轨道交通车站出入口客流预测——以北京市为例  

Passenger flow prediction at entrance and exit of rail transit stations:a case study of Beijing

作　　者：马洁 刘智丽[1] 王书灵 董皓 MA Jie;LIU Zhi-li;WANG Shu-ling;DONG Hao(School of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044,China;Beijing Transport Institute,Beijing 100073,China;Beijing Public Transport Tram Corporation,Beijing 100080,China)

机构地区：[1]北京交通大学交通运输学院,北京100044 [2]北京交通发展研究院,北京100073 [3]北京公交有轨电车有限公司,北京100080

出　　处：《吉林大学学报（工学版）》2024年第8期2197-2205,共9页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金项目(62003027).

摘　　要：针对轨道交通车站出入口客流精准预测问题,综合考虑车站周边土地利用情况、交通接驳条件、车站属性和吸引力等因素,构建了双层客流预测模型,包括基于多元非线性回归的交通小区层客流预测以及基于CRITIC法的出入口层客流预测。模型以可获取数据为基础,先预测交通小区内所有出入口客流总量,再将客流总量分配至交通小区的各出入口。随机选取不同类型轨道交通车站对模型有效性进行验证,结果表明,出入口日进站量的模型预测值与实际值误差在30%以内,平均误差为20%,具有较高的预测精度。Regarding the accurate prediction of passenger flow at the entrance and exit of rail transit stations,Considering the land use around the station,Rail transit connection conditions,station attributes and attraction,a two-level passenger flow prediction model is constructed in this paper,station attributes and attraction,a two-level passenger flow prediction model is constructed in this paper,including the passenger flow prediction at the traffic district level based on multiple nonlinear regression and the passenger flow prediction at the entrance and exit level based on the CRITIC method.On the basis of the available data,the total passenger flow of all entrances and exits in the traffic district is predicted,and then be allocated to each entrance and exit.Different types of rail transit stations are randomly selected to verify the effectiveness of the model.The results show that the error between the predicted value of the model and the actual value of the daily entry volume is within 30%,and the average error is 20%,which has a high prediction accuracy.

关 键 词：轨道交通 双层客流预测模型 非线性回归 CRITIC法 

分 类 号：U291.69[交通运输工程—交通运输规划与管理]