基于PSO-SVM的车辆防碰撞预警模型研究(英文)
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Research on the Vehicle Anti-collision Warning Model Based On PSO-SVM
  • 作者:周宣赤 ; 张孝兵 ; 张宏峰 ; 夏云海
  • 英文作者:ZHOU Xuan-chi;ZHANG Xiao-bing;ZHANG Hong-feng;XIA Yun-hai;China Academy of Aerospace Aerodynamics;Beijing Aerospace Yisen Wind Tunnel Engineering Technology Co.Ltd.;
  • 关键词:粒子群优化算法 ; 支持向量机 ; 车辆行驶状态 ; 防碰撞 ; 预警
  • 英文关键词:PSO;;SVM;;vehicle traffic state;;anti-collision;;warning
  • 中文刊名:JZDF
  • 英文刊名:Control Engineering of China
  • 机构:中国航天空气动力技术研究院;北京航天益森风洞工程技术有限公司;
  • 出版日期:2018-01-20
  • 出版单位:控制工程
  • 年:2018
  • 期:v.25;No.157
  • 基金:院自主创新研发项目
  • 语种:英文;
  • 页:JZDF201801011
  • 页数:9
  • CN:01
  • ISSN:21-1476/TP
  • 分类号:64-72
摘要
提出了结合"PSO-SVM"和"五要素"车辆防碰撞预警模型对车辆的行驶状态是否安全进行监测和预警。利用Matlab仿真软件,结合SVM技术与"驾驶员、车、路、环境、车辆行驶状态"五要素车辆行驶安全评价模型,进行了车辆行驶状态监测与安全报警的仿真实验。较详细的论述了影响因素的选取和确定,以及预警模型的建立和测试过程,仿真实验的测试结果误差较小,表明该方法有一定的有效性。
        In order to reduce the traffic accidents and ensure driving safety,the paper combines PSO-SVM and the five elements of the safety evaluation model("driver,vehicle,road,environment,and vehicle running state"),and puts forward a vehicle anti-collision warning model which can conduct analysis and early warning by monitoring the vehicle traffic status.Firstly,the paper discusses the influencing factors of the driving security,and analyzes the correlation between the influencing factors and collision.Then the vehicle anti-collision warning model based on PSO-SVM is built up.Finally,the paper carries out the simulation experiment of the model by MATLAB simulation software,and tests the procedure of the warning model in detail.Simulation results demonstrate the high accuracy and effectiveness of the algorithm.
引文
[1]Tian S,Xu L H,Zhou J.Evaluation model and simulation of vehicle driving safety based on GIS[J].Highway.2008,37(12):135-139.
    [2]Jiang N H,Yu J G.Study of rear-end collision prediction for freeway based on RBF neural network[D].Northeast Forestry University,2011.
    [3]Ma Y L,Wang Y W,Pei Y L.Experimental psychology study on relationship between fatigue and driving time[J].Journal of Southwest Jiaotong University,2009,44(4):535-540.
    [4]Cheng D H,Fang M.Studing on judging safe state of vehicle in true environment[J].Microcomputer Information,2008,25(29):255-256,269.
    [5]Li S G,Lu X Y.Research of constructional engineering project bidding risk analysis based on rough sets and support vector machine[J].Computer Engineering and Applications,2008,44(17):224-227.
    [6]Su H Z,Wen Z P,Wu Z R.An early-warning model of dam safety based on SVM theory[J].Journal of Basic Science and Engineering,2009,17(1):40-47.
    [7]Zheng Y H,Xu L Z,Huang F C.Study of water quality analysis based on support vector classification[J].Chinese Journal of Scientific Instrument,2006,27(6):291-293.
    [8]Vapnik V N.The nature of statistical learning theory[M].New York:Springer-Verlag,1995.
    [9]Zhang X G.Introduction to statistical learning theory and support vector machines[J].Acta Automatica Sinica,2000,26(1):32-42.
    [10]Zhou T,Zhang Y N,Yuan H J,et al.SVM based on improvement particle swarm optimization algorithm[J].Computer Engineering and Applications,2007,43(15):44-49.
    [11]Chen B R,Feng X T.Particle swarm optimization with contracted ranges of both search space and velocity[J].Journal of Northeastern University,2005,26(5):488-491.
    [12]Wu Q D,Wang L.Intelligent particle swarm optimization alogrithm research and application[M].Nanjing:Jiangsu Education Press,2005.
    [13]Kennedy,R.C.Eberhart.Particle swarm optimization[R],Proc.IEEE Int.Conf.Neutral Network IV,1995.
    [14]Van den Bergh F.An analysis of particle swarm optimizers[D].Pretoria:University of Pretoria,South Africa,2002.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700