A Method of Generating Effective Paths of Urban Rail Transit Based on Passenger Fare Collection Data
-
摘要: 有效路径集合生成是城市轨道交通断面客流预测、线网运力计算和客流分析的基础。为解决传统有效路径生成中存在的各路径有效程度无法评估、线性约束无法赋权的问题，降低问卷随机性对最终路径集生成的影响，本文在传统有效路径问卷调查数据的基础上，对乘客出行路径选择行为进行分析并做出假设，引入乘客出行时长，针对处于不同时长聚类簇下的有效路径分别建立评估模型，提出1种有效路径集生成方法。将轨道交通网络中站点和线路分别抽象为节点和边，构建轨道交通网络有向图；考虑出行路径类型、乘客出行主观因素以及乘客出行密度分布规律，利用自适应的DBSCAN算法处理乘客出行时长数据，以各时长下的出行密度为基准划分聚类簇，以聚类簇及其属性为输入，构建Logit模型并以其评估结果替代传统有效路径生成中的线性条件约束，并独立计算各簇所代表潜在有效路径的有效性权重，基于有效路径出行时长区间的连续性特点获取有效路径集。以广州地铁线网中多对出行OD为例进行验证，结果表明: 结合乘客出行数据聚类分析后所得到的有效路径集，调整兰德系数为0.652，相比于其他传统路径算法的生成结果，提升了0.379；同时在路径总时长-换乘次数平面上所产生的集合边界更为平滑，对复杂线网与快速变化的新开线网拥有更强的适应性。Abstract: It is a fundamental task to generate effective paths for predicting cross-section passenger flows, calculat-ing network capacity, and analyzing passenger demand of urban rail transit system. To solve the problems of tradi-tional effective path generation in which the validity of each path cannot be evaluated, and the linear constraint can-not be assigned, as well as aiming at reducing the influences of randomness of questionnaire on the final path set generation, a method of generating effective path sets is developed based on traditional survey data. The proposed method analyzes route choice behavior of passengers and makes corresponding hypothesis. Then, models for evalu-ating effective routes under different clusters are established by introducing passenger trip duration. Additionally, the stations and the lines between them are abstracted as nodes and edges of the network of rail transit. And then, considering route types, subjective factors, and the density of passenger flows, the passenger's travel time data are processed using the adaptive DBSCAN algorithm and are divided into clusters according to the density of passenger flows at different time intervals. Furthermore, taking the clustering results as the input, a Logit model is developed to replace the linear constraints in path generation. Weights of effective paths represented by clusters are calculated separately, and the effective path set is obtained based on its continuity characteristics at travel time intervals. Exper-iments are conducted based on multiple origin-destination trip data from the metro network in the City of Guang-zhou. Study results show that the effective paths have an average adjusted Rand index of 0.652. Compared with the traditional algorithms, the adjusted Rand index has improved by 0.379. It indicates that the proposed method produc-es a smoother set boundary in the plane of route length and transfer time, which is more adaptable to complex and changeable networks.
-
Key words:
- Urban rail transit /
- Effective path /
- Travel data /
- Density-based clustering /
- K-short circuit algorithm
-
图 1 考虑乘客出行数据的有效路径生成方法流程
Figure 1. Flow-process diagram of efficient route generation method considering passenger travel data
图 6 广州地铁区庄—晓港OD对的乘客出行时长聚类结果
Figure 6. Clustering results of passenger travel data from Quzhuang to Xiaogang in Guangzhou Metro
图 7 不同方法得到的广州地铁区庄—晓港OD对有效路径集轨迹
Figure 7. Trajectories of effective routes set of Quzhuang-Xiaogang obtained by different methods in Guangzhou Metro
表 2 不同算法结果与出行调查数据对比
Table 2. Comparison of different algorithm results and travel survey data
起点 终点 调查结果路径条数 Dial算法路径条数/ARI BFS算法（2）路径条数/ARI BFS算法（3）路径条数/ARI k短路算法（2）路径条数/ARI k短路算法（3）路径条数/ARI 考虑乘客出行数据的k短路算法据的k短路算法 坦尾 公园前 2 2/1 2/1 3/0 2/1 3/0 2/1 广州火车站 珠江新城 1 5/0 3/0 7/0 2/0 7/0 3/0 区庄 虫雷岗 4 4/1 3/0.324 6/0 3/0.324 4/1 4/1 嘉禾望岗 西朗 3 6/0 3/-0.333 6/0 4/0.324 6/0 4/0.324 广州火车站 虫雷岗 3 5/0 2/0.167 3/1 3/1 4/0.231 3/1 黄沙 大学城南 4 7/0.024 1 6/0.222 9/0 6/0.222 7/0.024 1 5/0.55 区庄 晓港 5 9/0.078 7 4/0.232 8/0.23 4/0.232 8/0.23 6/0.691 平均值 3.142 5.429/0.3 3.286/0.23 6/0.176 3.43/0.443 5.57/0.212 4.43/0.652 路径条数RMSE 2.777 1.254 3.464 1.069 3.047 1.000 路径条数的MAPE/% 103.1 46.9 140.7 32.6 131.2 39.8 ARI的MAPE/% 70.0 77.0 82.4 52.7 75.7 34.8 
下载: 导出CSV
表 3 广州地铁线网区庄—晓港OD对的出行时长聚类簇属性
Table 3. Clusters attributes of passenger travel data from Quzhuang to Xiaogang in Guangzhou Metro
数据簇编号 均值 峰值 下界/s 上界/s 潜在路径数 Ⅰ 1.984 4.282 1 296 2 173 4 Ⅱ 0.462 0.757 2 173 2 308 2 Ⅲ 0.246 0.461 2 308 2 995 2
下载: 导出CSV
表 4 不同方法得到的广州地铁区庄-晓港OD对有效路径集生成结果集合
Table 4. Union set of effective routes set of Quzhuang-Xiaogang obtained by different methods in Guangzhou Metro
路径编号 路径 换乘次数 区间数目 预期用时/s 得到该路径的方法 1 区庄一动物园一杨箕一五羊邨一珠江新城—广州塔—客村—鹭江—中大—晓港 2 9 1 594 本文方法k短路、Dial、BFS（2，3） 2 区庄—东山口—东湖—团一大广场—北京路—海珠广场—市二宫—江南西—昌岗—晓港 2 9 1 658 本文方法k短路、Dial BFS（2，3） 3 区庄—淘金—小北—广州火车站—越秀公园—纪念堂—公园前—海珠广场—市二宫—江南西—昌岗—晓港 2 11 1 873 本文方法k短路、BFS（2，3） 4 区庄—动物园—杨箕—体育西路—珠江新城—广州塔—客村—鹭江—中大—晓港 3 9 2 164 本文方法。Dial、k短路、BFS（3） 5 区庄—东山口—烈士陵园—农讲所—公园前—海珠广场—市二宫—江南西—昌岗—晓港 3 9 2 278 本文方法、Dialk短路、BFS（3） E1 区庄—东山口—杨箕—体育西路—珠江新城—广州塔—客村—鹭江—中大—晓港 3 9 2 414 本文方法、BFS（3） E2 区庄—东山口—杨箕—五羊邨—珠江新城—广州塔—客村—鹭江—中大—晓港 4 10 2 470 Dial E3 区庄—动物园—杨箕—东山口—东湖—团一大广场—北京路—海珠广场—市二宫—江南西—昌岗—晓港 4 12 2 706 Dial E4 区庄—动物园—杨箕—东山口—烈士陵园—农讲所—公园前—海珠广场—市二宫—江南西—昌岗—晓港 3 12 2 572 k短路、BFS（3） E5 区庄—动物园—杨箕—五羊邨—珠江新城—猎德—潭村—员村—科韵路—车陂南—琶洲—新港东—磨碟沙—赤岗—客村—鹭江—中大—晓港 2 18 2 763 k短路、BFS（2，3） E6 区庄—动物园—杨箕—体育西路—珠江新城—猎德—潭村—员村—科韵路—车陂南—琶洲—新港东—磨碟沙—赤岗—客村—鹭江—中大—晓港 5 18 2 986 Dial E7 区庄—东山口—杨箕—体育西路—珠江新城—猎德—潭村—员村—科韵路—车陂南—琶洲—新港东—磨碟沙—赤岗—客村—鹭江—中大—晓港 5 18 3 158 Dial E8 区庄—东山口—杨箕—五羊邨—珠江新城—猎德—潭村—员村—科韵路—车陂南—琶洲—新港东—磨碟沙—赤岗—客村—鹭江—中大—晓港 4 18 2 858 Dial
下载: 导出CSV
-
[1] XU G M, LIU W, YANG H. A reliability-based assignment method for railway networks withheterogeneous passen-gers[J]. Transportation Research Part C: Emerging Technolo-gies, 2018, 93: 501-524. doi: 10.1016/j.trc.2018.06.017 [2] XU G M, LIU W, WU R F, et al. A double time-scale passen-ger assignment model for high-speed railway networks with continuum capacity approximation[J]. Transportation Re-search Part E: Logistics and Transportation Review, 2021, 150: 1-25. [3] 张永生, 姚恩建, 刘莎莎, 等. 城市轨道交通乘客半补偿路径选择建模与应用[J]. 铁道学报, 2018, 40(2): 1-7. doi: 10.3969/j.issn.1001-8360.2018.02.001ZHANG Y S, YAO E J, LIU S S, et al. Metro passen-gers'semi-compensatory route choice modeling and applica-tion[J]. Journal of the China Railway Society, 2018, 40(2): 1-7. (in Chinese) doi: 10.3969/j.issn.1001-8360.2018.02.001 [4] 曾诚, 吴佳媛, 罗无瑕, 等. 基于双向BFS算法的城市轨道交通有效路径研究[J]. 交通运输工程与信息学报, 2021, 19(1): 100-108. https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC202101012.htmZENG C, WU J Y, LUO W X, et al. Subway passenger flow assignment based on BFS and weighted semiclustering algo-rithm[J]. Journal of Transportation Engineering and Informa-tion, 2021, 19(1): 100-108. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTGC202101012.htm [5] 许胜博, 朱志国. 基于换乘次数的城市轨道交通有效径路集生成算法研究[J]. 交通运输工程与信息学报, 2017, 15(2): 83-90. doi: 10.3969/j.issn.1672-4747.2017.02.013XU S B, ZHU Z G. Study on effective path set generating al-gorithm for urban rail transit based on transfer times[J]. Jour-nal of Transportation Engineering and Information, 2017, 15(2): 83-90. (in Chinese) doi: 10.3969/j.issn.1672-4747.2017.02.013 [6] 黄婷婷, 朱海燕, 杨聚芬. 基于前景理论的轨道交通乘客路径选择模型[J]. 都市快轨交通, 2019, 32(2): 59-63. https://www.cnki.com.cn/Article/CJFDTOTAL-DSKG201902017.htmHUANG T T, ZHU H Y, YANG J F. The route choice model of urban rail traveler based on prospect theory[J]. Urban Rap-id Rail Transit, 2019, 32(2): 59-63. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DSKG201902017.htm [7] MINGOZZI A, GIORGI S, BALDACCI R. An exact method for the vehicle routing problem with backhauls[J]. Transporta-tion Science, 1999, 33(3): 315-329. doi: 10.1287/trsc.33.3.315 [8] CANCA D, DE-LOS-SANTOS A, LAPORTE G, et al. Inte-grated railway rapid transit network design and line planning problem with maximum profit[J]. Transportation Research Part E: Logistics and Transportation Review, 2019, 127(7): 1-30. [9] 杨泳, 严余松, 户佐安, 等. Logit随机网络配流模型的改进Dial算法[J]. 交通运输系统工程与信息, 2013, 13(2): 158-163. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201302025.htmYANG Y, YAN Y S, HU Z A, et al. Improved Dial's algo-rithm for Logit-Based stochastic traffic assignment model[J]. Journal of Transportation Engineering and Information, 2013, 13(2): 158-163. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201302025.htm [10] 王冠, 钟鸣, 李建忠, 等. 时变网络下轨道交通出行路径动态选择模型: 以武汉市为例[J]. 交通信息与安全, 2020, 38(3): 48-56. doi: 10.3963/j.jssn.1674-4861.2020.03.00701WANG G, ZHONG M, LI J Z, et al. A route dynamic assign-ment model of rail transit with time-varying network topolo-gy: A case study of Wuhan city[J]. Journal of Transport Infor-mation and Safety, 2020, 38(3): 48-56. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2020.03.00701 [11] 王璐瑶, 蒋熙. 基于集成学习的城市轨道交通乘客路径选择建模[J]. 铁道学报, 2020, 42(6): 18-24. https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB202006003.htmWANG L Y, JIANG X. Ensemble learning based bodeling of passenger route choice on urban rail transit network[J]. Jour-nal of the China Railway Society, 2020, 42(6): 18-24. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB202006003.htm [12] 周薇. 城市轨道交通有效路径选择的改进Dial算法[J]. 西华大学学报(自然科学版), 2013(6): 38-40, 50. https://www.cnki.com.cn/Article/CJFDTOTAL-SCGX201306009.htmZHOU W. Improved Dial algorithm for urban rail transit path selection[J]. Journal of Xihua University(Natural Sci-ence Edition), 2013(6): 38-40, 50. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SCGX201306009.htm [13] BINDER S, MAKNOON M Y, AZADEH SS, et al. Passen-ger-centric timetable rescheduling: A user equilibrium ap-proach[J]. Transportation Research Part C: Emerging Tech-nologies, 2021(132): 103368. [14] 朱炜, 韦锦, 洪玲, 等. 基于旅行时间分析的城轨乘客路径集验证方法[J]. 同济大学学报(自然科学版), 2019, 47(1): 56-63. https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201901007.htmZHU W, WEI J, HONG L, et al. Validation method of pas-senger route choice set based on travel time analysis for ur-ban rail transit[J]. Journal of Tongji University(Natural Sci-ence), 2019, 47(1): 56-63. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201901007.htm [15] 翁小雄, 张洁颖. 基于BFS和加权半监督聚类算法的地铁客流分配研究[J]. 都市快轨交通, 2020, 33(3): 77-84. https://www.cnki.com.cn/Article/CJFDTOTAL-DSKG202003018.htmWEN X X, ZHANG J Y. Subway passenger flow assignment based on BFS and weighted semiclustering algorithm[J]. Ur-ban Rapid Rail Transit, 2020, 33(3): 77-84. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DSKG202003018.htm [16] ANUPRIYA, GRAHAM D J, CARBO J M, et al. Under-standing the costs of urban rail transport operations[J]. Trans-portation Research Part B: Methodological, 2020(38): 292-316. [17] 毛保华, 四兵锋, 刘智丽. 城市轨道交通网络管理及收入分配理论与方法[M]. 北京: 科学出版社, 2007.MAO B H, SI B F, LIU Z L. Theory and method of urban rail transit network management and income distribution[M]. Beijing: Science Press, 2007. (in Chinese) [18] 杨信丰, 刘兰芬, 李引珍, 等. 基于影响度的有效路径集合的确定[J]. 交通运输系统工程与信息, 2011, 11(6): 104-110. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201106017.htmYANG X F, LIU L F, LI Y Z, et al. Determining the efficient paths based on effect degree[J]. Journal of Transportation Systems Engineering and Information Technology, 2011, 11(6): 104 -110. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201106017.htm [19] 周慧娟, 邢玉玲. 基于乘客轨道交通出行全过程的服务水平评价体系[J]. 交通工程, 2020, 20(6): 44-50. https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA202006008.htmZHOU H J, XING Y L. Level of service evaluation system based on the entire journey of passenger travel on rail tran-sit[J]. Journal of Transportation Engineering, 2020, 20(6): 44-50. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DLJA202006008.htm [20] 李文杰, 闫世强, 蒋莹, 等. 自适应确定DBSCAN算法参数的算法研究[J]. 计算机工程与应用, 2019, 55(5): 1-7. https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG201905002.htmLI W J, YAN S Q, JIANG Y, et al. Research on method of self-adaptive determination of DBSCAN algorithm parame-ters[J]. Computer Engineering and Applications, 2019, 55(5): 1-7. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG201905002.htm [21] HUBERT L, ARABIE P. Comparing partitions[J]. Journal of Classification, 1985, 2(1): 193-218. -
点击查看大图
图(7) / 表(4)
计量
- 文章访问数: 632
- HTML全文浏览量: 236
- PDF下载量: 25
- 被引次数: 0