首页 | 本学科首页   官方微博 | 高级检索  
     

基于神经网络的时变大滞后系统的Smith预估控制
引用本文:季春光,王朋,李士勇,吴锐.基于神经网络的时变大滞后系统的Smith预估控制[J].哈尔滨工业大学学报,2003,35(3):303-306.
作者姓名:季春光  王朋  李士勇  吴锐
作者单位:1. 哈尔滨工业大学,计算机科学与工程学院,黑龙江,哈尔滨,150001
2. 哈尔滨工业大学,航天学院,黑龙江,哈尔滨,150001
基金项目:哈尔滨工业大学校跨学科交叉研究基金资助项目(HIT .MD2 0 0 1 3 5 )
摘    要:针对大滞后不确定系统提出了一种基于人工神经网络的改进型smith预估控制方案,设计了一个基于神经网络的补偿器来克服不确定的大延迟对控制性能的不利影响,解决了传统smith预估控制鲁棒性差及需要预先知道受控对象精确数学模型的问题。数字仿真结果表明,此方案可以在被控对象数学模型未知的情况下对时滞对象进行控制,特别是当时滞对象的特性发生变化时,具有较好的适应性,控制效果远远优于普通Smith预估控制。

关 键 词:神经网络  大滞后  不确定系统  Smith预估器
文章编号:0367-6234(2003)03-0303-04
修稿时间:2002年1月7日

Neural networks based smith pre-estimated control for time-varying system with large time delay
JI Chun guang ,WANG Peng ,LI Shi yong ,WU Rui.Neural networks based smith pre-estimated control for time-varying system with large time delay[J].Journal of Harbin Institute of Technology,2003,35(3):303-306.
Authors:JI Chun guang  WANG Peng  LI Shi yong  WU Rui
Affiliation:JI Chun guang 1,WANG Peng 1,LI Shi yong 2,WU Rui 1
Abstract:An improved Smith pre estimated control method based on artificial neural networks is proposed for control of an uncertain system with large time delay. A compensator based on neural networks is designed to overcome the effect resulting from uncertain large time delay. It can be used to solve the problems of bad robustness and the prerequisite condition that precise mathematical models must be know in advance for the conventional Smith control method.Simulation result prove that this method can control large time delay plants without knowing their mathematical models, especially when the plant is time varying, this new method is adaptive .
Keywords:neural networks  large time delay  uncertain system  Smith predictor
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号