计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (36): 189-191.

• 工程与应用 • 上一篇    下一篇

基于RBF神经网络整定的高速公路匝道PID控制器

曾爱国1,梁新荣1,2,韦彦秀1   

  1. 1.五邑大学 信息学院,广东 江门 529020
    2.华南理工大学 自动化学院,广州 510640
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-12-21 发布日期:2007-12-21
  • 通讯作者: 曾爱国

Freeway ramp PID controller regulated by RBF neural network

ZENG Ai-guo1,LIANG Xin-rong1,2,WEI Yan-xiu1   

  1. 1.School of Information,Wuyi University,Jiangmen,Guangdong 529020,China
    2.College of Automation,South China University of Technology,Guangzhou 510640,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-21 Published:2007-12-21
  • Contact: ZENG Ai-guo

摘要: 研究RBF神经网络整定PID控制器的参数,并应用到高速公路入口匝道控制中。首先阐述了入口匝道控制原理,然后建立了高速公路交通流模型,并设计了RBF神经网络整定的高速公路匝道PID控制器,RBF神经网络通过对被控对象Jacobian信息的辨识来动态调节PID控制器的参数,最后用MATLAB软件进行系统仿真。仿真结果表明,该控制器具有优越的动态和稳态性能,用于高速公路入口匝道控制中效果良好。

关键词: 高速公路, 匝道控制, 交通流模型, RBF神经网络, PID参数整定

Abstract: A parameter adjustment method of the PID controller with RBF neural network is developed and applied to freeway on-ramp metering.The control principle of a ramp is firstly formulated,then a freeway traffic flow model is built,and the PID ramp controller regulated by RBF neural network is designed.RBF neural network identifies the Jacobian matrix of the control plant and then adjusts the parameters of PID controller dynamically.Finally,the controller is simulated in MATLAB software.Simulation result shows that the controller has good dynamic and steady-state performance.It is very effective to freeway on-ramp metering.

Key words: freeway, ramp metering, traffic flow model, RBF neural network, PID parameter adjustment