基于贝叶斯学习的复杂系统研制风险演化分析
|
摘要
大型复杂装备的系统结构和研制流程呈现网络化特征,研究风险演化机理有助于控制风险、降低复杂性.通过系统动态过程建模仿真获取数据样本,运用贝叶斯学习从仿真数据样本中提炼风险演化网络,识别不同风险等级的节点之间存在的关联关系,降低了仅凭经验构建风险网络的主观性.对贝叶斯学习获得的风险网络进行概率推理,在总体高风险等级下计算风险网络节点的风险后验概率分布,进而确定风险演化关键节点和传播链路.最后,通过与复杂网络特征指标评估下的静态特征进行对比分析,研究风险网络动态特征与静态特征的差异性,结果表明网络结构特征和风险传播的动态特征共同决定了风险演化关键节点和传播链路.
System structures and developing process of large-scale complex weapon are characterized with networks.Research on risk evolution mechanism is useful to control risk and reduce complexity.Based on dynamic data samples presented by system process modeling and simulations,risk evolution networks was refined by Bayesian learning to recognize correlations among nodes with different risk levels.By this way,subjectivity is reduced than risk networks built only by experience.The risk networks from Bayesian learning was further used to implement Bayesian inference and calculate risk posterior probability distributions of risk network nodes under the conditions of system total risk at high level,and then the critical nodes and propogation chains of risk evolution were identified.Finally,comparing with static characteristics based on complex network characteristic indicators,the differences between dynamic and static characteristics of risk networks were under discussion.It is found that the critical nodes and chains of risk evolution are jointly determined by network structure characteristics and dynamic features of risk evolution.
System structures and developing process of large-scale complex weapon are characterized with networks.Research on risk evolution mechanism is useful to control risk and reduce complexity.Based on dynamic data samples presented by system process modeling and simulations,risk evolution networks was refined by Bayesian learning to recognize correlations among nodes with different risk levels.By this way,subjectivity is reduced than risk networks built only by experience.The risk networks from Bayesian learning was further used to implement Bayesian inference and calculate risk posterior probability distributions of risk network nodes under the conditions of system total risk at high level,and then the critical nodes and propogation chains of risk evolution were identified.Finally,comparing with static characteristics based on complex network characteristic indicators,the differences between dynamic and static characteristics of risk networks were under discussion.It is found that the critical nodes and chains of risk evolution are jointly determined by network structure characteristics and dynamic features of risk evolution.
引文
[1]Li C,Wang K.The risk element transmission theory research of multi-objective risk-time-cost trade-off[J].Computers and Mathematics with Applications,2009,57(11):1792-1799.
[2]Garg T.Estimating change propagation risk using TRLs and system architecture[D].Massachusetts:Massachusetts Institute of Technology,2017.
[3]Eusgeld I,Kroger W,Sansavini G,et al.The role of network theory and object-oriented modeling within a framework for the vulnerability analysis of critical infrastructures[J].Reliability Engineering&System Safety,2009,94(5):954-963.
[4]Fang C,Marle F,Zio E,et al.Network theory-based analysis of risk interactions in large engineering projects[J].Reliability Engineering&System Safety,2012,106(2):1-10.
[5]赵贤利,罗帆.基于复杂网络理论的机场飞行区风险演化模型研究[J].电子科技大学学报(社会科学版),2013,15(4):31-34.Zhao X L,Luo F.Research on the risks evolution model based on complex networks in airport flight area[J].Journal of University of Electronic Science&Technology of China, 2013,15(4):31-34.
[6]肖盛,张建华,肖河.基于复杂网络理论与风险理论的地区电网脆弱性评估[J].电网与清洁能源,2013,29(6):21-28.Xiao S,Zhang J H,Xiao H.Vulnerability assessment of a regional power grid based on complex network theory and risk theory[J].Power System&Clean Energy,2013,29(6):21-28.
[7]赵阳,李华强,王伊渺,等·基于复杂网络理论和条件概率的灾难性事故风险评估方法[J].电网技术,2013,37(11):3190-3196.Zhao Y,Li H Q,Wang Y M,et al.A complex network theory and conditional probability based risk assessment method for disastrous accidents[J].Power System Technology,2013,37(11):3190-3196.
[8]覃璇,李仲学,赵怡晴.尾矿库风险演化复杂网络模型及关键隐患分析[J].系统工程理论与实践,2017,37(6):1648-1653.Qin X,LI Z X,Zhao Y Q.A complex network model for analyzing risks and major hazards of tailing impoundments[J].Systems Engineering—Theory&Practice,2017,37(6):1648-1653.
[9]Lee E,Park Y,Shin J G.Large engineering project risk management using a Bayesian belief network[J].Expert Systems with Applications,2009,36(3):5880-5887.
[10]Qazi A,Quigley J,Dickson A,et al.Evaluation of control strategies for managing supply chain risks using Bayesian belief networks[C]//Proceeding of International Conference on Industrial Engineering and Systems Management International Conference on Industrial Engineering and Systems Management,Seville,Spain,2016:1146-1154.
[11]Eppinger S,Browning T.Design structure matrix methods and applications[M].Massachusetts,USA:MIT Press,2012.
[12]Weber P,MedinarOliva G,Simon C,et al.Overview on Bayesian networks applications for dependability,risk analysis and maintenance areas[J].Engineering Applications of Artificial Intelligence,2012,25(4):671-682.
[13]徐青.舰船总体设计流程分析[J].中国舰船研究,2012,7(5):1-7.Xu Q.Analysis of the overall warship design process[J].Chinese Journal of Ship Research,2012,7(5):1-7.
[14]郭世泽,陆哲明.复杂网络基础理论[M].北京:科学出版社,2012.Guo S Z,Lu Z M.Foundation of complex networks[M].Beijing:Science Press,2012.
[2]Garg T.Estimating change propagation risk using TRLs and system architecture[D].Massachusetts:Massachusetts Institute of Technology,2017.
[3]Eusgeld I,Kroger W,Sansavini G,et al.The role of network theory and object-oriented modeling within a framework for the vulnerability analysis of critical infrastructures[J].Reliability Engineering&System Safety,2009,94(5):954-963.
[4]Fang C,Marle F,Zio E,et al.Network theory-based analysis of risk interactions in large engineering projects[J].Reliability Engineering&System Safety,2012,106(2):1-10.
[5]赵贤利,罗帆.基于复杂网络理论的机场飞行区风险演化模型研究[J].电子科技大学学报(社会科学版),2013,15(4):31-34.Zhao X L,Luo F.Research on the risks evolution model based on complex networks in airport flight area[J].Journal of University of Electronic Science&Technology of China, 2013,15(4):31-34.
[6]肖盛,张建华,肖河.基于复杂网络理论与风险理论的地区电网脆弱性评估[J].电网与清洁能源,2013,29(6):21-28.Xiao S,Zhang J H,Xiao H.Vulnerability assessment of a regional power grid based on complex network theory and risk theory[J].Power System&Clean Energy,2013,29(6):21-28.
[7]赵阳,李华强,王伊渺,等·基于复杂网络理论和条件概率的灾难性事故风险评估方法[J].电网技术,2013,37(11):3190-3196.Zhao Y,Li H Q,Wang Y M,et al.A complex network theory and conditional probability based risk assessment method for disastrous accidents[J].Power System Technology,2013,37(11):3190-3196.
[8]覃璇,李仲学,赵怡晴.尾矿库风险演化复杂网络模型及关键隐患分析[J].系统工程理论与实践,2017,37(6):1648-1653.Qin X,LI Z X,Zhao Y Q.A complex network model for analyzing risks and major hazards of tailing impoundments[J].Systems Engineering—Theory&Practice,2017,37(6):1648-1653.
[9]Lee E,Park Y,Shin J G.Large engineering project risk management using a Bayesian belief network[J].Expert Systems with Applications,2009,36(3):5880-5887.
[10]Qazi A,Quigley J,Dickson A,et al.Evaluation of control strategies for managing supply chain risks using Bayesian belief networks[C]//Proceeding of International Conference on Industrial Engineering and Systems Management International Conference on Industrial Engineering and Systems Management,Seville,Spain,2016:1146-1154.
[11]Eppinger S,Browning T.Design structure matrix methods and applications[M].Massachusetts,USA:MIT Press,2012.
[12]Weber P,MedinarOliva G,Simon C,et al.Overview on Bayesian networks applications for dependability,risk analysis and maintenance areas[J].Engineering Applications of Artificial Intelligence,2012,25(4):671-682.
[13]徐青.舰船总体设计流程分析[J].中国舰船研究,2012,7(5):1-7.Xu Q.Analysis of the overall warship design process[J].Chinese Journal of Ship Research,2012,7(5):1-7.
[14]郭世泽,陆哲明.复杂网络基础理论[M].北京:科学出版社,2012.Guo S Z,Lu Z M.Foundation of complex networks[M].Beijing:Science Press,2012.