基于软约束调整方法的区域预测控制  

Zone predictive control based on soft constraint adjustment method

作　　者：李奇安[1] 商越 李悦[1] 

机构地区：[1]辽宁石油化工大学信息与控制工程学院,辽宁抚顺113001

出　　处：《南京理工大学学报》2014年第3期332-336,共5页Journal of Nanjing University of Science and Technology

摘　　要：针对复杂工业过程控制中带有区域约束要求的多变量预测控制问题,提出了一种软约束调整方法。依据控制要求的不同,将输出变量分为两类,即质量变量和一般约束变量,并结合工程经验合理选择变量的权重。将线性二次高斯方法引入到软约束的调整中,并兼顾系统的期望目标,以获得满意的优化结果。仿真结果表明所提方法不需要判断输出变量是否违反区域控制要求,也避免了复杂的交互矩阵计算问题,更符合实际工业生产需要。A soft constraint adjustment method is developed for the multivariable predictive control problem with zone constraint requirements in complicated industrial process control. All output variables are grouped into two categories,namely quality variables and normal constraint variables, according to different control requirements. The variable weights are chosen according to engineering experience. In order to further improve the control performance,the linear quadratic Gaussian method is introduced into the soft constraint adjustment method. The simulation results show that the proposed algorithm doesn＇t need to estimate whether the output variables stay within the zone control requirements and avoids complicated interaction matrix calculations, which can satisfy the actual industrial needs more easily.

关 键 词：软约束调整方法 预测控制 区域控制 复杂工业过程控制 区域约束 多变量预测控制 质量变量 一般约束变量 权重 线性二次高斯方法 交互矩阵计算 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]