基于AFC数据的地铁站点客流典型时变特征分析  

Typical Time Varying Characteristic of Passenger Flow at Metro Stations Based on AFC Data

作　　者：李秀劲 段征宇[1] 马忠政[2] LI Xiujin;DUAN Zhengyu;MA Zhongzheng(Key Laboratory of Road Traffic Engineering of the Ministry of Education,Tongji University,Shanghai 201804,China;Shanghai Shentong Metro Group Co.,Ltd,Shanghai 201103,China)

机构地区：[1]同济大学道路与交通工程教育部重点实验室,上海201804 [2]上海申通地铁集团有限公司,上海201103

出　　处：《交通与运输》2021年第6期21-26,共6页Traffic & Transportation

基　　金：上海市“科技创新行动计划”社会发展科技攻关项目(地铁网络客流预测与韧性地铁评价体系与示范应用,编号:20dz1202903)。

摘　　要：地铁站点客流的时变特征是地铁客流管理和预测的重要参数。基于上海1个月的地铁自动售检票系统小时客流数据,采用K-Means聚类算法分析站点客流典型时变曲线特征,并利用POI数据计算点客流时变特征与站点周边土地利用之间的关联性。结果显示,上海地铁站点可分为居住导向型、就业导向型、商业型、混合型、混合偏居住型、混合偏就业型等。不同类型站点服务范围内的土地利用有显著差异,且二者之间有很强的相关性。本研究为地铁客流预测、地铁站点规划设计和地铁运营组织提供相关参考。The time-varying characteristics of metro station passenger flow are important parameters for metro passenger flow management and prediction.Based on the one-month metro AFC hourly passenger flow data in Shanghai,this study used the K-Means clustering algorithm to analyze the characteristics of the typical time-varying curve of the station passenger flow,and the POI data is used to analyze the correlation between the time-varying characteristics of the station passenger flow and the land use around the station.The analysis results show that Metro stations in Shanghai can be divided into six types,including residence-oriented,employment-oriented,commercial,mixed,mixed-biased residence and mixed-biased employment.There are significant differences in land use within the service areas of different types of stations,and there is a strong correlation between them.This study provides relevant reference for metro passenger flow prediction,metro station planning and design,and metro operation organization.

关 键 词：城市交通 地铁客流 客流时变特征 K-MEANS聚类算法 土地利用 

分 类 号：U491[交通运输工程—交通运输规划与管理]