基于概率约束的DMC预测控制算法研究  

Probabilistic Constrains into Algorithm of Dynamic Matrix Control

作　　者：姚薇[1] 郭伟[1] 

机构地区：[1]南京信息工程大学信息与通信系,南京210044

出　　处：《武汉理工大学学报》2006年第8期100-103,共4页Journal of Wuhan University of Technology

基　　金：南京信息工程大学科研资助项目(Qd11)

摘　　要：动态矩阵控制(DMC)是模型预测控制(Model Predictive Control)的典型算法,能有效处理系统输入输出约束和抑制随机干扰。对于存在约束的线性稳定系统,该文将条件均值和状态估计误差协方差引入系统的约束表达式中,通过高斯近似把概率约束指标转换为确定性线性约束,建立科学的有约束DMC预测控制系统,使被控对象能够更好地满足约束。这种方法简单,易于实现,Matlab进行仿真结果证明了其可行性与优越性。Dynamic matrix control（DMC）, an important control algorithm of Model predictive control , was of interest because it was an effective method to restrain stochastic disturbances and handle constraints. In this paper, using a Gaussian approximated for a linear system with probabilistic constraints, the original problem was approximated by detemlinistically-constrained DMC problem, The efficiency of this approach was demonstrated by simulation results using Matlab.

关 键 词：动态矩阵控制 概率约束 高斯近似 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]