
基于客流特征的城市轨道交通站点分类——以青岛市为例
Classification of Urban Rail Transit Stations Based on Passenger Flow Characteristics: A Case Study of Qingdao
为提高城市轨道交通与常规公交衔接服务能力,提升城市公共交通系统整体吸引力,结合服务需求对轨道交通站点进行了分类,并针对不同类型的轨道交通站点提出常规公交接驳服务建议。基于青岛市轨道交通刷卡数据,提取乘客出行特征和车站客流分布特征,应用K-Means算法对轨道交通站点进行分类,并结合轨道交通站点客流特征将轨道交通站点识别为就业导向型、职住混合型、居住导向型、娱乐购物型等4类。在此基础上,提出不同类型站点常规公交出行接驳服务建议:对于就业导向型站点,建议实施以乘客总换乘时间最短为目标的接驳公交运营时刻表,减少乘客等车时间;对于职住混合型站点,建议采用定制公交模式提供个性化接驳出行服务;对于居住导向型站点,建议提供“区域巡游定制公交”服务,在保障公共服务的基础上,提升接驳公交车运营效益;对于娱乐购物型站点,建议在周末或旅游旺季提供休闲微循环线路,以满足该区域乘客游玩购物的出行需求。
In order to improve the connecting service capacity between urban rail transit and bus transit, and enhance the overall attractiveness of the urban public transportation system, the rail transit stations were classified based on service needs, and some suggestions for bus transit connecting services were proposed for different types of rail transit stations. Based on the smart card data of Qingdao rail transit, the characteristics of passenger travel and passenger flow distribution at stations were extracted, and K-Means algorithm was applied to classify rail transit stations. Combined with the passenger flow characteristics of rail transit stations, the rail transit stations were identified as work-oriented stations, mixed work-residence stations, residential-oriented stations and commercial stations. On this basis, taking into account the passenger flow characteristics and passenger travel characteristics of different rail transit stations, some suggestions for bus transit transfer services at different types of rail transit stations were proposed: for work-oriented stations, it is recommended to implement a transfer bus operation schedule with the goal of minimizing the total transfer time of passengers to reduce passenger waiting delays; for mixed work-residence stations, it is recommended to use customized bus modes to provide customized public transportation to provide personalized travel services; for residential-oriented stations, it is recommended to provide a "regional tour customized bus" service to improve the operational efficiency of connecting buses while ensuring public services; for commercial stations, it is recommended to provide leisure micro circulation lines on weekends or in peak tourist seasons to meet the travel needs of passengers in this area for shopping.
城市轨道交通 / 聚类算法 / 出行客流特征 / 刷卡数据 / 车站分类
urban rail transit / clustering algorithm / passenger flow characteristics / smart card data / classification of stations
[1] |
中华人民共和国交通运输部. 中国城市客运发展报告[M]. 北京: 人民交通出版社股份有限公司, 2019.
|
[2] |
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.
|
[3] |
陈艳艳, 张糯, 路尧. 基于外部接驳的城市轨道交通车站站点分类研究[J]. 都市快轨交通, 2017, 30(5):51-55.
|
[4] |
王焕栋, 马红伟. 基于站点兴趣点的城市轨道交通站点分类方法[J]. 交通与运输, 2020, 36(4):33-37.
|
[5] |
李清嘉, 彭建东, 杨红. 武汉市不同站域建成环境与轨道交通站点客流特征关系分析[J]. 地球信息科学学报, 2021, 23(7):1246-1258.
|
[6] |
杨兴. 客流特征视角下的城市轨道交通站点类型识别及影响机理研究[D]. 西安: 长安大学, 2022.
|
[7] |
蒋阳升, 俞高赏, 胡路, 等. 基于聚类站点客流公共特征的轨道交通车站精细分类[J]. 交通运输系统工程与信息, 2022, 22(4):106-112.
|
[8] |
|
[9] |
刘海旭. 轨道交通站点服务功能识别及其相关因素研究[D]. 北京: 北京交通大学, 2020.
|
[10] |
姚振康, 高国飞, 郑汉, 等. 基于谱聚类的城市轨道交通车站间客流分型研究[J]. 都市快轨交通, 2022, 35(2):99-104.
|
[11] |
王浩. 城市轨道交通站点类型与功能演变[D]. 西安: 西北大学, 2023.
|
[12] |
李亮, 赵星, 张海燕, 等. 基于时空维度变量的杭州市轨道交通站点聚类研究[J]. 北京交通大学学报, 2022, 46(4):31-42.
|
[13] |
晏仲书. 基于AFC数据的城市轨道交通网络客流分配方法研究[D]. 南京: 东南大学, 2022.
|
[14] |
周志华. 机器学习[M]. 北京: 清华大学出版社, 2019:75-77.
|
[15] |
崔叙, 喻冰洁, 梁朋朋, 等. 基于“客流-用地”的城市轨道交通站点类型识别与空间再平衡研究——以成都市为例[J]. 现代城市研究, 2021(7):68-79.
|
[16] |
李晓璐, 于昕明, 郗艳红, 等. 基于DBSCAN算法的城轨车站乘客聚集特征分析[J]. 控制与决策, 2019, 34(1):19-24.
|
[17] |
陈艳艳, 王子帆, 孙浩冬, 等. 公共交通乘客的活动模式和规律性研究[J]. 华南理工大学学报(自然科学版), 2023, 51(8):40-50.
|
[18] |
申犁帆, 张纯, 李赫, 等. 城市轨道交通通勤与职住平衡状况的关系研究——基于大数据方法的北京实证分析[J]. 地理科学进展, 2019, 38(6):791-806.
|
[19] |
马壮林, 杨兴, 潭晓伟, 等. 基于客流时间序列的城市轨道交通车站分类[J]. 长安大学学报, 2021, 41(6):113-126.
|
/
〈 |
|
〉 |