基于AFC数据的轨道站点分类研究

Research on Classification of Rail Stations Based on AFC Data

为探究城市轨道交通各站点乘客出行特征,提出一种基于数据挖掘的站点分类研究方法.使用城市轨道进出站刷卡数据,讨论不同输入变量下的聚类结果,建立一种基于K-means聚类算法的不同类型站点识别方法,并运用于重庆市主城区轨道站点分类研究.结果表明,进出站客流数据能较好反映不同类型轨道站点的时空特性.最后分析了不同类型站点乘客出行特征,针对不同类型站点的识别研究为今后精细化研究轨道站点客流奠定基础,为轨道站点的规划设计提供参考.

In order to explore the characteristics of passenger trips at various stations of urban rail transit,a method of station classification research based on data mining is proposed.Using the card swipe data of urban rail transit stations,the clustering results under different input variables are discussed,and a different type of site identification method based on K-means clustering algorithm is established,and is applied to the classification study of rail stations in the main urban area of Chongqing.The results show that the inbound and outbound passenger flow data can better reflect the spatiotemporal characteristics of different types of rail stations.Finally,the passenger travel characteristics of different types of stations are analyzed.The identification research for different types of stations lays the foundation for future refined research on passenger flow at rail stations,and provides reference for the planning and design of rail stations.