基于时频分解与深度学习的轨道客流预测

doi:10.6040/j.issn.1672-3961.0.2023.040

摘要/Abstract

摘要： 为提高城市轨道线网站点短时客流预测精度,在对轨道站点分类的基础上分别对各类型站点进行客流预测。以动态时间弯曲作为度量,采用K-means算法对站点进行分类,分析各类型站点客流时序特征;为弱化原始客流数据中噪声的影响,利用经验模态分解(empirical mode decomposition, EMD)方法对各类站点原始客流进行时频分解;提出一种融合图卷积网络(graph convolution network, GCN)和门控循环单元(gated recurrent unit, GRU)的深度学习模型,并以分解得到的分量作为模型输入。以西安地铁为例进行研究,结果表明,根据连续一周站点客流时序特征可将站点分为办公就业型、密集居住型、休闲娱乐型、偏远居住型和职住均衡型5类。采用平均绝对百分比误差及均方根误差作为评价指标,结果表明本研究所提方法对各类站点客流预测的精度优于基准模型。

关键词: 客流预测, 图卷积, 门控循环单元, 站点分类, 经验模态分解

中图分类号:

U491.1+4

徐金华,罗义凯,李昱燃,李岩. 基于时频分解与深度学习的轨道客流预测[J]. 山东大学学报 (工学版), 2024, 54(2): 60-68.

XU Jinhua, LUO Yikai, LI Yuran, LI Yan. Prediction of rail passenger flow based on time-frequency decomposition and deep learning[J]. Journal of Shandong University(Engineering Science), 2024, 54(2): 60-68.

参考文献

[1] 徐成永, 叶轩, 宣晶. 轨道交通运行效果评估、客流特征分析和发展对策研究[J]. 都市快轨交通, 2019, 32(6): 44-50. XU Chengyong, YE Xuan, XUAN Jing, et al. Operational evaluation, characteristic analysis and development strategy of urban rail transit in Beijing[J]. Urban Rapid Rail Transit, 2019, 32(6): 44-50.
[2] 赵阳阳, 夏亮, 江欣国. 基于经验模态分解与长短时记忆神经网络的短时地铁客流预测模型[J]. 交通运输工程学报, 2020, 20(4): 194-204. ZHAO Yangyang, XIA Liang, JIANG Xinguo. Short-term metro passenger flow prediction based on EMD-LSTM[J]. Journal of Traffic and Transportation Engineering, 2020, 20(4): 194-204.
[3] 邵滢宇, 丁柏群. 基于聚类分析的地铁站点分类:以哈尔滨地铁1号线为例[J]. 森林工程, 2015, 31(3): 106-111. SHAO Yingyu, DING Boqun. Metro stations classification based on clustering analysis: a case study of Harbin metro line 1[J]. Forest Engineering, 2015, 31(3): 106-111.
[4] 傅搏峰, 吴娇蓉, 陈小鸿. 郊区轨道站点分类方法研究[J]. 铁道学报, 2008, 30(6): 19-23. FU Bofeng, WU Jiaorong, CHEN Xiaohong. Method of classification of suburban rail transit station sites[J]. Journal of the China Railway Society, 2008, 30(6): 19-23.
[5] KIM M K, KIM S P, HEO J, et al. Ridership patterns at subway stations of Seoul capital area and characteristics of station influence area[J]. KSCE Journal of Civil Engineering, 2017, 21(3): 964-975.
[6] 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. YIN Qin, MENG Bin, ZHANG Liying. Classification of subway stations in Beijing based on passenger flow characteristics[J]. Progress in Geography, 2016, 35(1): 126-134.
[7] 李海林, 张丽萍. 时间序列数据挖掘中的聚类研究综述[J]. 电子科技大学学报, 2022, 51(3): 416-424. LI Hailin, ZHANG Liping. Summary of clustering research in time series data mining[J]. Journal of University of Electronic Science and Technology of China, 2022, 51(3): 416-424.
[8] 王会青, 孙宏伟, 张建辉. 基于Map/Reduce的时间序列相似性搜索算法[J]. 山东大学学报(工学版), 2016, 46(1): 15-21. WANG Huiqing, SUN Hongwei, ZHANG Jianhui. Time series similarity searching algorithm based on Map/Reduce[J]. Journal of Shandong University(Engineering Science), 2016, 46(1): 15-21.
[9] 朱才华, 孙晓黎, 李培坤, 等. 融合车站分类和数据降噪的城市轨道交通短时客流预测[J]. 铁道科学与工程学报, 2022, 19(8): 2182-2192. ZHU Caihua, SUN Xiaoli, LI Peikun, et al. Short-term urban rail transit passenger flow prediction based on incorporating station classification and data noise reduction[J]. Journal of Railway Science and Engineering, 2022, 19(8): 2182-2192.
[10] NI M, HE Q, GAO J. Forecasting the subway passenger flow under event occurrences with social media[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 18(6): 1623-1632.
[11] 杨军, 侯忠生. 一种基于灰色马尔科夫的大客流实时预测模型[J]. 北京交通大学学报, 2013, 37(2): 119-123. YANG Jun, HOU Zhongsheng. A grey Markov based on large passenger flow real-time prediction model[J]. Journal of Beijing Jiaotong University, 2013, 37(2): 119-123.
[12] 刘美琪, 焦朋朋, 孙拓. 城市轨道交通进站客流量短时预测模型研究[J]. 城市轨道交通研究, 2015, 18(11): 13-17. LIU Meiqi, JIAO Pengpeng, SUN Tuo. On short-term forecasting model of passenger flow in urban rail transit[J]. Urban Mass Transit, 2015, 18(11): 13-17.
[13] 冯树民, 刘浩, 李来成. 雨雪天气下轨道交通客流预测模型[J]. 哈尔滨工业大学学报, 2022, 54(9): 1-6. FENG Shumin, LIU Hao, LI Laicheng. Prediction model of rail transit passenger flow in rain and snow weather[J]. Journal of Harbin Institute of Technology, 2022, 54(9): 1-6.
[14] 丁聪, 倪少权, 吕红霞. 基于梯度提升的城市轨道交通客流量预测分析[J]. 城市轨道交通研究, 2018, 21(9): 60-63. DING Cong, NI Shaoquan, LÜ Hongxia. Forecast and analysis of urban rail transit passenger flow based on gradient boosting[J]. Urban Mass Transit, 2018, 21(9): 60-63.
[15] 刘晓磊, 段征宇, 余庆, 等. 基于图卷积循环神经网络的城市轨道客流预测[J]. 华南理工大学学报(自然科学版), 2022, 50(3): 21-27. LIU Xiaolei, DUAN Zhengyu, YU Qing, et al. Passenger flow forecast of urban rail transit based on graph convolution and recurrent neural network[J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(3): 21-27.
[16] 温惠英, 张东冉, 陆思园. GA-LSTM模型在高速公路交通流预测中的应用[J]. 哈尔滨工业大学学报, 2019, 51(9): 81-87. WEN Huiying, ZHANG Dongran, LU Siyuan. Application of GA-LSTM model in highway traffic flow prediction[J]. Journal of Harbin Institute of Technology, 2019, 51(9): 81-87.
[17] YUAN X, HUANG B, WANG Y, et al. Deep learning-based feature representation and its application for soft sensor modeling with variable-wise weighted SAE[J]. IEEE Transactions on Industrial Informatics, 2018, 14(7): 3235-3243.
[18] 王金水, 欧雪雯, 陈俊岩, 等. 基于组合模型的城市轨道站点短时客流分类预测[J/OL]. 铁道科学与工程学报.(2022-09-22)[2022-10-30]. https://kns.cnki.net/kcms/detail/43.1423.U.20220919.1928.015.html.
[19] 田秀娟, 于德新, 邢雪, 等. 交叉口短时流量CEEMDAN-PE-OSELM预测模型[J]. 哈尔滨工业大学学报, 2018, 50(3): 83-89. TIAN Xiujuan, YU Dexin, XING Xue, et al. Prediction model of CEEMDAN-PE-OSELM for intersections short-term traffic flow[J]. Journal of Harbin Institute of Technology, 2018, 50(3): 83-89.
[20] WALKER R T. Geography, VonThünen, and Tobler's first law: tracing the evolution of a concept[J]. Geographical Review, 2022, 112(4): 591-607.
[21] AN D, TONG X, LIU K, et al. Understanding the impact of built environment on metro ridership using open source in Shanghai[J]. Cities, 2019, 93: 177-187.
[22] CHAI D, WANG L, YANG Q. Bike flow prediction with multi-graph convolutional networks[C] //Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Seattle, USA: ACM, 2018: 397-400.
[23] 黄皓,周丽华,黄亚群,等. 基于混合深度模型的虚假信息早期检测[J]. 山东大学学报(工学版), 2022, 52(4): 89-98. HUANG Hao, ZHOU Lihua, HUANG Yaqun, et al. Early detection of fake news based on hybrid deep model[J]. Journal of Shandong University(Engineering Science), 2022, 52(4): 89-98.
[24] 孙鸿昌,周风余,单明珠,等. 基于模式划分的空调能耗混合填补方法[J]. 山东大学学报(工学版), 2022, 52(1): 9-18. SUN Hongchang, ZHOU Fengyu, SHAN Mingzhu, et al. Mode division based hybrid filling method of air conditioning energy consumption[J]. Journal of Shandong University(Engineering Science), 2022, 52(1): 9-18.
[25] 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. JIANG Yangsheng, YU Gaoshang, HU Lu, et al. Refined classification of urban rail transit stations based on clustered station's passenger traffic flow features[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(4): 106-112.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed