基于神经网络与多模型的非线性自适应广义预测解耦控制  

Nonlinear adaptive decoupling generalized predictive control using neural networks and multiple models

作　　者：石宇静[1] 柴天佑[1] 

机构地区：[1]东北大学自动化研究中心,辽宁沈阳110004

出　　处：《控制理论与应用》2008年第4期634-640,共7页Control Theory & Applications

基　　金：国家重点基础研究发展计划(973)项目(2002CB312201);国家自然科学基金重点资助项目(60534010);国家创新研究群体科学基金(60521003);长江学者和创新团队发展计划资助项目(IRT0421).

摘　　要：针对一类非线性多变量离散时间动态系统,提出了基于神经网络与多模型的非线性自适应广义预测解耦控制方法.该控制方法由线性鲁棒广义预测解耦控制器和神经网络非线性广义预测解祸控制器以及切换机构组成.线性鲁棒广义预测解耦控制器用于保证闭环系统输入输出信号有界,神经网络非线性广义预测解耦控制器能够改善系统性能.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.同时本文给出了所提自适应解耦控制方法的稳定性和收敛性分析.最后,通过仿真实例验证了该方法的有效性.A nonlinear adaptive decoupling generalized predictive control approach based on neural networks and multiple models is proposed for a class of nonlinear multivariable discrete time dynamical systems. The control approach is composed of a linear robust decoupling generalized predictive controller, a neural network nonlinear decoupling generalized predictive controller and a switching mechanism. The linear robust decoupling generalized predictive controller ensures the boundedness of the input and output signals in the closed-loop system, and the neural network nonlinear decoupling generalized predictive controller improves the performance of the system. By using the switching scheme between the linear and nonlinear controllers, it is demonstrated that the stability and the improved system performance can be achieved simultaneously. Stability and convergence analysis are also given. Finally, simulation examples are presented to show the effectiveness of the proposed method.

关 键 词：非线性 广义预测控制 解耦 神经网络 多模型 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]