计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (21): 209-211.

• 工程与应用 • 上一篇    下一篇

可控受限多变量耦合系统的智能控制


刘英晖,刘贺平   

  1. 北京科技大学 信息工程学院,北京 100083
  • 收稿日期:2008-12-24 修回日期:2009-04-27 出版日期:2009-07-21 发布日期:2009-07-21
  • 通讯作者: 刘英晖

Intelligent control of limited controllability multivariable coupling control system

LIU Ying-hui,LIU He-ping
  

  1. School of Information Engineering,University of Science and Technology Beijing,Beijing 100083,China
  • Received:2008-12-24 Revised:2009-04-27 Online:2009-07-21 Published:2009-07-21
  • Contact: LIU Ying-hui

摘要: 针对可控受限多变量耦合系统,提出了一种基于对角递归神经网络(DRNN)整定的PID混合解耦控制。采用对角递归神经网络来辨识系统模型,进而对PID控制器参数进行整定,实现多变量解耦控制。通过对多变量耦合控制系统的设计和实时控制,实际控制结果达到了解耦控制的要求,并具有无超调、响应速度快、控制精度高等特点。

关键词: 可控受限多变量耦合系统, 对角递归神经网络(DRNN), 混合解耦控制, PID控制

Abstract: According to the limited controllability of the multivariable coupling system,a PID self-tuning mixed decoupling control method based on DRNN is put forward.It can realize decoupling multivariable system with identifying system model with DRNN and tuning the parameters of PID controller.It is used to real-time control of the multivariable furnace temperature control system.The experimental results indicate that mixed decoupling method based on DRNN has the advantage of non-overshoot,high speed and high control precision compared with common PID control.

Key words: limited controllability multivariable coupling system, Diagonal Recurrent Network(DRNN), mixed decoupling control, PID control