首页 | 本学科首页   官方微博 | 高级检索  
     

基于神经网络与多模型的非线性自适应广义预测控制
引用本文:石宇静,柴天佑.基于神经网络与多模型的非线性自适应广义预测控制[J].自动化学报,2007,33(5):540-545.
作者姓名:石宇静  柴天佑
作者单位:1.东北大学自动化研究中心 沈阳 110004
基金项目:国家重点基础研究发展计划(973计划);国家自然科学基金;国家创新研究群体科学基金;教育部长江学者和创新团队发展计划
摘    要:针对一类不确定非线性离散时间动态系统, 提出了基于神经网络与多模型的非线性广义预测自适应控制方法. 该自适应控制方法由线性鲁棒广义预测自适应控制器, 神经网络非线性广义预测自适应控制器和切换机制三部分构成. 线性鲁棒广义预测自适应控制器保证闭环系统的输入输出信号有界, 神经网络非线性广义预测自适应控制器能够改善系统的性能. 切换策略通过对上述两种控制器的切换, 保证系统稳定的同时, 改善系统性能. 给出了所提自适应方法的稳定性和收敛性分析. 最后通过仿真实例验证了所提方法的有效性.

关 键 词:广义预测控制    自适应    多模型    神经网络
收稿时间:2006-03-09
修稿时间:2006-06-03

Neural Networks and Multiple Models Based Nonlinear Adaptive Generalized Predictive Control
SHI Yu-Jing,CHAI Tian-You.Neural Networks and Multiple Models Based Nonlinear Adaptive Generalized Predictive Control[J].Acta Automatica Sinica,2007,33(5):540-545.
Authors:SHI Yu-Jing  CHAI Tian-You
Affiliation:1.Research Center of Automation, Northeastern University, Shengyang 110004
Abstract:In this paper, a nonlinear generalized predictive adaptive control method based on neural networks and multiple models is proposed for a class of uncertain nonlinear discrete time dynamical systems. This approach is composed of a linear robust generalized predictive adaptive controller, a neural network nonlinear generalized predictive adaptive controller and a switching mechanism. The linear robust generalized predictive adaptive controller can ensure the boundedness of the input and output signals in the closed-loop system and the neural network nonlinear generalized predictive adaptive controller can improve the performance of the system. The purpose of using the switching mechanism is to obtain stability and improved system performance simultaneously. Stability and convergence analysis of the proposed adaptive method is given. Finally, simulation examples are included to demonstrate the effectiveness of the proposed method.
Keywords:Generalized predictive control  adaptive  multiple models  neural networks
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
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