融合多源数据预测高速公路站间旅行时间

摘要/Abstract

摘要：

为精确预测高速公路站间旅行时间，融合收费数据和微波车检数据开展预测. 首先，基于两种数据源的预测结果，采用决策级融合策略；然后，建立了权重分配预测模型、BP神经网络预测模型；针对神经网络收敛速度慢，易陷入局部最优的缺陷，基于遗传算法优化BP神经网络预测模型；最后，利用京哈高速公路北京段收费数据和微波检测器数据对3 种融合模型进行了验证，对比工作日及非工作日2 种交通流状态下3 种模型的性能指标.试验结果表明，基于遗传神经网络的融合模型相比其他2 种模型，预测精度及稳定性均得到了较高的提升，相对误差控制在10%以内，能够更好地满足实际需求.

关键词: 智能交通, 旅行时间预测, 遗传神经网络, 数据融合, 权重分配模型

Abstract:

In order to predict highway travel time accurately, toll collection data and microwave detection data are fused for travel time prediction. First, based on two prediction results, the decision level fusion strategy is determined. Then, the weight distribution model and back propagation neural network model are selected as the basic models. The next, because the neural network convergence is slow and easy to fall into local optimum, the Genetic algorithm is adopted to optimize the neural network model. Finally, on Beijing segment of Jingha Highway, suitable performance indices are proposed to compare the performance of three models in different traffic states, including weekday and weekend. The results show that the fusion model based on GA- BP neural network based on microwave detection data and toll data produced sufficient accuracy and stability. The Mean Relative Error (MPE) of all prediction periods are less than 10% for the normal and holiday traffic flow, which can better meet the practical requirements.

Key words: intelligent transportation, travel time prediction, GA- BP, multi- source data fusion, weight distribution model

中图分类号:

U491.1

赵建东，徐菲菲，张琨，白继根. 融合多源数据预测高速公路站间旅行时间[J]. 交通运输系统工程与信息, 2016, 16(1): 52-57.

ZHAO Jian-dong，XU Fei-fei，ZHANG Kun，BAI Ji-gen. Highway Travel Time Prediction Based on Multi-source Data Fusion[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(1): 52-57.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract19135.shtml

http://www.tseit.org.cn/CN/Y2016/V16/I1/52

参考文献

[1] 李瑞敏，陈熙怡. 多源数据融合的道路旅行时间估计方法研究:[J]. 公路交通科技，2014，31(2): 99-103. [LI R M, CHEN X Y. Study on methods of travel time estimation based on multi-source data fusion[J]. Journal of Highway and Transportation Research and Development, 2014, 31(2): 99-103.]

[2] 杨兆升，孙晓梅，王志建. 快速路截面数据和车牌识别数据融合算法[J]. 北京工业大学学报，2009，35(10)：1378-1383. [YANG Z S, SUN X M, WANG Z J. Fusion algorithm for section detector data and license plate recognition data of expressway[J]. Journal of Beijing
University of Technology, 2009, 35(10): 1378-1383.]
[3] 杨兆升，于悦，杨薇. 基于固定型检测器和浮动车的路段行程时间获取技术[J]. 吉林大学学报（工学版），2009，39(2)：168-171. [YANG Z S, YU Y, YANG W.Acquisition of travel time based on inductive coil detector and probe vehicle[J]. Journal of Jilin University(Engineering and Technology Edition), 2009, 39(2):168-171.]
[4] 王媛. 大范围战略交通协调控制系统关键技术研究[D]. 长春：吉林大学，2009. [WANG Y. Research on key technologies of large-scale strategic traffic coordination and control system[D]. Changchun: JilinUniversity, 2009.]
[5] 聂庆慧，夏井新，张韦华. 基于多源ITS数据的行程时间预测体系框架及核心技术[J]. 东南大学学报(自然科学版)，2011，4l(1)：199-204. [NIE Q H, XIA J X,ZHANG W H. Framework and key technologies for travel time prediction based on multiple ITS data sources[J]. Journal of Southeast University (Natural Science Edition), 2011, 41(1): 199-204.]
[6] 李惠兵，杨晓光. 面向行程时间预测准确度评价的数据融合方法[J]. 同济大学学报（自然科学版），2013，41(1)：60- 65. [LI H B, YANG X G. Highway travel prediction between stations based on toll ticket data[J].Journal of Tongji University (Natural Science), 2013, 41(1): 60-65.]
[7] Hwang K P, Lee W H, Wu W B. Travel time prediction by weighted fusion of probing vehicles and vehicle detectors data sources [C]//The 12th International Conference on ITS Telecommunications, Taibei: IEEE Communication Society, 2012: 476-481.
[8] 王立晓，刘锴，森川高行. 浮动车和固定检测两种数据源的差异特[J]. 哈尔滨理工大学学报，2013，18(5)：91- 97. [WANG L X, LIU K, Morikawa Takayuki. A study on the difference and feature of probe vehicles data and fixed point data[J]. Journal of Harbin University of Science and Technology, 2013, 18(5): 91-97.]
[9] Nour- Eddin El Faouzi, Lawrence A Klein, Olivier De Mouzon. Improving travel time estimates from inductive loop and toll collection data with dempster-shafer data fusion[J]. Transportation Research Record, 2009, 2129(1): 73-80.
[10] 李瑞敏，马玮. 基于BP神经网络与D-S证据理论的路段平均速度融合方法[J]. 交通运输工程学报，2014，14(5)：111-118. [LI R M, MA W. Fusion method of road section average speed based on BP neural network and D-S evidence theory[J]. Journal of Traffic and Transportation Engineering, 2014, 14(5): 111-118.]
[11] Yoshikazu Ohba, Hideki Ueno, Masao Kuwahara. Travel time calculation method for expressway using toll collection system data [C]//IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems, Tokyo: IEEE Intelligent Transportation System Council, 1999: 471-475.
[12] F Soriguera, D Rosas, F Robuste. Travel time measurement in closed toll highways[J]. Transportation Research Part B, 2010, 44(10): 1242-1267.
[13] Yamazaki H, Uno N, Kurauchi F. The effect of a new intercity expressway based on travel time reliability using electronic toll collection data[J]. IET Intelligent Transport System, 2012, 6(3): 306-317.
[14] 赵建东，王浩，刘文辉，等. 基于收费数据的高速公路站间旅行时间预测[J]. 同济大学学报（自然科学版），2013，41(12)：1849-1854. [ZHAO J D, WANG H, LIU W H, et al. Highway travel prediction between stations based on toll ticket data[J]. Journal of Tongji University(Natural Science), 2013, 41(12): 1849-1854.]
[15] 赵建东，王浩，刘文辉. 高速公路旅行时间自适应插值卡尔曼滤波预测[J]. 华南理工大学学报（自然科学版），2014，42(2)：109-115. [ ZHAO J D, WANG H, LIU W H. Prediction of expressway travel time based on adaptive interpolation Kalman Filtering[J]. Journal of south China university of technology (natural science edition), 2014, 42(2)：109-115.]
[16] Jiandong Zhao, Feifei Xu, Jigen Bai, et al. Travel time prediction based on pattern matching method[J].International Journal on Smart Sensing and Intelligent Systems，2015，8(1): 658-676.
[17] 王启明，等. 高速公路旅行时间与收费广场通行水平分析课题研究报告[R]. 北京：北京：北京云星宇交通工程有限公司，2012. [WANG Q M, et al. Research report on the analysis of the highway travel time and the traffic level of the toll plaza[R]. Beijing：Beijing YunXingYu Traffic Engineering Co., LTD, 2012.]