基于贝叶斯网络的并发型突发事件链建模方法

doi:10.16381/j.cnki.issn1003-207x.2017.1561

摘要/Abstract

摘要： 现实情形中，由于致灾因子和作用对象的相似性，初始突发事件的发生易引发多个次生事件并发及耦合，致使事件的演化发展及可能造成的损失具有更大的不确定性。然而，现有的突发事件链式演化分析多运用串发型事件链，对于并发型突发事件存在适用性较低的问题。针对上述问题，本文将突发事件抽象描述为以输入、状态和输出属性为组成要素，通过属性要素间的作用关系构成的复杂系统，进而从属性层面分析事件间的关联关系；以贝叶斯网络为建模工具，识别并发型突发事件间具有的因果关系和耦合关系，给出事件贝叶斯网络关联方法，构建并发型突发事件链模型；基于历史数据获取网络节点间的先验概率信息，运用贝叶斯网络推理算法实现并发型突发事件的演化分析；最后，通过实例验证本文方法在实际应用中的科学性及可行性，并通过对比分析阐明其在提高灾害损失预测精度方面具有一定的优势。

关键词: 突发事件链, 并发事件, 耦合效应, 贝叶斯网络

Abstract: In realistic circumstances, because of the similarities between the hazard factors and their affected objects in different emergencies, the occurrence of initial emergencies is likely to trigger the concurrence and coupling of multiple secondary emergencies, which makes the evolution of emergencies more uncertain and causes more serious losses. However, the existing emergency chain evolution analyses mostly used serial emergency chains, which is less applicable to concurrent emergencies. In view of the above problems, this paper presents a modeling method of concurrent emergency chain based on Bayesian Network to model the parallel evolution of concurrent emergencies. Firstly, emergency is described as a complex system composed of input, state, output attributes and the mutual influence relationships between them. And the causality and coupling relationships between emergencies are analyzed and defined on attribute level. Secondly, Bayesian network is applied to represent a single emergency formally. Based on the defined causality and coupling relationships between emergencies, the identification method of the causality and coupling relationships between single emergency Bayesian networks, the association method of concurrent emergency Bayesian networks, and the concrete construction method of the Bayesian network on concurrent emergency chain are put forward. Thirdly, the reasoning algorithm and its complexity and feasibility of the constructed concurrent emergencies Bayesian network are discussed. Through the Bayesian network reasoning process, the evolution analysis of concurrency emergencies can be realized in case of the prior probabilities between network nodes are obtained based on historical data analysis. Finally, to demonstrate the feasibility and validity of the proposed methods, the historical data of rainstorm disasters and the subsequent secondary disasters, such as mudslides, landslides, and floods and so on, in Sichuan Province from 2008 to 2015 is collected. Then the K2 network learning method is used to study the historical data to generate the Bayesian network of each disaster. Based on the identification of the interrelationships between the single Bayesian networks corresponding to each disaster, the integrated Bayesian network is constructed by correlating the interrelated single Bayesian networks. Taking the rainstorm disaster happened in August 16, 2015 in Yibin City as an example to instantiate the initial evidence information of the constructed integrated Bayesian network, the joint tree reasoning method is applied to predict the possible losses caused by the rainstorm and its derivative disasters. The analyses of the prediction result and the comparison with related serial emergency chains verify the scientificalness and effectiveness of the proposed methods while being used in evolution analysis of concurrent emergencies.

Key words: emergency chain, concurrent emergencies, coupling effect, bayesian network

中图分类号:

X913.4

陈雪龙，姜坤. 基于贝叶斯网络的并发型突发事件链建模方法[J]. 中国管理科学, 2021, 29(10): 165-177.

CHEN Xuelong, JIANG Kun. Modeling Method of Concurrent Emergency Chain Based on Bayesian Network[J]. Chinese Journal of Management Science, 2021, 29(10): 165-177.

参考文献

[1] 季学伟, 翁文国, 赵前胜. 突发事件链的定量风险分析方法 [J] . 清华大学学报, 2009, 49(11): 1749-1752.Ji Xuewei, Weng Wenguo, Zhao Qiansheng. Quantitative disaster chain risk analysis [J] . Journal of Tsinghua University, 2009, 49(11): 1749-1752.
[2] 李勇健, 王治莹, 乔晓娇. 基于超图的非常规突发事件链网络模型研究 [J] . 管理评论, 2015, 27(12): 192-201.Li Yongjian, Wang Zhiying, Qiao Xiaojiao. Network model of unconventional emergency chain based on hypergraph [J] . Management Review, 2015, 27(12):192-201.
[3] 史培军, 吕丽莉, 汪明,等. 灾害系统：灾害群、灾害链、灾害遭遇 [J] . 自然灾害学报, 2014, 23(6): 1-12.Shi Peijun, Lv Lili, Wang Ming, et al. Disaster system: Disaster cluster，disaster chain and disaster compound [J] . Journal of Natural Disasters, 2014, 23(6): 1-12.
[4] 裘江南, 刘丽丽, 董磊磊. 基于贝叶斯网络的突发事件链建模方法与应用 [J] . 系统工程学报, 2012, 27(6): 739-750.Qiu Jiangnan, Liu Lili, Dong Leilei. Modeling method and application of emergent event chain based on Bayesian network [J] . Journal of Systems Engineering, 2012, 27(6): 739-750.
[5] 王建伟, 荣莉莉. 突发事件的连锁反应网络模型研究 [J] . 计算机应用研究, 2008, 25(11): 3288-3291.Wang Jianwei, Rong Lili. Research on the chain-reacting network model of emergency events [J] . Application Research of Computers, 2008, 25(11): 3288-3291.
[6] 马骁霏, 仲秋雁, 曲毅,等. 基于情景的突发事件链构建方法 [J] . 情报杂志, 2013, 32(8): 155-158.Ma Xiaofei, Zhong Qiuyan, Qu Yi, et al. A scenario-based construction method of emergency event chain [J] . Journal of Intelligence, 2013, 32(8): 155-158.
[7] Shi Bo. Probabilistic risk and control analysis of self-circulation disaster crisis evolution chain [J] . Disaster Advances, 2012, 5(4): 593-596.
[8] 荣莉莉, 谭华. 基于孕灾环境的突发事件连锁反应模型 [J] . 系统工程, 2012, 30(7): 40-47.Rong Lili, Tan Hua. Modeling chain-reactions to emergency based on disaster-pregnant environment [J] . Systems Engineering, 2012, 30(7): 40-47.
[9] Dirk H, Hendrik A, Christion K. Disasters as extreme events and the importance of networks for disaster response management [M] . Disaster Management and Networks: Springer Berlin Heidelberg, 2006．
[10] Jensen F V, Nielsen T D. Bayesian networks and decision graphs [M] . 2nd Ed. New York: Springer Science Business Media, 2007: 10-11.
[11] 李藐, 陈建国, 陈涛,等. 突发事件的事件链概率模型 [J] . 清华大学学报(自然科学版), 2010, 50(8): 1173-1177.Li Miao, Chen Jianguo, Chen Tao, et al. Event chain probabilistic model of emergent events [J] . Journal of Tsinghua University(Science and Technology), 2010, 50(8): 1173-1177.
[12] 荣莉莉, 张继永. 突发事件的不同演化模式研究 [J] . 自然灾害学报, 2012, 21(3): 1-6.Rong Lili, Zhang Jiyong. Research on different evolution models of emergency [J] . Journal of Natural Disasters, 2012, 21(3): 1-6.
[13] 迟菲, 陈安. 突发事件耦合机理与应对策略研究 [J] . 中国安全科学学报, 2014, 24(2): 171-176.Chi Fei, Chen An. Coupling mechanism of emergency and strategies for coping with it [J] . China Safety Science Journal, 2014, 24(2): 171-176.
[14] 杨保华, 方志耕, 刘思峰,等. 基于GERTS网络的非常规突发事件情景推演共力耦合模型 [J] . 系统工程理论与实践, 2012, 32(5): 963-970.Yang Baohua, Fang Zhigen, Liu Sifeng, et al. Model of co-coupling in unconventional incidents based on GERTS network [J] . Systems Engineering-Theory & Practice, 2012, 32(5): 963-970.
[15] Kenneth H, Ian B. Hazardousness of a place: A regional ecology of damaging events [M] . Toronto: Toronto Press, 1971.
[16] Li Jian, Chen Changkun. Modeling the dynamics of disaster evolution along causality networks with cycle chains [J] . Physica A Statistical Mechanics & Its Applications, 2014, 401(401): 251–264.
[17] 石彪, 池宏, 祁明亮,等. 资源约束下的应急预案重构方法研究 [J] . 中国管理科学, 2017, 25(1):117-128.Shi Biao, Chi Hong, Qi Mingliang, et al. A study on emergency plan reconstruction with resource constrain [J] . Chinese Journal of Management Science, 2017, 25(1):117-128.
[18] Jensen F V, Nielsen T D. Bayesian networks and decision graphs [M] , 2nd Ed. New York: Springer Science Business Media, 2007.
[19] Bertero B. Earthquake engineering-from engineering seismology to performance based engineering [J] . Earthquake Spectra, 2005, 21(2): 609-611.
[20] 裘江南, 师花艳, 叶鑫,等. 基于事件的定性知识表示模型 [J] . 系统工程, 2009, 27(10): 1-8.Qiu Jiangnan, Shi Huayan, Ye Xin, et al. Qualitative knowledge representing model based on events [J] . Systems Engineering, 2009, 27(10): 1-8.
[21] 卢小丽, 于海峰. 基于知识元的突发事件风险分析 [J] . 中国管理科学, 2014, 22(8): 108-114.Lu Xiaoli, Yu Haifeng. Emergency risk analysis based on knowledge element [J] . Chinese Journal of Management Science, 2014, 22(8): 108-114.
[22] 肖盛燮, 冯玉涛, 王肇慧,等. 灾变链式阶段的演化形态特征 [J] . 岩石力学与工程学报, 2006, 25(S1): 2629-2633.Xiao Shengxie, Feng Yutao, Wang Zhaohui, et al. Shape characteristics of evolvement in chain-styled phases of disasters [J] . Chinese Journal of Rock Mechanics and Engineering, 2006, 25(S1): 2629-2633.
[23] 姜坤. 情景驱动的并发型突发事件链建模方法 [D] . 大连：大连理工大学, 2018.Jiang Kun. Scenario driven concurrent emergency chain modeling method [D] . Dalian: Dalian University of Technology, 2018.
[24] Lauritzen S L, Spiegelhalter D J. Local computations with probabilities on graphical structures and their application to expert systems [J] . Journal of the Royal Statistical Society, 1988, 50(157): 157-224.
[25] 胡玉胜. 动态Bayes网络研究及其应用 [D] . 北京：北京科技大学, 2001.Hu Yusheng. Research and application of dynamic Bayesian network [D] . Beijing: University of Science and Technology Beijing, 2001.
[26] 蒋国萍. 软件项目风险管理的贝叶斯网络模型研究 [D] . 长沙：国防科学技术大学, 2005.Jiang Guoping. Research on Bayesian network model in software project risk management [D] . Changsha: National University of Defense Technology, 2005.
[27] Renooij S. Forecast verification and the uncertain truth [C] // Proceedings of the 16th Belgium-Netherlands Conference on Artificial Intelligence,Groningen, Netherlands, Oct.21-22,2004: 275-282.
[28] 马骁霏, 仲秋雁, 曲毅,等. 基于共性知识元模型和欧氏距离的突发事件关键属性确定方法 [J] . 系统工程, 2013, 31(10): 93-97.Ma Xiaofei, Zhong Qiuyan, Qu Yi, et al. Determination method of key property of emergency based on common knowledge model and Euclidean distance [J] . Systems Engineering, 2013, 31(10): 93-97.
[29] Cooper F G, Herskovits E. A Bayesian method for the induction of probabilistic networks from data [J] . Machine Learning, 1992, 9(4): 309-347.
[30] Madsen A L, Jensen F V. Lazy propagation: A junction tree inference algorithm based on lazy evaluation [J] . Artificial Intelligence, 1999, 113(1-2): 203-245.