terms of intelligent early warning, generative AI, such as GANs(generative adversarial networks) and Transformers, can generate fire spread simulations within 5 s. LSTM–TCNN(long short-term memory-temporal convolutional neural network) reduces temperature field prediction from minute-level to second-level(with 90% accuracy), and digital twins construct 1∶1 virtual tunnels to generate synthetic data, thereby reducing the demand for training data by 50%. [Conclusions and Prospects] AI can effectively improve detection accuracy and response efficiency in tunnel fire monitoring and early warning. However, several challenges remain, including the scarcity of real-world samples(applying highway models to railways reduces accuracy by 15%–20%), the limited ability of traditional algorithms to capture global features, a lack of standardization in system integration, and high deployment costs. Future research will focus on using generative diffusion models to generate high-fidelity data and alleviate the sample scarcity issue, while reinforcement learning will be employed to optimize the collaborative control of equipment. In addition, a three-dimensional visualization platform based on BIM(building information modeling) and digital twins will be developed to enable VR/AR-based simulations. Further improvements in multimodal fusion are expected to enhance data reliability and cross-scenario adaptability, thereby advancing the intelligence of tunnel fire prevention and control. This research will contribute to improve the intelligence level of tunnel fire early warning and emergency response and promote the practical application of AI in tunnel fire engineering.
[1]央视网.科技创新助力我国隧道技术装备领先世界[EB/OL].(2024-06-09)[2025-10-20]. https://www.gov.cn/yaowen/shipin/202406/content_6956591.htm.CCTV.com. Technological innovation helps China's tunnel technology and equipment take the lead in the world[EB/OL].(2024-06-09)[2025-10-20]. https://www.gov.cn/yaowen/shipin/202406/content_6956591.htm.(in Chinese)
[2]赵峰,夏永旭,谢涛.公路隧道运营事故统计分析研究[J].公路, 2014, 59(6):280–287.ZHAO F, XIA Y X, XIE T. Analysis and study of operational accidents in road tunnel[J]. Highway, 2014, 59(6):280–287.(in Chinese)
[3]蒋亚强,李乐,廖曙江,等.隧道火灾烟气最高温升特性的全尺寸试验研究[J].工程热物理学报, 2015, 36(10):2287–2292.JIANG Y Q, LI L, LIAO S J, et al. Full-scale experimental study on maximum temperature rise characteristics of fire smoke in urban tunnels[J]. Journal of Engineering Thermophysics, 2015,36(10):2287–2292.(in Chinese)
[4]赖金星,周慧,程飞,等.公路隧道火灾事故统计分析及防灾减灾对策[J].隧道建设, 2017, 37(4):409–415.LAI J X, ZHOU H, CHENG F, et al. Statistical analysis of highway tunnel fire accidents and disaster prevention and mitigation measures[J]. Tunnel Construction, 2017, 37(4):409–415.(in Chinese)
[5]喻凌峰.基于多传感器数据融合的隧道火灾监测报警技术研究[J].隧道建设(中英文), 2022, 42(增刊2):261–266.YU L F. Research on tunnel fire monitoring and alarm technology based on multi-sensor data fusion[J]. Tunnel Construction(Chinese&English), 2022, 42(S2):261–266.(in Chinese)
[6]胡其志,殷秋雨,李鸣,等.分布式光纤在公路隧道火灾监控中的应用研究[J].公路, 2020, 65(4):383–387.HU Q Z, YIN Q Y, LI M, et al. Research on the application of distributed optical fiber in highway tunnel fire monitoring[J].Highway, 2020, 65(4):383–387.(in Chinese)
[7]卢毅,田芳,陈建忠,等.公路隧道火灾灾情监测技术现状及展望[J].公路交通技术, 2021, 37（增刊1）:83–86, 92.LU Y, TIAN F, CHEN J Z, et al. Current situation and prospect of highway tunnel fire disaster monitoring technology[J].Highway Transportation Technology, 2021, 37(S1):83–86, 92.(in Chinese)
[8]WANG H, SHI Y, CHEN L, et al. A tunnel fire detection method based on an improved Dempster-Shafer evidence theory[J].Sensors, 2024, 24(19):6455–6455.
[9]VERONIKA A, MARTIN B. Effective placement of video surveillance system using 3d scanning technology for traffic safety[J]. Transportation Research Procedia, 2021, 55:1665–1672.
[10]LEE B, HAN D. Real-time fire detection using camera sequence image in tunnel environment[J]. International Journal of Information Acquisition, 2007, 4(4):327–338.
[11]ALBOODY A, QAISAR S M, ROUSSEL G. Artificial intelligence assistive fire detection and seeing the invisible through smoke using hyperspectral and multi-spectral images[C]//2023 IEEE13th International Conference on Electronics and Information Technologies(ELIT). Lviv, Ukraine, 2023:181–185.
[12]吴宗胜,韩改宁,李红.公路隧道智能火灾检测系统设计[J].计算机技术与发展, 2022, 32(3):163–168.WU Z S, HAN G N, LI H. Design of intelligent fire detection system for highway tunnels[J]. Computer Technology and Development, 2022, 32(3):163–168.(in Chinese)
[13]郭澄霖.基于深度学习的火焰检测与边缘计算设备部署[D].海口:海南大学, 2022.GUO C L. Flame detection based on deep learning and deployment of edge computing devices[D]. Haikou:Hainan University, 2022.(in Chinese)
[14]GUO C, YAN Z G, LIU T. Application of the tunnel fire scenario dynamic reconstruction based on intelligent disaster prevention platform in Shanghai[C]//IOP Conference Series:Earth and Environmental Science. IOP Publishing, 2021, 861(7):072041.
[15]郭超,闫治国.基于多源数据深度学习的地下空间智慧防灾系统框架研究[J].现代隧道技术, 2020, 57（增刊1）:13–23.GUO C, YAN Z G. Research on the framework of intelligent disaster prevention system for underground space based on multisource data deep learning[J]. Modern Tunnelling Technology,2020, 57(S1):13–23.(in Chinese)
[16]DENG L, SHI C, LI H, et al. Prediction of energy mass loss rate for biodiesel fire via machine learning and its physical modeling of flame radiation evolution[J]. Energy, 2023, 275:127388.
[17]LIU W, DENG L, LI H, et al. Experimental study and machine learning on the maximum temperature beneath tunnel ceiling induced by adjacent tandem fires in longitudinally ventilated tunnel[J]. International Journal of Thermal Sciences, 2023, 187:108169.
[18]UPADHYAY R K, VISHWAKARMA P K, MISHRA K B.Failure analysis of a separator under various thermal loading:A numerical study[J]. Journal of Loss Prevention in the Process Industries, 2024, 91:105399.
[19]PAZ-PAREDES I, JIMÉNEZ F, MUÑOZ J A D, et al.Computational fluid dynamics for modeling of hydrotreating fixed-bed reactors:A review[J]. Processes, 2025, 13(3):894.
[20]CHEN J, ZHANG H, WANG L, et al. Effects of the jet fan air velocity response strategy and fire source location on the immersed tunnel fire smoke control[J]. Journal of Zhejiang University-SCIENCE A, 2025, 26(4):320–338.
[21]QIU M X, LI Y, XU L, et al. Experimental study on flame behaviour characteristics induced by unequal double fires in a tunnel under different ventilation modes[J]. Tunnelling and Underground Space Technology, 2025, 163:106730.
[22]QIU M X, XU L, ZHAO Y, et al. Experimental investigation on maximum ceiling temperature and longitudinal attenuation in a closed tunnel with an inclined shaft[J]. International Journal of Thermal Sciences, 2025, 208:109484.
[23]JEVTIĆR B, BLAGOJEVIĆMĐ. On a linear fire detection using coaxial cables[J]. Thermal Science, 2014, 18(2):603–614.
[24]GAUR A, SINGH A, KUMAR A, et al. Video flame and smoke based fire detection algorithms:A literature review[J]. Fire Technology, 2020, 56(5):1943–1980.
[25]HAN D, LEE B. Flame and smoke detection method for early real-time detection of a tunnel fire[J]. Fire Safety Journal, 2009,44(7):951–961.
[26]ZHU J, SONG Y, WANG J, et al. A highly flame-retardant, agile fire-alarming and ultrasensitive cotton fabric-based piezoresistive sensor for intelligent fire system[J]. Polymer Degradation and Stability, 2023, 211:110338.
[27]ZHANG X, WU X, PARK Y, et al. Perspectives of big experimental database and artificial intelligence in tunnel fire research[J]. Tunnelling and Underground Space Technology,2021, 108:103691.
[28]WU X, PARK Y, LI A, et al. Smart detection of fire source in tunnel based on the numerical database and artificial intelligence[J].Fire Technology, 2021, 57(2):657–682.
[29]JIANG L, GUO X, YANG Y, et al. Inversion of tunnel fires using limited monitored temperature data based on transfer learning approach and full-scale scenario applications[J].Engineering Applications of Artificial Intelligence, 2025, 162:112708.
[30]赵洋,周弋,王金双,等.基于非线性状态估计的电缆隧道火灾隐患监控预警方法[J].电力信息与通信技术, 2022, 20(3):104–109.ZHAO Y, ZHOU Y, WANG J S, et al. Monitoring and early warning method for fire hazards in cable tunnels based on nonlinear state estimation[J]. Electric Power Information and Communication Technology, 2022, 20(3):104–109.(in Chinese)
[31]《中国公路学报》编辑部.中国隧道工程学术研究综述·2015[J].中国公路学报, 2015, 28(5):1–65.Editorial Department of China Journal of Highway and Transport.Review on China's tunnel engineering research:2015[J]. China Journal of Highway and Transport, 2015, 28(5):1–65.(in Chinese)
[32]杨健.公路隧道典型事故特征分析及预防控制技术研究[D].福州：福州大学, 2017.YANG J. Study on characteristic analysis of typical accidents and prevention&control technology in highway tunnels[D].Fuzhou:Fuzhou University, 2017.(in Chinese)
[33]张金雷,杨健,刘晓冰,等.基于计算机视觉的轨道交通站内火灾检测与定位[J].交通运输系统工程与信息, 2024, 24(3):53–63.ZHANG J L, YANG J, LIU X B, et al. Fire detection and localization in rail transit stations based on computer vision[J].Journal of Transportation Systems Engineering and Information Technology, 2024, 24(3):53–63.(in Chinese)
[34]JAIN H, DHUPPER R, SHRIVASTAVA A, et al. AI-enabled strategies for climate change adaptation:Protecting communities,infrastructure, and businesses from the impacts of climate change[J]. Computational Urban Science, 2023, 3(1):25.
[35]MOHAN K V M, SATISH A R, RAO K M, et al. Leveraging machine learning to predict wild fires[C]//2021 2nd International Conference on Smart Electronics and Communication(ICOSEC).IEEE, 2021:1393–1400.
[36]PARK M, TRAN D Q, JUNG D, et al. Wildfire-detection method using Dense net and cycle GAN data augmentationbased remote camera imagery[J]. Remote Sensing, 2020, 12(22):3715.
[37]何俊,张彩庆,李小珍,等.面向深度学习的多模态融合技术研究综述[J].计算机工程, 2020, 46(5):1–11.HE J, ZHANG C Q, LI X Z, et al. Survey of research on multimodal fusion technology for deep learning[J]. Computer Engineering, 2020, 46(5):1–11.(in Chinese)
[38]DESIKAN J M, SINGH S K, SRIVASTAVA A, et al. Hybrid machine learning-based fault-tolerant sensor data fusion and anomaly detection for fire risk mitigation in IIoT environment[J].Sensors, 2025, 25(7):2146.
[39]SELLARDS P K, ALLEN M, ZHU P, et al. Robotic wildfire detection using computer vision[C]//2025 ASEE North Central Section(NCS)Annual Conference. Chicago, 2025.
[40]丁晓晔,王振华,王光虎,等.高校实验室氢气意外泄漏及火灾数值模拟分析[J].实验技术与管理, 2023, 40(11):232–239, 257.DING X Y, WANG Z H, WANG G H, et al. Numerical simulation analysis of the accidental hydrogen leakage and fire in a university laboratory[J]. Experimental Technology and Management, 2023, 40(11):232–239, 257.(in Chinese)
[41]SU Z H, LI Y F, ZHONG H et al.Evaluating the impact of tunnel slope on critical velocity and confinement velocity in metro tunnel carriage fires[J]. Tunnelling and Underground Space Technology, 2024, 154:106141.
[42]王克拾.基于CFD模拟分析的大断面公路隧道汽车火灾温度特性研究[D].上海:同济大学, 2008.WANG K S. Study on temperature characteristics of vehicle fires in large-section highway tunnels based on CFD simulation analysis[D]. Shanghai:Tongji University, 2008.(in Chinese)
[43]李立明.隧道火灾烟气的温度特征与纵向通风控制研究[D].合肥:中国科学技术大学, 2012.LI L M. Study on temperature characteristics and longitudinal ventilation control of fire smoke in tunnels[D].Hefei:University of Science and Technology of China, 2012.(in Chinese)
[44]李牧,何金诚,杨恒.双分支GAN与注意力机制的火灾隐患检测算法[J].计算机工程与应用, 2024, 60(14):228–239.LI M, HE J C, YANG H. Fire hazard detection algorithm based on dual-branch GAN and attention mechanism[J]. Computer Engineering and Applications, 2024, 60(14):228–239.(in Chinese)
[45]XU H, ZLATANOVA S, LIANG R, et al. Generative AI as a Pillar for predicting 2D and 3D wildfire spread:Beyond physicsbased models and traditional deep learning[J]. Fire, 2025, 8(8):293.
[46]CUI Y, GU X, XI J, et al. Performance optimization of lithiumion battery based on CFD numerical simulation and deep learning algorithm[J]. Journal of Energy Storage, 2025, 127:117156.
[47]XIE C Z, XU D Z, GAI P P, et al. A deep learning–based surrogate model for spatial-temporal temperature field prediction in subway tunnel fires via CFD simulation[J]. Journal of Dynamic Disasters, 2025, 1(1):100002.
[48]LATTIMER B, HODGES J, LATTIMER A. Using machine learning in physics-based simulation of fire[J]. Fire Safety Journal, 2020, 114:102991.
[49]SHEN X, CAO Z, LIU H, et al. Inverse tracing of fire source in a single room based on CFD simulation and deep learning[J].Journal of Building Engineering, 2023, 76:107069.
[50]WU X Q, ZHANG X N, HUANG X Y, et al. A real-time forecast of tunnel fire based on numerical database and artificial intelligence[J]. Building Simulation, 2022, 15(4):511–524.
[51]吴乐,钟茂华,胡鹏,等.高层建筑火灾全尺寸实验设计与实践[J].实验技术与管理, 2025, 42(5):9–18.WU L, ZHONG M H, HU P, et al. Design and practice of fullscale experiments on high-rise building fires[J]. Experimental Technology and Management, 2025, 42(5):9–18.(in Chinese)
[52]罗巍,杨威,于立娟,等.基于数字孪生的工业机器人运动仿真平台设计[J].实验技术与管理, 2025, 42(5):192–199.LUO W, YANG W, YU L J, et al. Design of motion simulation platform for industrial robots based on digital twin[J]. Experimental Technology and Management, 2025, 42(5):192–199.(in Chinese)
[53]沐虹霞,朱旭平.基于加权马氏距离判别的计算机实验室火灾风险预警方法[J].实验技术与管理, 2024, 41(1):239–244.MU H X, ZHU X P. Fire risk early warning method for computer labs based on weighted mahalanobis distance discrimination[J].Experimental Technology and Management, 2024, 41(1):239–244.(in Chinese)
[54]张小宁,吴西强,黄鑫炎.基于数字孪生的隧道火灾实时量化、预测与风险评估技术[J].消防科学与技术, 2025, 44(2):163–167, 174.ZHANG X N, WU X Q, HUANG X Y. Research on real-time quantification, prediction and risk assessment technology of tunnel fire based on digital twin[J]. Fire Science and Technology,2025, 44(2):163–167, 174.(in Chinese)
[55]祖耕余.高速公路隧道火灾报警系统解决方案探讨及提升[J].中国交通信息化, 2024(6):129–131.ZU G Y. Discussion and improvement on the solution of fire alarm system for expressway tunnels[J]. China ITS Journal,2024(6):129–131.(in Chinese)
[56]郭奕孜.基于数字孪生的隧道火灾防控仿真平台研究[D].西安:长安大学, 2024.GUO Y Z. Research on simulation platform for tunnel fire prevention and control based on digital twin[D]. Xi’an:Chang’an University, 2024.(in Chinese)
[57]GEORGE M B, AYIKU E O. AI-driven fire risk indices integrating climate, fuel, and terrain for wildfire prediction and management[J]. Journal of Engineering and Technology Management, 2024, 8(2):67.
[58]葛小三,陈曦,赵文智,等.基于生成对抗网络的建筑物损毁检测[J].测绘学报, 2022, 51(2):238–247.GE X S, CHEN X, ZHAO W Z, et al. Building damage detection based on generative adversarial network[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(2):238–247.(in Chinese)
[59]SZEWCZYŃSKI K, KRÓL A, KRÓL M. Should we expect a disastrous fire accident in an urban road tunnel? Literature data review and a case study for selected tunnels in Poland[J].Sustainability, 2021, 13(11):6172.
[60]ZHANG Y, GENG P, SIVAPARTHIPAN C B, et al. Big data and artificial intelligence based early risk warning system of fire hazard for smart cities[J]. Sustainable Energy Technologies and Assessments, 2021, 45:100986.
[61]DARYAL U, GIRI A, KARKI S, et al. Early warning systems:Enhancing fire prediction and response[M]//Forest fire and climate change:Insights into science. Cham:Springer Nature Switzerland, 2025:451–474.
[62]REDDY P D K, MARGALA M, SHANKAR S S, et al. Early fire danger monitoring system in smart cities using optimization-based deep learning techniques with artificial intelligence[J]. Journal of Reliable Intelligent Environments, 2024, 10(2):197–210.
Basic Information:
DOI：10.16791/j.cnki.sjg.2026.01.001
China Classification Code:U458.1;TP18;TP277
Citation Information:
[1]LI Yanfeng,REN Yongsheng,QIU Mingxuan ,et al.Application of artificial intelligence to tunnel fire monitoring and early warning systems[J].Experimental Technology and Management,2026,43(01):1-10.DOI:10.16791/j.cnki.sjg.2026.01.001.
Fund Information:
北京工业大学教学研究立项(ER2024RCB06); 北京市自然科学基金项目(8222002)