大型高铁车站最高聚集人数计算模型研究  

Research on the calculation model of maximum assembled people in large high-speed railway station

作　　者：米荣伟 帅斌[1,2,3] 许旻昊 雷渝 MI Rongwei;SHUAI Bin;XU Minghao;LEI Yu(School of Transportation and Logistics,Southwest Jiaotong University,Chengdu 611756,China;National United Engineering Laboratory of Integrated and Intelligent Transportation,Southwest Jiaotong University,Chengdu 611756,China;National Engineering Laboratory of Integrated Transportation Big Data Application Technology,Southwest Jiaotong University,Chengdu 611756,China)

机构地区：[1]西南交通大学交通运输与物流学院,四川成都611756 [2]西南交通大学综合交通运输智能化国家地方联合工程实验室,四川成都611756 [3]西南交通大学综合交通大数据应用技术国家工程实验室,四川成都611756

出　　处：《铁道科学与工程学报》2021年第12期3102-3109,共8页Journal of Railway Science and Engineering

基　　金：国家自然科学基金资助项目(71173177);国家铁路局科技计划项目(KF2013-020,KF2014-041);四川省科技厅国际科技创新合作项目(2021YFH0106)。

摘　　要：为了更好地拟合高速铁路车站旅客聚集趋势,提高车站旅客最高聚集人数预测结果的准确性,基于旅客候车时间及检票通道服务速率,对比对数正态分布、威布尔分布、复合负指数分布、有理函数分布等4种函数拟合效果,研究最优拟合分布参数和列车乘车人数与车站及列车属性之间的相关性。将相关性较强的属性与最优拟合分布参数、列车乘车人数进行K-means聚类分析,利用Silhouette指数判断聚类效果,最终得到各类属性与最优拟合分布参数和列车乘车人数的检索表。基于检索表建立适用于高速铁路车站的最高聚集人数计算模型,并以成都东站作为算例进行计算和分析。研究结果表明:该最高聚集人数计算模型可以准确模拟旅客聚集趋势,减小预测最高聚集人数与实际最高聚集人数之间的误差。To better fit the trend of passenger agglomeration in high-speed railway stations and improve the accuracy of the prediction results for the maximum number of passengers in the station, based on the waiting time of passengers and the service rate of ticket gates, the log-normal distribution, Weibull distribution, and compound negative exponential distribution were compared for their fitting results. The best fitting distribution parameters and the correlation between the number of train passengers and the attributes of stations and trains were studied;the attributes with a strong correlation with the best fitting distribution parameters were combined;and K-means clustering analysis was performed on the number of train passengers. The Silhouette index was used to assess the clustering effect. Finally, various attributes and optimal fitting distribution parameters and the retrieval table of the number of train passengers were obtained. Based on the retrieval table, it is suitable for high-speed railway stations. The calculation model of the highest gathering number of people was calculated and analyzed with Chengdu East Railway Station taken as an example. The results show that the calculation model of the highest gathering number can accurately simulate the trend of passenger gathering and reduce the difference between the predicted maximum number of gatherings and the actual maximum number of gatherings error.

关 键 词：高速铁路车站 最高聚集人数 旅客聚集规律 列车乘车人数 K-MEANS聚类 

分 类 号：U291.6[交通运输工程—交通运输规划与管理]