中国安全科学学报 ›› 2021, Vol. 31 ›› Issue (6): 182-188.doi: 10.16265/j.cnki.issn 1003-3033.2021.06.024

• 应急技术与管理 • 上一篇    下一篇

基于贝叶斯网络的城镇洪涝应急情景推演研究

王喆1,2,3 副教授, 孔维磊1,2,3, 方丹辉**1,2,3 副教授, 段志飞1,2,3   

  1. 1 武汉理工大学 中国应急管理研究中心,湖北 武汉 430070;
    2 安全预警与应急联动技术湖北省协同创新中心,湖北 武汉 430070;
    3 武汉理工大学 安全科学与应急管理学院,湖北 武汉 430070
  • 收稿日期:2021-03-12 修回日期:2021-05-08 出版日期:2021-06-28 发布日期:2021-12-28
  • 通讯作者: **方丹辉(1976—),女,湖北荆门人,博士,副教授,主要从事应急管理、情景推演、公共安全等方面的研究工作。E-mail:
    2871926@qq.com。
  • 作者简介:王喆 (1980—),男,湖北武汉人,工学博士,副教授,硕士生导师,主要从事应急决策、人工智能、应急物流等方面的研究。E-mail:philo_wang@163.com。
  • 基金资助:
    教育部人文社会科学研究青年基金资助(20YJC630154);国家自然科学基金资助(71501151);国家社会科学基金资助(16CTQ022);湖北省自然科学基金资助(2016CFB467)。

Research on urban flood and waterlog emergency scenario deductionbased on Bayesian network

WANG Zhe1,2,3, KONG Weilei1,2,3, FANG Danhui1,2,3, DUAN Zhifei1,2,3   

  1. 1 China Research Center for Emergency Management, Wuhan University of Technology, Wuhan Hubei 430070, China;
    2 Hubei Collaborative Innovation Center for Early Warning and Emergency Response Technology, Wuhan Hubei 430070, China;
    3 School of Safety Science and Emergency Management, Wuhan University of Technology, Wuhan Hubei 430070, China
  • Received:2021-03-12 Revised:2021-05-08 Online:2021-06-28 Published:2021-12-28

摘要: 为处理城镇洪涝灾害复杂演变过程,结合证据理论与知识元模型,利用贝叶斯网络,针对城镇洪涝灾害进行应急情景推演研究。将城镇洪涝灾害情景推演要素归类为孕灾环境、致灾因子、承灾体和应急管理,并分析各要素之间的作用关系,建立城镇洪涝灾害应急情景贝叶斯网络,以验证应急管理措施的科学性和有效性,并通过2016年武汉市洪涝灾害进行实例分析。结果表明:知识元模型能建构城镇洪涝灾害应急情景的复杂演化路径,证据理论能处理应急情景演化中的不确定性信息,而贝叶斯网络能有效仿真推演并评价应急管理措施。

关键词: 城镇洪涝灾害, 应急情景推演, 知识元, 贝叶斯网络, 致灾因子, 承灾体

Abstract: In order to deal with complex evolution process of urban flood and waterlog disaster, Bayesian network was utilized in combination with evidence theory and knowledge meta-model for emergency scenario deduction research on urban flood and waterlog disasters. Then, their deduced elements were classified into disaster-pregnant environment, disaster-causing factors, disaster-bearing carrier and emergency management, and relationship between elements was analyzed. Finally, a Bayesian network of urban flood and waterlog disaster emergency scenarios was established to verify scientificity and effectiveness of emergency management measures through case study of flood disaster in Wuhan in 2016. The results show that the knowledge element model can construct a complex evolution path of urban flood and waterlog disaster emergency scenarios since evidence theory can deal with uncertain information in evolution of these scenarios while Bayesian network can effectively evaluate emergency management measures through simulation evolution.

Key words: urban flood and waterlog disaster, emergency scenario deduction, knowledge element, Bayesian network, disaster-causing factors, disaster-bearing carrier

中图分类号: