基于C-OWA算子和BP神经网络的地铁车站火灾安全评价
|
摘要
为克服地铁车站火灾安全指标动态性变化、耦合性作用等特征导致管理人员难以借助传统数理统计方法对车站安全做出科学且具有延展性评价的难题,提出构建基于C-OWA算子和BP神经网络的地铁车站火灾安全评价模型。首先,根据火灾发生的不同阶段并考虑人员疏散因素,构建地铁车站火灾安全评价指标体系;然后,利用C-OWA算子对专家决策数据重新集结处理,削弱个别极值对权重的影响,提高赋权的科学性;最后,利用BP神经网络连续自适应学习和反馈能力模拟指标复杂的耦合关系。将该模型运用在郑州地铁2号线紫荆山车站的火灾安全评价中,结果表明该车站火灾安全性高。
It is difficult for managers to make scientific and extensible evaluation on metro station safety based on traditional mathematical statistical method induced by dynamic variation of fire safety indices of metro stations and coupling effect. Hence,a safety evaluation model for metro station in case of fire based on C-OWA operator and BP neural network is proposed. Firstly,a fire safety evaluation index system for metro station is established from the aspect of different stages of fire and considering the factors of personnel evacuation. And then the C-OWA operator is used to regroup the decision-making data of experts to weaken the influence of individual extreme value on the weight and improve the scientificity of empowerment. Finally,the continuous adaptive learning and feedback capabilities of BP neural network are used to simulate the complex coupling of indices. The model is applied to the evaluation of fire safety of Zijinshan Station on Line 2 of Zhengzhou Metro; and the results show that the fire safety level of the station is high.
It is difficult for managers to make scientific and extensible evaluation on metro station safety based on traditional mathematical statistical method induced by dynamic variation of fire safety indices of metro stations and coupling effect. Hence,a safety evaluation model for metro station in case of fire based on C-OWA operator and BP neural network is proposed. Firstly,a fire safety evaluation index system for metro station is established from the aspect of different stages of fire and considering the factors of personnel evacuation. And then the C-OWA operator is used to regroup the decision-making data of experts to weaken the influence of individual extreme value on the weight and improve the scientificity of empowerment. Finally,the continuous adaptive learning and feedback capabilities of BP neural network are used to simulate the complex coupling of indices. The model is applied to the evaluation of fire safety of Zijinshan Station on Line 2 of Zhengzhou Metro; and the results show that the fire safety level of the station is high.
引文
[1]刘钊,佘才高,周振强.地铁工程设计与施工[M].北京:人民交通出版社,2004.LIU Zhao,SHE Caigao,ZHOU Zhenqiang.Design and construction of metro engineering[M].Beijing:China Communications Press,2004.
[2]马一太,曾宪阳,刘万福.地铁火灾危险性的模糊综合评判[J].铁道学报,2006,28(3):106.MA Yitai,ZENG Xianyang,LIU Wanfu.Comprehensive fuzzy evaluation of subway fire danger[J].Journal of the China Railway Socilety,2006,28(3):106.
[3]睢羽,宋守信.基于投影寻踪聚类思想的地铁火灾二次事故风险评估[J].消防科学与技术,2013,32(7):789.SUI Yu,SONG Shouxin.Secondary accident risk caused by subway fire based on projection pursuit clustering method[J].Fire Science and Technoligy,2013,32(7):789.
[4]JOHANSSON H,MALMNAS P E.Application of supersoft decision theory in fire risk assessment[J].Journal of Fire Protection Engineering,2004,14(1):55.
[5]CHOI H H,CHO H N,SEO J W.Risk assessment methodology for underground contruction project[J].Journal of Construction Engineering and Management,2004:130(2):258.
[6]李炎锋,石勃伟,王超,等.城市地下轨道交通火灾风险评估体系模型研究:以某地铁车站为例[J].防灾减灾工程学报,2010,30(6):680.LI Yanfeng,SHI Bowei,WANG Chao,et al.Study of fire risk assessment system for urban underground rail traffic:A subway station is selected as example[J].Journal of Disaster Prevention and Mitigation Engineering,2010,30(6):680.
[7]赵海荣,徐晓虎,郭欣承.基于G1法的地铁换乘站火灾风险模糊综合评价[C]//2012(沈阳)国际安全科学与技术学术研讨会论文集.沈阳:东北大学,2012:360.ZHAO Hairong,XU Xiaohu,GUO Xincheng.Fuzzy comprehensive evaluation on metro interchange station fire risk based on G1 method[C]//Proceedings of 2012(Shenyang)International Colloquium on Safety Science and Technology.Shenyang:Northeastern University,2012:360.
[8]褚鹏宇,刘澜,尹俊淞.基于动态变权模糊Petri网的地铁火灾风险评估[J].安全与环境学报,2016,16(6):39.CHU Pengyu,LIU Lan,YIN Junsong.On the subway fire risk assessment based on the dynamically variable weight Petri net[J].Journal of Safety and Environment,2016,16(6):39.
[9]马剑,叶新,林鹏.基于证据理论的地铁火灾安全评价方法[J].中国安全生产科学技术,2017,13(1):134.MA Jian,YE Xin,LIN Peng.Safety evaluation method of subway fire based on evidence theory[J].Journal of Safety Science and Technology,2017,13(1):134.
[10]李江华.SOM神经网络在地铁车站火灾风险评价中的应用[J].现代交通技术,2014,11(5):77.LI Jianghua.Application of SOM neural network in metro station fire risk assessment[J].Modern Transportation Technology,2014,11(5):77.
[11]喻茗之,张村峰.基于优化的神经网络的地铁火灾风险评价[J].消防科学与技术,2016,35(6):847.YU Mingzhi,ZHANG Cunfeng.Subway fire risk assessment based on optimized neural network[J].Fire Science and Technology,2016,35(6):847.
[12]YAGER R R.Families of OWA operators[J].Fuzzy Sets and Systems,1993,59(2):125.
[13]赵金先,李龙,刘敏.基于OWA算子赋权的地铁工程项目管理绩效灰色评价[J].建筑经济,2014,35(9):125.ZHAO Jinxian,LI Long,LIU Min.Gray evaluation of metro project performance management based on OWA operator weights[J].Construction Economy,2014,35(9):125.
[14]王煜,徐泽水.OWA算子赋权新方法[J].数学的实践与认识,2008,38(3):51.WANG Yu,XU Zeshui.A new method of giving OWA weights[J].Mathematics in Practice and Theory,2008,38(3):51.
[15]宋博,武瑞娟,牛发阳.基于OWA与灰色聚类的城市轨道交通PPP融资风险评价方法研究[J].隧道建设,2017,37(4):435.SONG Bo,WU Ruijuan,NIU Fayang.Research on risk evaluation method of PPP financing mode for urban rail transit based on OWA and grey clustering method[J].Tunnel Construction,2017,37(4):435.
[16]睢羽,宋守信.地铁火灾二次事故BP神经网络安全评价方法研究[J].火灾科学,2013,22(1):44.SUI Yu,SONG Shouxin.BP neural networks assessment model of secondary accident risk caused by subway fire[J].Fire Safety Science,2013,22(1):44.
[2]马一太,曾宪阳,刘万福.地铁火灾危险性的模糊综合评判[J].铁道学报,2006,28(3):106.MA Yitai,ZENG Xianyang,LIU Wanfu.Comprehensive fuzzy evaluation of subway fire danger[J].Journal of the China Railway Socilety,2006,28(3):106.
[3]睢羽,宋守信.基于投影寻踪聚类思想的地铁火灾二次事故风险评估[J].消防科学与技术,2013,32(7):789.SUI Yu,SONG Shouxin.Secondary accident risk caused by subway fire based on projection pursuit clustering method[J].Fire Science and Technoligy,2013,32(7):789.
[4]JOHANSSON H,MALMNAS P E.Application of supersoft decision theory in fire risk assessment[J].Journal of Fire Protection Engineering,2004,14(1):55.
[5]CHOI H H,CHO H N,SEO J W.Risk assessment methodology for underground contruction project[J].Journal of Construction Engineering and Management,2004:130(2):258.
[6]李炎锋,石勃伟,王超,等.城市地下轨道交通火灾风险评估体系模型研究:以某地铁车站为例[J].防灾减灾工程学报,2010,30(6):680.LI Yanfeng,SHI Bowei,WANG Chao,et al.Study of fire risk assessment system for urban underground rail traffic:A subway station is selected as example[J].Journal of Disaster Prevention and Mitigation Engineering,2010,30(6):680.
[7]赵海荣,徐晓虎,郭欣承.基于G1法的地铁换乘站火灾风险模糊综合评价[C]//2012(沈阳)国际安全科学与技术学术研讨会论文集.沈阳:东北大学,2012:360.ZHAO Hairong,XU Xiaohu,GUO Xincheng.Fuzzy comprehensive evaluation on metro interchange station fire risk based on G1 method[C]//Proceedings of 2012(Shenyang)International Colloquium on Safety Science and Technology.Shenyang:Northeastern University,2012:360.
[8]褚鹏宇,刘澜,尹俊淞.基于动态变权模糊Petri网的地铁火灾风险评估[J].安全与环境学报,2016,16(6):39.CHU Pengyu,LIU Lan,YIN Junsong.On the subway fire risk assessment based on the dynamically variable weight Petri net[J].Journal of Safety and Environment,2016,16(6):39.
[9]马剑,叶新,林鹏.基于证据理论的地铁火灾安全评价方法[J].中国安全生产科学技术,2017,13(1):134.MA Jian,YE Xin,LIN Peng.Safety evaluation method of subway fire based on evidence theory[J].Journal of Safety Science and Technology,2017,13(1):134.
[10]李江华.SOM神经网络在地铁车站火灾风险评价中的应用[J].现代交通技术,2014,11(5):77.LI Jianghua.Application of SOM neural network in metro station fire risk assessment[J].Modern Transportation Technology,2014,11(5):77.
[11]喻茗之,张村峰.基于优化的神经网络的地铁火灾风险评价[J].消防科学与技术,2016,35(6):847.YU Mingzhi,ZHANG Cunfeng.Subway fire risk assessment based on optimized neural network[J].Fire Science and Technology,2016,35(6):847.
[12]YAGER R R.Families of OWA operators[J].Fuzzy Sets and Systems,1993,59(2):125.
[13]赵金先,李龙,刘敏.基于OWA算子赋权的地铁工程项目管理绩效灰色评价[J].建筑经济,2014,35(9):125.ZHAO Jinxian,LI Long,LIU Min.Gray evaluation of metro project performance management based on OWA operator weights[J].Construction Economy,2014,35(9):125.
[14]王煜,徐泽水.OWA算子赋权新方法[J].数学的实践与认识,2008,38(3):51.WANG Yu,XU Zeshui.A new method of giving OWA weights[J].Mathematics in Practice and Theory,2008,38(3):51.
[15]宋博,武瑞娟,牛发阳.基于OWA与灰色聚类的城市轨道交通PPP融资风险评价方法研究[J].隧道建设,2017,37(4):435.SONG Bo,WU Ruijuan,NIU Fayang.Research on risk evaluation method of PPP financing mode for urban rail transit based on OWA and grey clustering method[J].Tunnel Construction,2017,37(4):435.
[16]睢羽,宋守信.地铁火灾二次事故BP神经网络安全评价方法研究[J].火灾科学,2013,22(1):44.SUI Yu,SONG Shouxin.BP neural networks assessment model of secondary accident risk caused by subway fire[J].Fire Safety Science,2013,22(1):44.