Risk analysis of metro station passenger flow based on passenger flow patterns
LI Zihao1, TIAN Xiangliang1, LI Zhongwen2, ZHOU Wei2, ZHOU Zhijie2, ZHONG Maohua1
1. Institute of Public Safety Research, Department of Engineering Physics, Tsinghua University, Beijing 100084, China; 2. Shenzhen Metro Co., Ltd, Shenzhen 518026, China
摘要地铁车站类型识别和客流风险识别对地铁安全运营管理有着重要的作用。基于深圳地铁AFC（automatic fare collection）系统数据，采用无关值和异常值清理、聚合、均值滤波、标准化、主成分分析等数据清洗步骤，提取不同时段客流比例、不同天数客流比例和换乘客流比例等特征。运用Gauss混合模型（GMM）对工作日和周末客流进行聚类，分析客流出行规律，辨识车站类型及其对应的客流风险时段，提出车站客流风险分析方法，通过大数据分析对车站类型和客流风险进行识别。分析结果对掌握车站大客流风险情况，避免大客流冲击造成的拥挤踩踏等群体性事件的发生，保障乘客安全具有指导意义。
Abstract：The safe operation and management of metro systems are related to the metro station design and the passenger flow rates into and out of stations and between stations. This study examines the passenger flow rates in and out of each station at various times on various days by filtering and standardizing the automatic fare collection (AFC) system data of the Shenzhen metro system. The data was analyzed using a principle component analysis (PCA) and a Gaussian mixture model (GMM) to cluster passenger movement data on weekdays and weekends to simplify analysis of the passenger flow patterns. The results were then used to identify time periods and types of metro stations having greater risks as a passenger flow risk analysis method for metro stations. This big data analysis can identify risk conditions for large passenger volumes to avoid mass incidents like stampedes so as to protect passenger safety.
李子浩, 田向亮, 黎忠文, 周炜, 周志杰, 钟茂华. 基于客流规律的地铁车站客流风险分析[J]. 清华大学学报（自然科学版）, 2019, 59(10): 854-860.
LI Zihao, TIAN Xiangliang, LI Zhongwen, ZHOU Wei, ZHOU Zhijie, ZHONG Maohua. Risk analysis of metro station passenger flow based on passenger flow patterns. Journal of Tsinghua University(Science and Technology), 2019, 59(10): 854-860.
[1] 顾保南, 杨照, 徐雷, 等. 1997-2017年中国城市轨道交通发展统计分析[J]. 城市轨道交通研究, 2018, 21(5):85-89.GU B N, YANG Z, XU L, et al. Statistical analysis of urban rail transit lines in China from 1997 to 2017[J]. Urban Mass Transit, 2018, 21(5):85-89. (in Chinese) [2] RATTI C, PULSELLI R M, WILLIAMS S, et al. Mobile landscapes:Using location data from cell phones for urban analysis[J]. Environment & Planning B-Planning & Design, 2006, 33(5):727-748. [3] GONZALEZ M C, HIDALGO C A, BARABASI A L. Understanding individual human mobility patterns[J]. Nature, 2008, 453:779-782. [4] ANAS A, ARNOTT R, SMALL K A. Urban Spatial Structure[J]. Journal of Economic Literature, 1998, 36(3):1426-1464. [5] 曹瑞, 涂伟, 巢佰崇, 等. 基于智能卡数据的地铁周边职住用地识别与分析[J]. 测绘地理信息, 2016, 41(3):74-78.CAO R, TU W, CHAO B C, et al. Identification and analysis of home and work regions in the vicinity of metro stations using smart card data[J]. Journal of Geomatics, 2016, 41(3):74-78. (in Chinese) [6] XIAO J Y, SHEN Y J, GE J F, et al. Evaluating urban expansion and land use change in Shijiazhuang, China, by using GIS and remote sensing[J]. Landscape & Urban Planning, 2006, 75(1):69-80. [7] ZHOU S H, DENG L F, HUANG M Y. Spatial analysis of commuting mode choice in Guangzhou, China[J]. Chinese Geographical Science, 2013, 23(3):353-364. [8] CHOI J, LEE Y J, KIM T, et al. An analysis of metro ridership at the station-to-station level in Seoul[J]. Transportation, 2012, 39(3):705-722. [9] READES J, ZHONG C, MANLEY E, et al. Finding pearls in London's oysters[J]. Built Environment, 2016, 42(3):365-381. [10] 金磊, 彭建, 柳昆, 等. 城市地铁车站分类理论及方法研究[J]. 地下空间与工程学报, 2010, 6(S1):1339-1342+1375.JIN L, PENG J, LIU K, et al. Sorting theory and investigation of urban metro station[J]. Chinese Journal of Underground Space and Engineering, 2010, 6(S1):1339-1342, 1375. (in Chinese) [11] 尹芹, 孟斌, 张丽英. 基于客流特征的北京地铁站点类型识别[J]. 地理科学进展, 2016, 35(1):126-134.YIN Q, MENG B, ZHANG L Y. Classification of subway stations in Beijing based on passenger flow characteristics[J]. Progress in Geography, 2016, 35(1):126-134. (in Chinese) [12] 高勃, 秦勇, 肖雪梅, 等. 基于K-means的北京地铁路网重要度聚类分析[J]. 交通运输系统工程与信息, 2014, 14(3):207-213.GAO B, QIN Y, XIAO X M, et al. K-means clustering analysis of key nodes and edges in Beijing subway network[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(3):207-213. (in Chinese) [13] 冷彪, 赵文远. 基于客流数据的区域出行特征聚类[J]. 计算机研究与发展, 2014, 51(12):2653-2662.LENG B, ZHAO W Y. Region ridership characteristic clustering using passenger flow data[J]. Journal of Computer Research and Development, 2014, 51(12):2653-2662. (in Chinese) [14] 余丽洁, 李岩, 陈宽民. 基于谱聚类的城市轨道站点分类方法[J]. 交通信息与安全, 2014, 32(1):122-125, 129.YU L J, LI Y, CHEN K M. Using spectral clustering for urban rail station classification[J]. Journal of Transport Information and Safety, 2014, 32(1):122-125, 129. (in Chinese) [15] KUSAKABE T, ASAKURA Y. Behavioural data mining of transit smart card data:A data fusion approach[J]. Transportation Research Part C:Emerging Technologies, 2014, 46:179-191. [16] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016.ZHOU Z H. Machine learning[M]. Beijing:Tsinghua University Press, 2016. (in Chinese)
2019, Vol. 59 
