交通运输系统工程与信息 ›› 2018, Vol. 18 ›› Issue (3): 225-233.

• 案例分析 • 上一篇    下一篇

多变量聚类分析的高速公路交通流状态实时评估

陈钊正 1,吴聪*2   

  1. 1. 江西省高速公路联网管理中心,南昌 330036; 2. 南京邮电大学 宽带无线通信技术教育部工程研究中心,南京 210003
  • 收稿日期:2017-12-27 修回日期:2018-02-24 出版日期:2018-06-25 发布日期:2018-06-25
  • 作者简介:陈钊正(1983-),男,江西鄱阳人,高级工程师,博士.
  • 基金资助:

    国家自然科学基金/ National Natural Science Foundation of China(61471206);江苏省科技厅重点资助/ Key Foundation Projects of the Science and Technology Department of Jiangsu Province(BE2016001-4).

A Method of Traffic State Estimation for Expressway Based on Multivariate Clustering Analysis

CHEN Zhao-zheng1, WU Cong2   

  1. 1. Jiangxi Expressway Networking Management Center, Nanchang 330036, China; 2. Engineering Research Center of Wideband Wireless Communication Technology, Ministry of Education, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • Received:2017-12-27 Revised:2018-02-24 Online:2018-06-25 Published:2018-06-25

摘要:

针对交通状态单变量判断传统方法的不足,本文建立了基于多变量聚类分析的高速公路交通流状态实时评估方法.结合实际交通流数据,利用模糊聚类、K均值聚类等算法对速度、流量等向量进行聚类分析,给出适合当前高速公路特点的交通状况划分方法和关键参数.本文方法能够实时、准确、全面地反映交通流的运行情况,为制定高效的交通管理控制方案及合理的出行方案提供数据基础.

关键词: 公路运输, 多变量, 聚类分析, K均值聚类, 交通流

Abstract:

For the shortcomings of the traditional traffic state of single variable judgment method, a real-time evaluation method of highway traffic flow based on multivariate cluster analysis is established. We use fuzzy clustering and K-means clustering algorithm, combined with the actual traffic flow data, to cluster the speed, flow and other vectors. The traffic state classification method is established, which is suitable for the current highway. It can reflect the traffic flow state in real time, accurately and comprehensively. This paper provides data foundation for efficient traffic management and reasonable travel plan.

Key words: highway transportation, many variables, cluster analysis, K-mean clustering, traffic flow

中图分类号: