一种自适应状态空间模型预测控制器设计方法  

A Design Method for Adaptive State-space Model Predictive Controller

作　　者：罗小锁[1] 陈学昌[1] 

机构地区：[1]重庆电子工程职业学院,重庆401331

出　　处：《计算机测量与控制》2013年第3期635-637,共3页Computer Measurement &Control

基　　金：国家自然科学基金项目资助(60874046)

摘　　要：针对存在非线性、时变、约束特性的复杂工业过程,提出一种自适应状态空间模型预测控制策略,利用在线辨识算法获得的状态空间模型作为系统模型,采用间接形式进行自适应预测控制器的设计,控制器包含了对约束问题的二次规划求解。最后应用于六状态2-CSTR过程控制的仿真实验,通过比较跟踪反应釜的温度输出,验证了所提出控制策略的有效性。In order to deal with nonlinear, time--varying and constrained characteristics in the complex industrial processes, an adaptive state space MPC （model predictive control） method is proposed. The state--space model, obtained through the on--line identification algo rithm, is regarded as the system model. Then, this model is used to design the adaptive predictive controller with indirect form. The solution of a quadratic program solving constraints is involved in this controller. The controller is applied to the process control simulation on a six-- state 2--CSTR. Through comparisons of performance in the reactor temperature output tracking, the effectiveness of the proposed control method is showed.

关 键 词：在线辨识 自适应 状态空间模型预测控制 约束 2-CSTR 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]