考虑多时间尺度特征的城市轨道交通短时客流量预测模型

doi:10.16097/j.cnki.1009-6744.2022.06.022

交通运输系统工程与信息 ›› 2022, Vol. 22 ›› Issue (6): 212-223.DOI: 10.16097/j.cnki.1009-6744.2022.06.022

考虑多时间尺度特征的城市轨道交通短时客流量预测模型

张文娟^*，杨皓哲，张彬，李秀杰

同济大学，机械与能源工程学院，上海 201804

收稿日期:2022-08-04 修回日期:2022-11-05 接受日期:2022-11-07 出版日期:2022-12-25 发布日期:2022-12-23
作者简介:张文娟(1970- )，女，山东菏泽人，副研究员，博士。
基金资助:
上海市科技创新行动计划(21DZ1203700)

Short-time Passenger Flow Prediction Model of Urban Rail Transit Considering Multi-timescale Features

ZHANG Wen-juan^*, YANG Hao-zhe, ZHANG Bin, LI Xiu-jie

School of Mechanical Engineering, Tongji University, Shanghai 201804, China

Received:2022-08-04 Revised:2022-11-05 Accepted:2022-11-07 Online:2022-12-25 Published:2022-12-23
Supported by:
Science and Technology Commission of Shanghai Municipality

摘要/Abstract

摘要： 针对目前城市轨道交通短时客流量预测模型在构建特征时容易忽略客流变化周期依赖性的不足，提出一种考虑多时间尺度特征的混合深度学习模型(GRU-Transformer)，该模型由添加注意力机制的 GRU(Gate Recurrent Unit)神经网络(Attention- GRU)和改进的 Transformer(ConvTransformer)两模块并行构成。首先，对周周期、日周期及相邻时段这3种时间尺度下的客流数据分别进行建模，并合并各周期数据作为模型输入。其次，搭建Attention-GRU和Conv-Transformer模块分别挖掘数据连续性与周期性特征，融合特征后输出预测值。最后，采集上海市地铁2号线两站点AFC(Automatic Fare Collection)客流数据，预测5 min时间粒度下的进出站客流量。为分析各模型参数对预测结果的影响，开展模型精细化调参实验，基于所得最优参数组合验证和评估模型。结果表明，相较于5个基线模型(BPNN(Back Propagation Neural Network)、CNN (Convolutional Neural Network)、GRU、CNN-GRU 及 Transformer)和4个GRU-Transformer消融模型，本文提出的GRU-Transformer模型预测精度最高，具有较好的实用性。

关键词: 智能交通, 短时客流量预测, 深度学习, 城市轨道交通, GRU, Transformer模型

Abstract: Current prediction models on short- time passenger flow of urban rail transits always ignore the period dependence of data in feature construction. To address this problem, a hybrid deep learning model (GRU-Transformer) considering multi-timescale temporal features is proposed. The model consists of two blocks in parallel, a GRU neural network with added attention mechanism (Attention-GRU) and an improved Transformer (Conv-Transformer). First, passenger flow data at three time scales, namely weekly periodic, daily periodic, and recent time segment, are modeled separately and combined as model inputs. Second, the Attention-GRU and Conv-Transformer blocks are built to mine the continuity and periodicity features respectively and the prediction values are output after feature fusion. Finally, the AFC passenger flow data of two stations of Shanghai Metro Line 2 were collected for the prediction of inbound and outbound passenger flow under the 5-minute time granularity. To analyze the influence of parameters, tuning experiments are carried out and the model is evaluated based on the optimal parameter combination. The results show that compared with five baseline models (BPNN, CNN, GRU, CNN-GRU, Transformer) and four GRU-Transformer ablation models, the GRU-Transformer model has the highest prediction accuracy and good practicability.

Key words: intelligent transportation, short-time passenger flow prediction, deeplearning, urban rail transit, GRU, Transformer model

中图分类号:

U495

张文娟, 杨皓哲, 张彬, 李秀杰. 考虑多时间尺度特征的城市轨道交通短时客流量预测模型[J]. 交通运输系统工程与信息, 2022, 22(6): 212-223.

ZHANG Wen-juan, YANG Hao-zhe, ZHANG Bin, LI Xiu-jie. Short-time Passenger Flow Prediction Model of Urban Rail Transit Considering Multi-timescale Features[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(6): 212-223.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2022.06.022

http://www.tseit.org.cn/CN/Y2022/V22/I6/212

参考文献

[1] ZHANG J, WANG F Y, WANG K, et al. Data-driven intelligent transportation systems: A survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(4): 1624-1639.

[2] 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 P, LI L. Prediction of urban rail transit station inflows based on ARIMA model[J]. Journal of Chongqing Jiaotong University(Natural Science), 2020, 39(1): 40-44.]

[3] JIAO P, LI R, SUN T, et al. Three revised Kalman filtering models for short-term rail transit passenger flow prediction[J]. Mathematical Problems in Engineering, 2016, 2016(3): 1-10.

[4] 郇宁, 谢俏, 叶红霞, 等. 基于改进KNN算法的城轨进站客流实时预测[J].交通运输系统工程与信息, 2018, 18(5): 121-128. [HUAN N, XIE Q, YE H X, et al. Realtime forecasting of urban rail transit ridership at the station level based on improved KNN algorithm[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(5): 121-128.]

[5] LI H, WANG Y, XU X, et al. Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network[J]. Applied Soft Computing, 2019, 83: 105620.

[6] LIU Y, LIU Z, JIA R. DeepPF: A deep learning based architecture for metro passenger flow prediction[J]. Transportation Research Part C: Emerging Technologies, 2019, 101: 18-34.

[7] YANG X, XUE Q, YANG X, et al. A novel prediction model for the inbound passenger flow of urban rail transit[J]. Information Sciences, 2021, DOI: 10.1016/j. ins.2021.02.036.

[8] ZHANG J, CHEN F, CUI Z, et al. Deep learning architecture for short-term passenger flow forecasting in urban rail transit[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(11): 7004-7014.

[9] 赵建立, 石敬诗, 孙秋霞, 等. 基于混合深度学习的地铁站进出客流量短时预测[J]. 交通运输系统工程与信息, 2020, 20(5): 128-134. [ZHAO J L, SHI J S, SUN Q X, et al. Short-time inflow and outflow prediction of metro stations based on hybrid deep learning[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(5): 128-134.]

[10] VASWANI A, SHAZEER N, PARMAR N, et al. Proceedings of the 31st International Conference on Neural Information Processing Systems[C]. Long Beach: Curran Associates Inc, 2017.

[11] LIN G, DING J, DING S, et al. 2021 International Conference on Big Data Analysis and Computer Science [C]. Piscataway: IEEE, 2021.

[12] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780．

[13] CHO K, MERRIENBOER B V, GULCEHRE C, et al. Learning phrase representations using RNN encoderdecoder for statistical machine translation[J]. Computer Science, 2014.

[14] 田永林, 王雨桐, 王建功, 等. 视觉 Transformer 研究的关键问题: 现状及展望[J]. 自动化学报, 2022, 48(4): 957- 979. [TIAN Y L, WANGY T, WANG J G, et al. Key problems and progress of vision transformers: The state of the art and prospects[J]. Acta Automatica Sinica, 2022, 48(4): 957-979.]

[15] 王福建, 俞佳浩, 赵锦焕, 等. 基于站点实时关联度的短时公交客流预测方法[J]. 交通运输系统工程与信息, 2021, 21(6): 131-144. [WANG F J, YU J H, ZHAO J H, et al. Short-term public traffic passenger volume forecasting methodbased on real-time relevance of stations[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 131-144.]

[16] 李洁, 彭其渊, 文超. 基于LSTM深度神经网络的高速铁路短期客流预测研究[J]. 系统工程理论与实践, 2021, 41(10): 2669- 2682. [LI J, PENG Q Y, WEN C. Short term passenger flow prediction of high speed railway based on LSTM deep neural network[J]. Systems Engineering: Theory & Practice, 2021, 41(10): 2669- 2682.]

考虑多时间尺度特征的城市轨道交通短时客流量预测模型

Short-time Passenger Flow Prediction Model of Urban Rail Transit Considering Multi-timescale Features

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	周琪, 梁肖, 黄俊生, 王海鹏, 毛保华. 城市轨道交通碳排放效率与影响因素研究[J]. 交通运输系统工程与信息, 2023, 23(1): 30-38.
[2]	赵建东, 贺晓宇, 余智鑫, 韩明敏. 多网联范围下的智能网联车换道决策组合模型研究[J]. 交通运输系统工程与信息, 2023, 23(1): 77-85.
[3]	孙伟, 张梦雅, 马成元, 朱际宸, 杨晓光. 新型混合交通交叉口信号与车辆轨迹协同控制方法[J]. 交通运输系统工程与信息, 2023, 23(1): 97-105.
[4]	陈喜群, 朱奕璋, 吕朝锋. 基于混合近端策略优化的交叉口信号相位与配时优化方法[J]. 交通运输系统工程与信息, 2023, 23(1): 106-113.
[5]	贺文武, 裴博彧, 李雅婷, 刘小雨, 徐少兵. 基于双向自适应门控图卷积网络的交通流预测[J]. 交通运输系统工程与信息, 2023, 23(1): 187-197.
[6]	高雨虹, 曲昭伟, 宋现敏. 基于猎人猎物优化与双向长短时记忆组合模型的汽车出车率预测[J]. 交通运输系统工程与信息, 2023, 23(1): 198-206.
[7]	郝威, 龚雅馨, 张兆磊, 易可夫. 面向高速公路混合交通流的车辆协同合流策略[J]. 交通运输系统工程与信息, 2023, 23(1): 224-235.
[8]	谢新林, 罗臣彦, 续欣莹, 谢刚. 双注意力引导的跨层优化交通场景语义分割[J]. 交通运输系统工程与信息, 2023, 23(1): 236-244.
[9]	杨柳, 杨莹, 宋允洲, 张宇. 驾驶压力影响因素与识别方法研究综述[J]. 交通运输系统工程与信息, 2022, 22(6): 40-50.
[10]	彭恺, 李夏苗. 我国城市轨道交通网络运营盈利能力的实证分析[J]. 交通运输系统工程与信息, 2022, 22(6): 68-73.
[11]	项新建, 胡海斌, 姚佳娜, 丁祎, 郑永平, 金立. 一种基于物影匹配算法的道路小目标跟踪方法[J]. 交通运输系统工程与信息, 2022, 22(6): 85-94.
[12]	陈志军, 胡军楠, 冷姚, 钱闯, 吴超仲. 基于轻量化网络和注意力机制的智能车快速目标识别方法[J]. 交通运输系统工程与信息, 2022, 22(6): 105-113.
[13]	朱兴林, 姚亮, 刘泓君, 叶拉森∙库肯, 艾力∙斯木吐拉. 考虑驾驶风格差异的高原公路危险路段识别研究[J]. 交通运输系统工程与信息, 2022, 22(6): 172-182.
[14]	刘江, 谭思伦, 蔡伯根, 王剑. 基于车路信息交互的车辆卫星定位协同定权方法[J]. 交通运输系统工程与信息, 2022, 22(5): 85-96.
[15]	张名芳, 吴禹峰, 王力, 王庞伟. 基于金字塔特征融合的二阶段三维点云车辆检测[J]. 交通运输系统工程与信息, 2022, 22(5): 107-116.