A multi-objective route optimization method for passenger evacuations at subway stations during a fire outbreak
-
摘要: 建立了一种地铁站乘客疏散网络，分析了网络节点的度以辨识关键节点，提出了节点失效后的修正走行疏散网络；设计了基于支持向量回归算法的闸机、楼梯/扶梯节点处乘客通行时间预测模型，分析了模型的预测性能，得到了乘客数量与通行时间的定量关系；建立了包括节点和路段通行时间的总疏散时间、总路段风险和总拥挤成本3个目标函数，构建了一种火灾爆发时地铁站乘客疏散多目标路径优化模型，提出了基于遗传算法的优化模型求解方法；模拟了火灾爆发时地铁站乘客的疏散运动，分析了路径优化模型帕累托解下的疏散效率，评估了路径优化策略的优化程度；设计了乘客动态引导微信小程序，为疏散路径推荐信息的及时发布提供了一种可能方案。研究结果表明：验证集中节点处乘客通行时间预测模型的平均绝对误差低至0.000 375，稳健指标值可高达0.999 334，说明预测数据与真实数据吻合程度高；闸机处实际采集数据与仿真数据的平均相对误差为4.9%，正态性检验、方差齐性检验和独立样本检验的显著值都大于0.05，验证了PathFinder软件可较为真实地模拟乘客运动；与正常疏散无优化策略相比，路径优化模型3组帕累托解下的优化程度分别为16.7%、15.9%、18.0%，因此，根据具体疏散场景、危险系数、服务质量要求等指标可选用相应的疏散优化策略。Abstract: A passenger evacuation network at subway stations was established, the degrees of network nodes were analyzed to identify key nodes, and a modified walking evacuation network was proposed after node failures. A time prediction model for passengers traveling through the gate and stair/escalator nodes was designed based on the support vector regression algorithm, and its prediction performance was analyzed. A quantitative relationship between the number of passengers and travel time was obtained. Three objective functions, namely the total evacuation time including the node and road section travel time, the total road risk, and the total congestion cost, were established. A multi-objective route optimization model for passenger evacuation at subway stations during a fire outbreak was constructed, and a solution method of optimization model was proposed based on the genetic algorithm. The evacuation movement of passengers at subway stations during a fire outbreak was simulated, and the evacuation efficiencies under the Pareto solution of the route optimization model was analyzed, then the optimization degree of the route optimization strategy was evaluated. A WeChat applet for passenger dynamic guidance was designed, providing a possible solution for the timely release of evacuation route recommendation information. Research results indicate that the mean absolute error of the passenger travel time prediction model at the nodes for the validation set can be as low as 0.000 375, and the robust indicator value is up to 0.999 334, indicating a high degree of consistency between predicted data and real data. The average relative error between the field collected data at the gate and the simulated data is 4.9%. The significance values of normality test, homogeneity test of variance, and independent sample test are all greater than 0.05, verifying that the PathFinder software can simulate passenger movements accurately. Compared with the normal evacuation without optimization strategies, the optimization degrees of the route optimization model under three sets of Pareto solutions are 16.7%, 15.9%, and 18.0%, respectively. Therefore, corresponding evacuation optimization strategies can be selected based on specific evacuation scenarios, risk factors, service quality requirements, and other indicators.
-
Key words:
- traffic planning /
- route planning /
- multi-objective optimization /
- passenger evacuation /
- fire /
- subway station
-
图 1 火灾下某地铁站修正走行疏散网络
Figure 1. Revised walking evacuation network of a subway station under fire
图 2 关键节点处训练集和验证集预测结果对比
Figure 2. Comparison of prediction results of training set and test set at some key nodes
图 3 关键节点处不同乘客数量的通行时间拟合曲线
Figure 3. Fitting curves of travel time with different numbers of passenger at some key nodes
图 4 两处进站闸机仿真值和实际值对比
Figure 4. Comparison between simulation results and actual results at two entrance gates
图 5 基于PyroSim软件搭建的青岛某地铁站模型
Figure 5. A subway station model in Qingdao based on PyroSim software
图 6 不同时刻地铁站内温度快照
Figure 6. Snapshots of temperature in subway station at different times
图 7 不同时刻地铁站内CO浓度快照
Figure 7. Snapshots of CO concentration in subway station at different times
图 8 不同时刻地铁站内可见度快照
Figure 8. Snapshots of visibility in subway station at different times
图 12 不同时刻地铁站乘客疏散仿真快照
Figure 12. Simulation snapshots of passenger evacuation in subway station at different times
图 13 Steering模式下站台乘客疏散过程的热力图
Figure 13. Thermal diagrams of passenger evacuation at platform under Steering mode
图 15 站台剩余乘客人数随疏散时间的变化曲线
Figure 15. Variation curves of passenger remaining number on platform with evacuation time
表 1 部分关键节点的度的值
Table 1. Values of some key nodes' degrees
节点 1~6 7~12 19~25 26~32 度 7 7 13 7 
下载: 导出CSV
表 2 乘客通行时间预测模型结果
Table 2. Prediction model results of passenger travel time
目标 训练集 验证集 MAE R2 MAE R2 1 0.000 984 0.996 493 0.000 832 0.997 389 2 0.000 428 0.998 752 0.000 379 0.999 030 3 0.000 701 0.997 730 0.000 687 0.997 999 4 0.001 097 0.996 323 0.002 379 0.995 981 5 0.000 386 0.998 876 0.000 375 0.999 334 6 0.001 559 0.995 104 0.001 773 0.994 479 7 0.000 898 0.997 269 0.000 679 0.997 171
下载: 导出CSV
表 3 95%置信区间下回归模型的显著性检验结果
Table 3. Significance test results of regression models under 95% confidence level
通行时间模型公式 R2 方差分析 F值 p T1 =-9.065e-6q2+0.137 6q+14.19 0.997 7 23 083.932 0.00 T2=2.279e-5q2+0.339 7q+16.41 0.999 1 56 929.787 0.00 T3=0.184 8q+36.75 0.997 9 50 426.833 0.00 T4=3.375e-6q2+0.136 2q+35.76 0.997 1 17 645.697 0.00 T5=-1.438e-5q2+0.336 9q+33.43 0.999 4 82 133.159 0.00 T6=-4.153e-5q2+0.190 9q+ 8.383 0.996 2 13 729.375 0.00 T7=-4.275e-6q2+0.062 6q+7.482 0.995 5 11 246.185 0.00
下载: 导出CSV
表 4 95%置信水平下实际值与仿真值的正态性检验结果
Table 4. Normality test results of actual and simulation values under 95% confidence level
进站闸机 统计值 F值 自由度 显著性 1 实际值 0.793 5 0.071 仿真值 0.826 5 0.130 2 实际值 0.978 5 0.921 仿真值 0.984 5 0.953
下载: 导出CSV
表 5 95%置信水平下实际值与仿真值的方差齐性检验结果
Table 5. Homogeneity test results of variance of actual and simulation values under 95% confidence level
进站闸机 平方和 自由度 均方 F值 显著性 1 0.9 1 0.9 0.014 0.910 2 0.9 1 0.9 0.008 0.932
下载: 导出CSV
表 6 95%置信水平下实际值和仿真值的T-独立样本检验结果
Table 6. T-independent sample test results of actual and simulation values under 95% confidence level
进站闸机 假设 T值 自由度 显著性(双尾) 平均值差值 标准误差平均值 95%置信区间 下限 上限 1 假定等方差 0.117 8 0.910 0.6 5.117 -11.119 12.399 2 假定等方差 -0.088 8 0.932 -0.6 6.812 -16.308 15.108
下载: 导出CSV
表 7 优化前后的疏散结果对比
Table 7. Comparison of evacuation results before and after optimization
帕累托解 优化前 优化后 I1/% I2/% I3/% I/% 疏散时间/s 路段风险 拥挤成本 疏散时间/s 路段风险 拥挤成本 1 232 610 7 639 225 437 3 786 0.6 16.9 32.5 16.7 2 232 610 7 639 235 433 4 192 -0.3 17.1 30.8 15.9 3 232 610 7 639 218 450 2 770 1.2 16.4 36.5 18.0
下载: 导出CSV
-
[1] 中国城市轨道交通协会. 城市轨道交通2021年度统计和分析报告[R]. 北京: 中国城市轨道交通协会, 2021.China Association of Metros. 2021 Statistical and analysis report on urban rail transit[R]. Beijing: China Association of Metros, 2021. (in Chinese) [2] YANG X X, ZHANG R, LI Y X, et al. Passenger evacuation path planning in subway station under multiple fires based on multiobjective robust optimization[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 21915-21931. doi: 10.1109/TITS.2022.3190291 [3] YU H, WANG Y M, QIU P Y, et al. Analysis of natural and man-made accidents happened in subway stations and trains: based on statistics of accident cases[C]//EDP Sciences. 2018 International Conference on Functional Materials and Chemical Engineering. Paris: EDP Sciences, 2019: 01031. [4] 陈阳光. 基于BIM的地铁车站火灾疏散研究[D]. 成都: 西南交通大学, 2023.CHEN Yang-guang. Research on fire evacuation of subway station based on BIM[D]. Chengdu: Southwest Jiaotong University, 2023. (in Chinese) [5] 王胜闯. 突发火灾下地铁站内人群疏散模型与仿真研究[D]. 沈阳: 沈阳大学, 2022.WANG Sheng-chuang. Study on crowd evacuation model and simulation in subway station under sudden fire[D]. Shenyang: Shenyang University, 2022. (in Chinese) [6] 黄昕, 靳健, 林作忠, 等. 基于A*算法的深部地下空间火灾疏散路径动态规划[J]. 北京工业大学学报, 2021, 47(7): 702-709. https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD202107005.htmHUANG Xin, JIN Jian, LIN Zuo-zhong, et al. Dynamic evacuation path planning for fire disaster of deep underground space based on A* algorithm[J]. Journal of Beijing University of Technology, 2021, 47(7): 702-709. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD202107005.htm [7] CHOI M, CHI S. Optimal route selection model for fire evacuations based on hazard prediction data[J]. Simulation Modelling Practice and Theory, 2019, 94: 321-333. doi: 10.1016/j.simpat.2019.04.002 [8] 陈一洲, 尹浩东, 孙旋, 等. 基于实时毒气影响的人群疏散路径优化研究[J]. 安全与环境学报, 2018, 18(6): 2316-2321. doi: 10.13637/j.issn.1009-6094.2018.06.049CHEN Yi-zhou, YIN Hao-dong, SUN Xuan, et al. Optimalization for the crowd masses evacuation route based on the study of the impact of real-time gas leakage[J]. Journal of Safety and Environment, 2018, 18(6): 2316-2321. (in Chinese) doi: 10.13637/j.issn.1009-6094.2018.06.049 [9] SHEN Yang, WANG Qing-song, YAN Wei-gang, et al. An evacuation model coupling with toxic effect for chemical industrial park[J]. Journal of Loss Prevention in the Process Industries, 2015, 33: 258-265. doi: 10.1016/j.jlp.2015.01.002 [10] AZADEH A, FARROKHI-ASL H. The close-open mixed multi depot vehicle routing problem considering internal and external fleet of vehicles[J]. Transportation Letters—The International Journal of Transportation Research, 2017, 11(2): 78-92. [11] 姜学鹏, 张帆, 陈欣格. 地铁隧道火灾人员疏散可靠度研究[J]. 消防科学与技术, 2020, 39(1): 9-13. https://www.cnki.com.cn/Article/CJFDTOTAL-XFKJ202001003.htmJIANG Xue-peng, ZHANG Fan, CHEN Xin-ge. Reliability research of human evacuation in subway tunnel fire[J]. Fire Science and Technology, 2020, 39(1): 9-13. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XFKJ202001003.htm [12] YANG X X, YANG Y, QU D Y, et al. Multi-objective optimization of evacuation route for heterogeneous passengers in the metro station considering node efficiency[J]. IEEE Transactions on Intelligent Transportation Systems, DOI: 10.1109/TITS.2023.3292912 .[13] LI X L, WANG H, YI S W, et al. Disaster-and-evacuation-aware backup datacenter placement based on multi-objective optimization[J]. IEEE Access, 2019, 7: 48196-48208. doi: 10.1109/ACCESS.2019.2909084 [14] 刘恒旭. 基于蚁群算法的地铁站火灾多目标疏散路径优化研究[D]. 西安: 西安建筑科技大学, 2018.LIU Heng-xu. Optimization of multi-target evacuation paths for subway stations based on ant colony algorithm[D]. Xi'an: Xi'an University of Architecture and Technology, 2018. (in Chinese) [15] HOSSEINI O, MAGHREBI M, MAGHREBI M F. Determining optimum staged-evacuation schedule considering total evacuation time, congestion severity and fire threats[J]. Safety Science, 2021, 139: 105211. doi: 10.1016/j.ssci.2021.105211 [16] 种法雯. 大型公共建筑室内火灾应急疏散路径仿真及优化研究[D]. 马鞍山: 安徽工业大学, 2018.CHONG Fa-wen. Simulation and optimization of emergency evacuation routes for indoor fires in large public buildings[D]. Maanshan: Anhui University of Technology, 2018. (in Chinese) [17] TSUKAHARA M, KOSHIBA Y, OHTANI H. Effectiveness of downward evacuation in a large-scale subway fire using Fire Dynamics Simulator[J]. Tunnelling and Underground Space Technology, 2011, 26(4): 573-581. doi: 10.1016/j.tust.2011.02.002 [18] 王婷, 杜慕皓, 唐永福, 等. 基于BIM的火灾模拟与安全疏散分析[J]. 土木建筑工程信息技术, 2014, 6(6): 102-108. doi: 10.16670/j.cnki.cn11-5823/tu.2014.06.018WANG Ting, DU Mu-hao, TANG Yong-fu, et al. Analysis on fire model and safety evacuation based on BIM[J]. Journal of Information Technology in Civil Engineering and Architecture, 2014, 6(6): 102-108. (in Chinese) doi: 10.16670/j.cnki.cn11-5823/tu.2014.06.018 [19] LI M X, ZHU S B, WANG J H, et al. Research on fire safety evacuation in a university library in Nanjing[J]. Procedia Engineering, 2018, 211: 372-378. doi: 10.1016/j.proeng.2017.12.025 [20] 邹馨捷, 萨木哈尔·波拉提, 郝明, 等. 基于Pyrosim和PathFinder的高校学生宿舍火灾人员疏散安全性模拟分析[J]. 安全与环境工程, 2020, 27(4): 195-200. https://www.cnki.com.cn/Article/CJFDTOTAL-KTAQ202004026.htmZOU Xin-jie, BOLATI S, HAO Ming, et al. Personnel evacuation safety simulation analysis of college student dormitory fire based on Pyrosim and PathFinder[J]. Safety and Environmental Engineering, 2020, 27(4): 195-200. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-KTAQ202004026.htm [21] ZHANG H, LONG H C. Simulation of evacuation in crowded places based on BIM and Pathfinder[J]. Journal of Physics: Conference Series, 2021, 1880(1): 012010. doi: 10.1088/1742-6596/1880/1/012010 [22] 王莉. 基于PATHFINDER的公共场所人员疏散行为规律及仿真模拟[J]. 西安科技大学学报, 2017, 37(3): 358-364. https://www.cnki.com.cn/Article/CJFDTOTAL-XKXB201703009.htmWANG Li. Evacuation behavior and simulation of large public places based on PATHFINDER[J]. Journal of Xi'an University of Science and Technology, 2017, 37(3): 358-364. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XKXB201703009.htm [23] SUN D J, GUAN S. Measuring vulnerability of urban metro network from line operation perspective[J]. Transportation Research Part A: Policy and Practice, 2016, 94: 348-359. doi: 10.1016/j.tra.2016.09.024 [24] FELICIANI C, NISHINARI K. Measurement of congestion and intrinsic risk in pedestrian crowds[J]. Transportation Research Part C: Emerging Technologies, 2018, 91: 124-155. [25] DAAMEN W. Modelling passenger flows in public transport facilities[D]. Delft: Netherlands Research School for Transport, 2004. [26] JIN T, YAMADA T. Irritating effects of fire smoke on visibility[J]. Fire Science and Technology, 1985, 5(1): 79-90. [27] GU B, SHENG V S, WANG Z J, et al. Incremental learning for V-support vector regression[J]. Neural Networks, 2015, 67: 140-150. [28] YANG Xiao-xia, ZHANG Rui, PAN Fu-quan, et al. Stochastic user equilibrium path planning for crowd evacuation at subway station based on social force model[J]. Physica A: Statistical Mechanics and its Applications, 2022, 594: 127033. [29] MA Chang-xi, WANG Chao, XU Xue-cai. A multi-objective robust optimization model for customized bus routes[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(4): 2359-2370. [30] YANG Xiao-xia, YANG Yi, LI Yong-xing, et al. Path planning for guided passengers during evacuation in subway station based on multi-objective optimization[J]. Applied Mathematical Modelling, 2022, 111: 777-801. [31] GUO Kai, ZHANG Li-mao. Simulation-based passenger evacuation optimization in metro stations considering multi-objectives[J]. Automation in Construction, 2022, 133: 104010. -
点击查看大图
计量
- 文章访问数: 335
- HTML全文浏览量: 57
- PDF下载量: 90
- 被引次数: 0
