都市快轨交通

基于PSO-SVR模型的轨道交通客流预测

PDF下载

胡松 ¹ , 常征 ¹ , 杨贝 ² , 王海鹏 ¹ , 马捷 ¹

都市快轨交通 | 学术探讨 2025,38(5): 50-56

收起

都市快轨交通 |学术探讨 2025 , 38 (5) : 50 -56

基于PSO-SVR模型的轨道交通客流预测

全屏

胡松¹, 常征¹, 杨贝², 王海鹏¹, 马捷¹

作者信息

^1.交通运输部公路科学研究院，北京　100088

^2.北京城市学院，北京　101309

通讯作者:

杨贝，女，硕士，工程师，主要从事智能交通、交通数据处理与分析等研究，1073369215@qq.com

作者简介:

胡松，男，博士，助理研究员，主要从事智能交通与数据挖掘、交通行为建模等研究，598529387@qq.com

Urban Rail Passengar Flow Prediction Using Particle Swarm Optimization-Tuned SVR Model

Song HU¹, Zheng CHANG¹, Bei YANG², Haipeng WANG¹, Jie MA¹

Affiliations

^1.Research Institute of Highway Ministry of Transport, Beijing 100088

^2.Beijing City University, Beijing 101309

出版时间: 2025-10-10 doi: 10.3969/j.issn.1672-6073.2025.05.007

文章导航

摘要

收起

为解决细粒度条件下城市轨道交通的客流规模精准预测及管理决策问题，基于轨道交通自动售检票数据分析客流时空分布特征及轨道交通客流影响因素，选取支持向量机回归（support vector regression，SVR）模型作为轨道交通客流预测算法并采用粒子群（particle swarm optimization，PSO）算法优化模型参数；基于2021年10月北京市地铁4号线客流，以15 min为客流统计与预测的时间粒度，将天气、时段和日期类型3个影响因素作为模型预测的输入变量，采用指标评价（均方误差、平均绝对误差、决定系数和相对精度）和模型对比方式验证模型的准确性。研究结果表明：本文所提模型能够准确刻画轨道客流时空特征并具有较高的预测精度，模型预测的均方误差MSE和决定系数R²分别为0.016 4和0.93；轨道交通客流量与不同模型预测结果的误差值之间存在正相关关系。研究有助于理解城市轨道交通客流分布特征与演变规律，为优化轨道交通运营组织、调度策略及线网规划等提供支撑。

关键词

城市交通 / 客流预测 / 支持向量回归模型 / 粒子群算法 / 参数优化

Abstract

收起

To address the challenge of accurate fine-granularity passenger flow prediction and decision support in urban rail transit, the study analyzes spatiotemporal passenger flow patterns and influencing factors using automatic fare collection (AFC) data, and employs a support vector regression (SVR) model whose parameters are optimized by a particle swarm optimization (PSO) algorithm. Using October 2021 data from Beijing Metro Line 4 at a 15 min aggregation interval, weather, time period, and date type were used as input variables; model accuracy was evaluated via mean squared error (MSE), mean absolute error (MAE), coefficient of determination (R²), and relative accuracy, together with comparative model experiments. The results demonstrate that the proposed model effectively captures the spatiotemporal characteristics of rail transit passenger flow and achieves high prediction accuracy, with a mean squared error of 0.0164 and a coefficient of determination of 0.93. Additionally, a positive correlation is observed between the volume of rail transit passenger flow and error values of different model predictions. The study enhances understanding of the distribution and evolution of urban rail transit passenger flows and supports optimization of operations organization, scheduling strategies, and network planning.

Key words

urban traffic / passenger flow prediction / support vector regression model / particle swarm optimization algorithm / parameter optimization

引用本文

胡松, 常征, 杨贝, 王海鹏, 马捷. 基于PSO-SVR模型的轨道交通客流预测. 都市快轨交通, 2025 , 38 (5) : 50 -56 . DOI: 10.3969/j.issn.1672-6073.2025.05.007

Song HU, Zheng CHANG, Bei YANG, Haipeng WANG, Jie MA. Urban Rail Passengar Flow Prediction Using Particle Swarm Optimization-Tuned SVR Model[J]. Urban Rapid Rail Transit, 2025 , 38 (5) : 50 -56 . DOI: 10.3969/j.issn.1672-6073.2025.05.007

基金

收起

中央级公益性科研院所基本科研业务费专项资金项目(2024-9071)
车路一体智能交通全国重点实验室自主研究项目(2024-Z010)
交通运输部公路科学研究所（院）交通强国试点项目(QG2022-2-8-4)
2023年度山东高速集团科技项目(2024创新复审-02)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

张惠臻, 高正凯, 李建强, 等. 基于循环神经网络的城市轨道交通短时客流预测[J]. 吉林大学学报(工学版), 2023, 53(2): 430-438. ZHANG Huizhen, GAO Zhengkai, LI Jianqiang, et al. Short-term passenger flow forecasting of urban rail transit based on recurrent neural network[J]. Journal of Jilin University (engineering and technology edition), 2023, 53(2): 430-438.

[2]

ROOS J, GAVIN G, BONNEVAY S. A dynamic Bayesian network approach to forecast short-term urban rail passenger flows with incomplete data[J]. Transportation research procedia, 2017, 26: 53-61.

[3]

GUO Jianhua, HUANG Wei, WILLIAMS B M. Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification[J]. Transportation research part C: emerging technologies, 2014, 43: 50-64.

[4]

赵鹏, 李璐. 基于ARIMA模型的城市轨道交通进站量预测研究[J]. 重庆交通大学学报(自然科学版), 2020, 39(1): 40-44. ZHAO Peng, LI Lu. Prediction of urban rail transit station inflows based on ARIMA model[J]. Journal of Chongqing Jiaotong University (natural science), 2020, 39(1): 40-44.

[5]

卢天伟, 姚恩建, 刘莎莎, 等. 城轨新线客流成长期进出站量短时预测研究[J]. 铁道学报, 2020, 42(5): 19-28. LU Tianwei, YAO Enjian, LIU Shasha, et al. Short-time forecast of entrance and exit passenger flow for new line of urban rail transit during growth period[J]. Journal of the China railway society, 2020, 42(5): 19-28.

[6]

ZHANG Zhe, WANG Cheng, GAO Yueer, et al. Short-term passenger flow forecast of rail transit station based on MIC feature selection and ST-LightGBM considering transfer passenger flow[J]. Scientific programming, 2020, 2020(1): 3180628.

[7]

何必胜, 朱永俊, 陈路锋, 等. 基于时空图神经网络的高速铁路车站短期客流预测方法[J]. 铁道学报, 2022, 44(9): 1-8. HE Bisheng, ZHU Yongjun, CHEN Lufeng, et al. A spatialtemporal graph neural network for prediction of short-term passenger flow at high-speed railway station[J]. Journal of the China railway society, 2022, 44(9): 1-8.

[8]

吴娟, 何跃齐, 张宁, 等. 基于VMD-GRU的城市轨道交通短时客流预测[J]. 都市快轨交通, 2022, 35(1): 79-86. WU Juan, HE Yueqi, ZHANG Ning, et al. Forecast of short-term passenger flow of urban rail transit based on VMD-GRU[J]. Urban rapid rail transit, 2022, 35(1): 79-86.

[9]

李金海, 窦亮, 张猛, 等. 城市轨道交通初期运营客流预测技术研究[J]. 都市快轨交通, 2024, 37(1): 102-106. LI Jinhai, DOU Liang, ZHANG Meng, et al. Passenger flow forecasting technology for initial operation of urban rail transit[J]. Urban rapid rail transit, 2024, 37(1): 102-106.

[10]

杜文博, 石婉君, 廖盛时, 等. 基于“时间-特征”协同注意力的机场快轨客流预测[J]. 北京航空航天大学学报, 2022, 48(9): 1605-1612. DU Wenbo, SHI Wanjun, LIAO Shengshi, et al. Passenger flow forecasting of airport express based on time and feature cooperative attention[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(9): 1605-1612.

[11]

SHANG Pan, LI Ruimin, GUO Jifu, et al. Integrating Lagrangian and Eulerian observations for passenger flow state estimation in an urban rail transit network: a spacetime-state hyper network-based assignment approach[J]. Transportation research part B: methodological, 2019, 121: 135-167.

[12]

傅成红, 杨书敏, 张阳. 改进支持向量回归机的短时交通流预测[J]. 交通运输系统工程与信息, 2019, 19(4): 130-134. FU Chenghong, YANG Shumin, ZHANG Yang. Promoted short-term traffic flow prediction model based on deep learning and support vector regression[J]. Journal of transportation systems engineering and information technology, 2019, 19(4): 130-134.

[13]

陆百川, 舒芹, 马广露, 等. 基于GA-PSO和时空特性的城市交通协同控制[J]. 合肥工业大学学报(自然科学版), 2020, 43(5): 673-679. LU Baichuan, SHU Qin, MA Guanglu, et al. Coordinated control of urban traffic based on GA-PSO swarm and spatial-temporal characteristics[J]. Journal of Hefei University of Technology (natural science), 2020, 43(5): 673-679.

[14]

帅春燕, 谢亚威, 单君, 等. 基于SSA-SVR模型的城市轨道交通短时进站客流预测[J]. 都市快轨交通, 2022, 35(5): 76-83. SHUAI Chunyan, XIE Yawei, SHAN Jun, et al. Prediction of short-term inbound passenger flow of urban rail transit based on the singular spectrum analysis and support vector regression model[J]. Urban rapid rail transit, 2022, 35(5): 76-83.

[15]

王雪琴, 许心越, 伍元凯, 等. 基于混合深度学习模型的城轨短时客流预测[J]. 铁道科学与工程学报, 2022, 19(12): 3557-3568. WANG Xueqin, XU Xinyue, WU Yuankai, et al. Short term passenger flow forecasting of urban rail transit based on hybrid deep learning model[J]. Journal of railway science and engineering, 2022, 19(12): 3557-3568.

2025年第38卷第5期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.3969/j.issn.1672-6073.2025.05.007

接收时间：2024-04-02
首发时间：2026-10-19
出版时间：2025-10-10

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2024-04-02
修回日期：2025-05-22

基金

中央级公益性科研院所基本科研业务费专项资金项目(2024-9071)

车路一体智能交通全国重点实验室自主研究项目(2024-Z010)

交通运输部公路科学研究所（院）交通强国试点项目(QG2022-2-8-4)

2023年度山东高速集团科技项目(2024创新复审-02)

作者信息

^1.交通运输部公路科学研究院，北京　100088

^2.北京城市学院，北京　101309

通讯作者:

杨贝，女，硕士，工程师，主要从事智能交通、交通数据处理与分析等研究，1073369215@qq.com

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dskgjt/CN/10.3969/j.issn.1672-6073.2025.05.007

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT