地铁站乘客沿楼梯上行疏散时间预测及安全性评估

doi:10.16265/j.cnki.issn1003-3033.2023.05.1263

中国安全科学学报 ›› 2023, Vol. 33 ›› Issue (5): 168-173.doi: 10.16265/j.cnki.issn1003-3033.2023.05.1263

地铁站乘客沿楼梯上行疏散时间预测及安全性评估

杨晓霞¹(), 蒋海龙², 李永行³, 潘福全², 杨金顺²

¹ 青岛理工大学信息与控制工程学院,青岛山东 266520
² 青岛理工大学土木工程学院,青岛山东 266520
³ 北京工业大学北京市交通工程重点实验室,北京 100124

收稿日期:2022-12-21 修回日期:2023-03-15 出版日期:2023-05-28
作者简介:
杨晓霞 (1988—),女,山东烟台人,博士,副教授,主要从事智能交通与协同控制、人工智能等方面的研究。E-mail:yangxiaoxiaaza@163.com。
基金资助:
国家自然科学基金资助(62003182)

Prediction of evacuation time and safety evaluation for passengers ascending stairs in subway stations

YANG Xiaoxia¹(), JIANG Hailong², LI Yongxing³, PAN Fuquan², YANG Jinshun²

¹ School of Information and Control Engineering, Qingdao University of Technology, Qingdao Shandong 266520, China
² School of Civil Engineering, Qingdao University of Technology, Qingdao Shandong 266520, China
³ Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, China

Received:2022-12-21 Revised:2023-03-15 Published:2023-05-28

摘要/Abstract

摘要：

为提高地铁站乘客疏散时的安全指数,有必要对瓶颈区域楼梯处的乘客疏散时间进行预测以评估其通行安全性。首先,针对地铁站乘客沿楼梯上行疏散数据难以采集的问题,采用MassMotion仿真软件搭建楼梯场景,模拟乘客沿楼梯上行疏散行为,获取疏散时间基础数据;然后,利用基础数据训练和测试随机森林模型,实现乘客沿楼梯上行疏散时间的预测;最后,以疏散时间、乘客密度、疏散恐慌度为指标,建立疏散安全综合评估模型,用于评估地铁站乘客沿楼梯上行的疏散安全等级。结果表明:所采用的随机森林模型预测结果的平均绝对误差(MAE)为3.45 s,平均绝对百分比误差(MAPE)为3.8%,相较于反向传播神经网络(BPNN)模型和支持向量回归(SVR)模型具有更高的预测准确度;采用疏散安全综合评估模型评估青岛某地铁站的楼梯安全性,得到早高峰时期的疏散安全性评估值为中等。

关键词: 地铁站, 楼梯, 疏散时间, 安全性评估, 随机森林模型, MassMotion

Abstract:

Stairs are the bottleneck areas in the process of passenger evacuation in the subway station. The safety assessment of passengers passing through the stairs helps to formulate the evacuation plan in advance. Firstly, aiming at the difficulty of collecting the evacuation data of passengers ascending the stairs, MassMotion simulation software was adopted to build a stair scene to simulate the evacuation behavior of passengers ascending the stairs, and the basic data of evacuation time were obtained. Then, the random forest model was trained and tested with basic data to predict the evacuation time of passengers ascending the stairs. Finally, a comprehensive evaluation model of evacuation safety was established, and the evacuation safety level of passengers ascending the stairs in the subway station was evaluated with evacuation time, passenger density and evacuation panic as indicators. The research results indicate that mean absolute error(MAE) of the prediction results of the random forest model used in this paper is 3.45 s, and mean absolute percentage error (MAPE) is 3.8%. Compared with back propagation neural network (BPNN) model and support vector regression (SVR) model, the prediction accuracy is higher. The comprehensive evaluation model of evacuation safety is used to evaluate the safety of the stairs in a subway station in Qingdao, and the evaluation value of evacuation safety in the early peak period is medium.

Key words: subway station, stairs, evacuation time, safety evaluation, random forest model, MassMotion

杨晓霞, 蒋海龙, 李永行, 潘福全, 杨金顺. 地铁站乘客沿楼梯上行疏散时间预测及安全性评估[J]. 中国安全科学学报, 2023, 33(5): 168-173.

YANG Xiaoxia, JIANG Hailong, LI Yongxing, PAN Fuquan, YANG Jinshun. Prediction of evacuation time and safety evaluation for passengers ascending stairs in subway stations[J]. China Safety Science Journal, 2023, 33(5): 168-173.

图/表 7

图1

表1

表2

表3

图2

表4

表5

参考文献 14

[1]	LUO Lin, LUO Yangqi, FENG Yujing, et al. Experimental investigation on pedestrian-bicycle mixed merging flow in T-junction[J]. Physica A: Statistical Mechanics and its Applications, 2022, 600:DOI: 10.1016/j.physa.2022.127492. doi: 10.1016/j.physa.2022.127492
[2]	YANG Xiaoxia, ZHANG Rui, PAN Fuquan, 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:DOI: 10.1016/j.physa.2022.127033. doi: 10.1016/j.physa.2022.127033
[3]	YANG Xiaoxia, ZHANG Rui, LI Yongxing, et al. Passenger evacuation path planning in subway station under multiple fires based on multi-objective robust optimization[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 99: DOI: 10.1109/TITS.2022.3190291. doi: 10.1109/TITS.2022.3190291
[4]	曹淑超, 席鑫, 倪璟煜, 等. 考虑群组行为的楼梯瓶颈处行人流模拟[J]. 中国安全科学学报, 2022, 32(2):28-33. doi: 10.16265/j.cnki.issn1003-3033.2022.02.005
	CAO Shuchao, XI Xin, NI Jingyu, et al. Simulation of pedestrian flow at bottleneck of stairs considering group behavior[J]. China Safety Science Journal, 2022, 32(2):28-33. doi: 10.16265/j.cnki.issn1003-3033.2022.02.005
[5]	WANG Jianyu, MA Jian, LIN Peng, et al. Pedestrian single file movement on stairway: investigating the impact of stair configuration on pedestrian ascent and descent fundamental diagram[J]. Safety Science, 2021, 143:DOI: 10.1016/j.ssci.2021.105409. doi: 10.1016/j.ssci.2021.105409
[6]	LAM J H T, YUEN J K K, LEE EWM, et al. Experimental study on upward movement in a high-rise building[J]. Safety Science, 2014, 70:397-405. doi: 10.1016/j.ssci.2014.07.011
[7]	张新生, 蔡宝泉. 基于改进随机森林模型的海底管道腐蚀预测[J]. 中国安全科学学报, 2021, 31(8): 69-74. doi: 10.16265/j.cnki.issn1003-3033.2021.08.010
	ZHANG Xinsheng, CAI Baoquan. Corrosion prediction of submarine pipelines based on improved random forest model[J]. China Safety Science Journal, 2021, 31(8):69-74. doi: 10.16265/j.cnki.issn1003-3033.2021.08.010
[8]	姚明, 温鹏景, 曹淑超, 等. 基于群组行为的大学校园楼梯及通道行人运动特征分析[J]. 交通运输系统工程与信息, 2019, 19(5): 242-250.
	YAO Ming, WEN Pengjing, CAO Shuchao, et al. Movement characteristics of pedestrian social groups in staircase and corridor on university campus[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(5): 242-250.
[9]	李泽群, 闫丰亭, 史志才, 等. 基于多智能体的虚拟化地铁站乘客行为仿真[J]. 系统仿真学报, 2020, 32(12):2341-2352. doi: 10.16182/j.issn1004731x.joss.20-FZ0431
	LI Zequn, YAN Fengting, SHI Zhicai, et al. Multi-agent behavior simulation for metro station passenger[J]. Journal of System Simulation, 2020, 32(12):2341-2352. doi: 10.16182/j.issn1004731x.joss.20-FZ0431
[10]	陈天. 基于异质行人流仿真的地铁进站闸机设施布局优化设计研究[D]. 南京: 东南大学, 2019.
	CHEN Tian. Optimizing the layout design of inbound ticket gates in metro station based on heterogeneous pedestrian flow simulation[D]. Nanjing: Southeast University, 2019.
[11]	GB/T 33668—2017, 地铁安全疏散规范[S].
	GT/T 33668-2017, Code for safety evacuation of metro[S].
[12]	冯涛. 基于Anylogic的突发情况下地铁车站行人疏散风险管理研究[D]. 成都: 西南交通大学, 2021.
	FENG Tao. Research on risk management of pedestrian evacuation in metro stations in emergency situations based on Anylogic[D]. Chengdu: Southwest Jiaotong University, 2021.
[13]	王春雪, 索晓, 吕淑然, 等. 地铁应急疏散恐慌程度模型研究[J]. 中国安全科学学报, 2015, 25(2): 171-176.
	WANG Chunxue, SUO Xiao, LYU Shuran, et al. Research on panic degree model of emergency evacuation from subway[J]. China Safety Science Journal, 2015, 25(2):171-176.
[14]	吴仁彪, 何宇翔, 贾云飞. 基于改进层次分析法的重点人员风险评价方法[J]. 中国安全科学学报, 2021, 31(10): 112-118. doi: 10.16265/j.cnki.issn1003-3033.2021.10.016
	WU Renbiao, HE Yuxiang, JIA Yunfei. Key personnel risk assessment method based on improved AHP[J]. China Safety Science Journal, 2021, 31(10):112-118. doi: 10.16265/j.cnki.issn1003-3033.2021.10.016

模型	误差
模型	MAE/s	MSE	RMSE/s	MAPE/%
随机森林模型	3.45	20.09	4.48	3.8
BPNN模型	3.94	21.94	4.68	4.7
SVR模型	4.43	31.81	5.64	6.0

项	特征向量	权重值	最大特征根	CI
时间指标	2.320 8	0.625	3	0
密度指标	0.928 3	0.25
恐慌指标	0.464 2	0.125

[1]	孙世梅, 张家严. 基于24Model-D-ISM的地铁站火灾疏散影响因素研究[J]. 中国安全科学学报, 2024, 34(4): 153-159.
[2]	陈娜, 郭浩然, 张志鹏, 赵军. 基于H-OWA算子和投影寻踪的地铁站水灾安全韧性评估[J]. 中国安全科学学报, 2023, 33(4): 148-154.
[3]	王美娜, 姜学鹏, 王启睿, 蒲婷, 彭义. 悬挂式轨道列车区间疏散模式安全性研究[J]. 中国安全科学学报, 2023, 33(4): 163-171.
[4]	吕伟, 汪京辉, 李加伟, 陈文涛, 房志明. 火灾场景下宽体客机人员疏散风险分析[J]. 中国安全科学学报, 2023, 33(3): 141-146.
[5]	蔡佳良, 李凯玲, 屈璐, 魏刘阳, 李瑶. 基于协助比的特殊人群疏散时间影响研究[J]. 中国安全科学学报, 2023, 33(3): 161-166.
[6]	孙华锴, 陈长坤, 翁佳俊, 朱凯, 吴珂. 考虑视觉障碍行人的疏散模型[J]. 中国安全科学学报, 2023, 33(12): 183-191.
[7]	曹淑超, 席鑫, 倪璟煜, 姚明. 考虑群组行为的楼梯瓶颈处行人流模拟[J]. 中国安全科学学报, 2022, 32(2): 28-33.
[8]	王凯, 胡经纬, 杨涛, 蔡炜垚, 王建华, 陈瑞鼎. 地铁站火灾烟流特性及协同集控系统[J]. 中国安全科学学报, 2022, 32(12): 133-140.
[9]	庄异凡, 黄家骏, 刘志钢, 杨立中, 潘寒川. 步行通道入口汇流人群渠化策略安全性评估方法[J]. 中国安全科学学报, 2022, 32(11): 184-191.
[10]	戢晓峰, 乔新, 普永明, 卢梦媛, 郝京京. 地铁站周边建成环境对交通事故风险的影响机制[J]. 中国安全科学学报, 2022, 32(10): 162-170.
[11]	于萍. 邮轮应急疏散过程建模、模拟与布局优化分析^*[J]. 中国安全科学学报, 2021, 31(9): 142-149.
[12]	巫诚诚, 陈大伟. 基于视域分析的高速施工交通组织安全性评估[J]. 中国安全科学学报, 2020, 30(5): 122-128.
[13]	成艳英, 谢玮, 张玉春, 彭奇, 刘劼玮, 陈柯. 公路隧道人员疏散时间计算模型及应用[J]. 中国安全科学学报, 2020, 30(4): 121-126.
[14]	胡瑞, 徐传玲, 冯永泰, 文超, 王全泉. 广深高速铁路列车分类型晚点预测^*[J]. 中国安全科学学报, 2019, 29(S2): 181-186.
[15]	张硕, 黄榕, 余强. 大型客车乘客疏散特性与制约因素试验研究[J]. 中国安全科学学报, 2019, 29(9): 181-187.

地铁站乘客沿楼梯上行疏散时间预测及安全性评估

Prediction of evacuation time and safety evaluation for passengers ascending stairs in subway stations

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 14

相关文章 15

编辑推荐

Metrics

本文评价