留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

融合先验经验聚类的终端区交通流相态识别

袁立罡 胡明华 张洪海 马勇

袁立罡, 胡明华, 张洪海, 马勇. 融合先验经验聚类的终端区交通流相态识别[J]. 交通运输工程学报, 2016, 16(5): 83-94. doi: 10.19818/j.cnki.1671-1637.2016.05.010
引用本文: 袁立罡, 胡明华, 张洪海, 马勇. 融合先验经验聚类的终端区交通流相态识别[J]. 交通运输工程学报, 2016, 16(5): 83-94. doi: 10.19818/j.cnki.1671-1637.2016.05.010
YUAN Li-gang, HU Ming-hua, ZHANG Hong-hai, MA Yong. Phase-state identification of traffic flow in terminal area incorporated with prior experience clustering[J]. Journal of Traffic and Transportation Engineering, 2016, 16(5): 83-94. doi: 10.19818/j.cnki.1671-1637.2016.05.010
Citation: YUAN Li-gang, HU Ming-hua, ZHANG Hong-hai, MA Yong. Phase-state identification of traffic flow in terminal area incorporated with prior experience clustering[J]. Journal of Traffic and Transportation Engineering, 2016, 16(5): 83-94. doi: 10.19818/j.cnki.1671-1637.2016.05.010

融合先验经验聚类的终端区交通流相态识别

doi: 10.19818/j.cnki.1671-1637.2016.05.010
基金项目: 

国家自然科学基金项目 71301074

国家自然科学基金项目 U1333202

江苏省自然科学基金项目 BK20131366

详细信息
    作者简介:

    袁立罡(1980-), 男, 江苏南京人, 南京航空航天大学工学博士研究生, 从事空中交通流量管理理论研究

    胡明华(1962-), 男, 湖南益阳人, 南京航空航天大学教授

  • 中图分类号: U8

Phase-state identification of traffic flow in terminal area incorporated with prior experience clustering

More Information
  • 摘要: 以终端区交通流为研究对象, 基于航迹谱聚类结果定义并提取交通流特征, 分析了特征间关系与交通流相态演化规律, 发掘了实测数据下交通流的自由态、平稳态与拥堵态, 以此为先验经验进一步设计因子分析与遗传期望最大化模糊聚类算法相结合的终端区交通流态势识别方法, 实现对交通流状态影响因素与交通流隐性特征的提取, 选取典型繁忙终端区的实测数据进行验证。分析结果表明: 基于客观数据挖掘的交通流态势识别方法具有良好的适应性与准确性, 自由态、平稳态与拥堵态的模型识别数量分别为6、36、37, 管制员判别数量分别为7、40、32, 误差率分别为14.3%、10.0%、15.6%, 模型识别率均在84%以上; 提取的交通流相态及时空特征可从局部细节构建终端区整体运行态势, 为终端区流量时空分布调配与进离场程序优化提供支撑。

     

  • 图  1  融合先验经验聚类的交通流相态识别过程

    Figure  1.  Identification process of traffic flow phase-state incorporated with prior experience clustering

    图  2  进场交通流航迹聚类结果

    Figure  2.  Trajectory clustering result of inbound traffic flow

    图  3  平均相对速度与其他均值的关系

    Figure  3.  Relationships of average relative velocity and other mean values

    图  4  平均航迹距离与其他均值的关系

    Figure  4.  Relationships of average trajectory distanceand other mean values

    图  5  平均航迹距离与各标准差的关系

    Figure  5.  Relationships of average trajectory distance and standard deviations

    图  6  各标准差之间的关系

    Figure  6.  Relationships among standard deviations

    图  7  交通流典型相态下航迹的水平与竖直分布

    Figure  7.  Horizontal and vertical distributions of trajectories under typical phase-states of traffic flow

    图  8  特征因子的概率分布

    Figure  8.  Probability distributions of characteristic factors

    图  9  平均相对速度与其他特征分量的关系

    Figure  9.  Relationships of average relative velocity and other characteristic components

    图  10  特征分量在不同聚类中的取值分布

    Figure  10.  Value distributions of characteristic components in different clusterings

    图  11  各聚类样本的24h比例分布

    Figure  11.  Proportion distribution of each clustering sample in 24h

    表  1  交通流特征的因子分析

    Table  1.   Factor analysis for traffic flow characteristic

    下载: 导出CSV

    表  2  进场交通流相态隐性特征

    Table  2.   Recessive characteristics of phase-states for inbound traffic flow

    下载: 导出CSV

    表  3  交通流相态识别对比结果

    Table  3.   Comparison result of traffic flow phase-state identification

    下载: 导出CSV
  • [1] 陈德望. 基于模糊聚类的快速路交通流状况分类[J]. 交通运输系统工程与信息, 2005, 5(1): 62-67. doi: 10.3969/j.issn.1009-6744.2005.01.012

    CHEN De-wang. Classification of traffic flow situation of urban freeways based on fuzzy clustering[J]. Journal of Transportation Systems Engineering and Information Technology, 2005, 5(1): 62-67. (in Chinese). doi: 10.3969/j.issn.1009-6744.2005.01.012
    [2] 徐琳, 曲仕茹. 基于数据流挖掘的交通流状态辨识方法研究[J]. 西北工业大学学报, 2011, 29(1): 34-38. doi: 10.3969/j.issn.1000-2758.2011.01.007

    XU Lin, QU Shi-ru. An effective RTRC-TFD method for detecting traffic flow using data stream mining[J]. Journal of Northwestern Polytechnical University, 2011, 29(1): 34-38. (in Chinese). doi: 10.3969/j.issn.1000-2758.2011.01.007
    [3] MENON P K, TANDALE M D, KIM J, et al. A framework for stochastic air traffic flow modeling and analysis[C]//AIAA. 2010 AIAA Guidance, Navigation, and Control Conference. Reston: AIAA, 2010: 1-28.
    [4] HU Jun, WU Zhen-ya. Research on the net amount of air traffic network[C]//SPIE. 2012International Conference on Graphic and Image Processing. Bellingham: SPIE, 2013: 1-7.
    [5] 王莉莉, 张新瑜, 张兆宁. 空中高速路交通流的跟驰现象及流量模型[J]. 西南交通大学学报, 2012, 47(1): 158-162. doi: 10.3969/j.issn.0258-2724.2012.01.026

    WANG Li-li, ZHANG Xin-yu, ZHANG Zhao-ning. Following phenomenon and air freeway flow model[J]. Journal of Southwest Jiaotong University, 2012, 47(1): 158-162. (in Chinese). doi: 10.3969/j.issn.0258-2724.2012.01.026
    [6] ZHANG Hong-hai, XU Yan, YANG Lei, et al. Macroscopic model and simulation analysis of air traffic flow in airport terminal area[J]. Discrete Dynamics in Nature and Society, 2014, 2014: 1-15.
    [7] 张洪海, 杨磊, 别翌荟, 等. 终端区进场交通流广义跟驰行为与复杂相变研究[J]. 航空学报, 2015, 36(3): 949-961. https://www.cnki.com.cn/Article/CJFDTOTAL-HKXB201503029.htm

    ZHANG Hong-hai, YANG Lei, BIE Yi-hui, et al. Research on generalized following behavior and complex phase-transition law of approaching traffic flow in terminal airspace[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36(3): 949-961. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-HKXB201503029.htm
    [8] 李楠, 任杰, 徐肖豪. 终端区交通态势识别研究[J]. 科学技术与工程, 2014, 14(11): 256-261. doi: 10.3969/j.issn.1671-1815.2014.11.056

    LI Nan, REN Jie, XU Xiao-hao. Identification of terminal area traffic situation[J]. Science Technology and Engineering, 2014, 14(11): 256-261. (in Chinese). doi: 10.3969/j.issn.1671-1815.2014.11.056
    [9] 徐肖豪, 任杰, 李楠. 基于FCM的终端区交通态势识别[J]. 航空计算技术, 2014, 44(1): 1-4, 8. doi: 10.3969/j.issn.1671-654X.2014.01.001

    XU Xiao-hao, REN Jie, LI Nan. Identification of terminal area traffic situation based on FCM[J]. Aeronautical Computing Technique, 2014, 44(1): 1-4, 8. (in Chinese). doi: 10.3969/j.issn.1671-654X.2014.01.001
    [10] REYNOLDS T G. Air traffic management performance assessment using flight inefficiency metrics[J]. Transport Policy, 2014, 34: 63-74. doi: 10.1016/j.tranpol.2014.02.019
    [11] HOFFMAN B, KROZEL J, PENNY S, et al. A cluster analysis to classify days in the national airspace system[C]//AIAA. 2003AIAA Guidance, Navigation, and Control Conference and Exhibit. Reston: AIAA, 2003: 1-12.
    [12] CHATTERJI G B, MUSAFFAR B. Characterization of days based on analysis of national airspace system performance metrics[C]//AIAA. 2007 AIAA Guidance, Navigation, and Control Conference and Exhibit. Reston: AIAA, 2007: 1-15.
    [13] MUKHERJEE A, GRABBE S, SRIDHAR B. Classification of days using weather impacted traffic in the national airspace system[C]//AIAA. 2013Aviation Technology, Integration, and Operations Conference. Reston: AIAA, 2013: 1-11.
    [14] BILIMORIA K D, LEE H Q. Analysis of aircraft clusters to measure sector-independent airspace congestion[C]//AIAA. AIAA 5th Aviation, Technology, Integration, and Operations Conference. Reston: AIAA, 2005: 1-9.
    [15] BILIMORIA K D, JASTRZEBSKI M. Properties of aircraft cluster in the national airspace system[C]//AIAA. AIAA6th Aviation Technology, Integration, and Operations Conference. Reston: AIAA, 2006: 1-8.
    [16] 王超, 徐肖豪, 王飞. 基于航迹聚类的终端区进场程序管制适用性分析[J]. 南京航空航天大学学报, 2013, 45(1): 130-139. doi: 10.3969/j.issn.1005-2615.2013.01.022

    WANG Chao, XU Xiao-hao, WANG Fei. ATC serviceability analysis of terminal arrival procedures using trajectory clustering[J]. Journal of Nanjing University of Aeronautics and Astronautics, 2013, 45(1): 130-139. (in Chinese). doi: 10.3969/j.issn.1005-2615.2013.01.022
    [17] 王超, 韩邦村, 王飞. 基于轨迹谱聚类的终端区盛行交通流识别方法[J]. 西南交通大学学报, 2014, 49(3): 546-552. doi: 10.3969/j.issn.0258-2724.2014.03.027

    WANG Chao, HAN Bang-cun, WANG Fei. Identification of prevalent air traffic flow in terminal airspace based on trajectory spectral clustering[J]. Journal of Southwest Jiaotong University, 2014, 49(3): 546-552. (in Chinese). doi: 10.3969/j.issn.0258-2724.2014.03.027
    [18] GARIEL M, SRIVASTAVA A N, FERON E. Trajectory clustering and an application to airspace monitoring[J]. IEEETransactions on Intelligent Transportation Systems, 2011, 12(4): 1511-1524. doi: 10.1109/TITS.2011.2160628
    [19] VON LUXBURG U. A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4): 395-416. doi: 10.1007/s11222-007-9033-z
    [20] 马勇, 胡明华, 顾欣, 等. 基于谱聚类的终端区飞行轨迹分析[J]. 航空计算技术, 2015, 45(5): 46-50. doi: 10.3969/j.issn.1671-654X.2015.05.012

    MA Yong, HU Ming-hua, GU Xin, et al. Trajectory analysis in terminal area based on spectral clustering[J]. Aeronautical Computing Technique, 2015, 45(5): 46-50. (in Chinese). doi: 10.3969/j.issn.1671-654X.2015.05.012
    [21] ANNONIR J, FORSTER C H Q. Analysis of aircraft trajectories using Fourier descriptors and kernel density estimation[C]//IEEE. 15th International IEEE Conference on Intelligent Transportation Systems. New York: IEEE, 2012: 1441-1446.
    [22] EUROCONTROL. European medium-term ATM network capacity plan assessment 2009-2012[R]. Brussels: EUROCONTROL, 2009.
    [23] 姚洪亮, 王秀芳, 王浩. 一种基于结构分解与因子分析的贝叶斯网络隐变量发现算法[J]. 计算机科学, 2012, 39(2): 244-249. doi: 10.3969/j.issn.1002-137X.2012.02.057

    YAO Hong-liang, WANG Xiu-fang, WANG Hao. Hidden variable discovering algorithm of Bayesian networks based on structural decomposition and factor analysis[J]. Computer Science, 2012, 39(2): 244-249. (in Chinese). doi: 10.3969/j.issn.1002-137X.2012.02.057
    [24] 李琦, 姜桂艳, 杨聚芬. 基于因子分析与聚类分析的交通事件自动检测算法融合[J]. 吉林大学学报: 工学版, 2012, 42(5): 1191-1197. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201205021.htm

    LI Qi, JIANG Gui-yan, YANG Ju-fen. Automatic incident detecting algorithms fusion method based on factor analysis and cluster analysis[J]. Journal of Jilin University: Engineering and Technology Edition, 2012, 42(5): 1191-1197. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201205021.htm
    [25] PERNKOPF F, BOUCHAFFRA D. Genetic-based EMalgorithm for learning Gaussian mixture models[J]. IEEETransactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1344-1348.
  • 加载中
图(11) / 表(3)
计量
  • 文章访问数:  2292
  • HTML全文浏览量:  94
  • PDF下载量:  3437
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-04-21
  • 刊出日期:  2016-10-25

目录

    /

    返回文章
    返回