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 (10): 1441-1450.

• •    下一篇

电气火灾早期征兆监测预警技术研究现状

马砺1, 蒋慧灵2, 李阳3, 刘树林1, 徐阳4, 黄霄1, 闫小庆1   

  1. （1.西安科技大学 安全科学与工程学院，陕西 西安 710054； 2.北京科技大学 大安全科学研究院，北京100083； 3.中国人民警察大学 物证鉴定中心，河北 廊坊 065000； 4.西安交通大学 电气绝缘与电力设备国家重点实验室，陕西 西安 710049）
  • 收稿日期:2025-07-29 修回日期:2025-09-04 出版日期:2025-10-15 发布日期:2025-10-15
  • 作者简介:马 砺，西安科技大学二级教授，博士生导师，主要从事火灾科学与防控技术领域的研究，陕西省西安市雁塔中路58号，710054，mal@xust.edu.cn。
  • 基金资助:
    国家重点研发计划项目（2023YFC3009800）

Research status of early warning and monitoring technology for electrical fire

Ma Li1, Jiang Huiling2, Li Yang3, Liu Shulin1, Xu Yang4, Huang Xiao1, Yan XiaoQing1   

  1. (1. College of Safety Science and Engineering, Xi'an University of Science and Technology, Xi'an Shaanxi 710054, China; 2. Research Institute of Macro-Safety Science, University of Science and Technology Beijing, Beijing 100083, China; 3. Institute of Forensic Science, China People's Police University, Langfang Hebei 065000, China; 4. State Key Laboratory of Electrical Insulation and Power Equipment, Xi′an Jiaotong University, Xi′an Shaanxi 710049, China)
  • Received:2025-07-29 Revised:2025-09-04 Online:2025-10-15 Published:2025-10-15

摘要： 电气火灾监测预警对火灾防控尤为重要。本文针对电气火灾早期征兆复杂多样、风险预警不精准等问题，对引起电气火灾的短路、过载、接触不良诱发的超温、发光连接、故障电弧等多种故障耦合致灾机理研究进程进行分析，深入比较目前各类故障识别方法和模型，梳理了电气火灾监测预警技术的发展现状。从致灾机理、监测识别技术及其预警系统厘清了当前研究存在的关键问题和技术难点。提出通过开展电气线路故障之间转化致灾场景重现试验，揭示电气火灾本源性故障及转化机制；建立融合电气参量、热解气体、环境等多元信息的电气线路超温危险状态预测模型；研究电气线路发光连接的“电-热-气-光”多源识别与定位技术，提出多因素耦合条件下的电气线路故障电弧监测方法；研究基于云边端协同的电气火灾危险感知能力的智能监测预警系统，构建电气故障致灾图谱和研发AI电气火灾预警智能体等技术是提升监测预警准确率的发展趋势。

关键词: 电气火灾, 早期征兆, 监测预警, 智能化

Abstract: Electrical fire monitoring and early warning are of great significance for fire prevention and control. In response to the complexity of early signs and the limited accuracy of risk prediction, this paper analyzes the research progress on the coupled mechanisms of multiple electrical faults which may lead to electrical fires, including overheating, short circuits, arc faults, overloads, and glowing connections, further compares fault identification methods and models, and provides a systematic review of the state-of-the-art in electrical fire monitoring and early warning technologies. The review highlights the critical scientific issues and technical challenges from the viewpoints of failure mechanisms, monitoring and identification technologies, and early warning systems. It is proposed to carry out experiments on reproducing disaster scenarios involving the transformation between different electrical faults, thereby identifying characteristic parameters of early warning signs associated with primary fault sources of electrical fires. Furthermore, a predictive model for overheating risk in electrical circuits was developed by integrating multi-source information, including electrical parameters, pyrolysis gases, and environmental factors, enabling accurate early-stage warning of overheating conditions. Multi-source recognition and localization approach for glowing connections that integrates electrical, thermal, gaseous, and optical signals was developed, and a monitoring strategy for fault arcs under multi-factor coupling conditions was proposed. Research on an intelligent monitoring and early warning system for electrical fire hazards based on cloud-edge-device collaboration, the construction of an electrical fault disaster spectrum, and AI-powered electrical fire early warning agents are key trends in improving the accuracy of monitoring and early warning.

Key words: electrical fire, early signs, monitoring and early warning, intelligentization