模型预测控制工程软件关键技术及其工业应用  

Key technology and industrial application of model predictive control engineering software

作　　者：赵均[1] 李田鹏[1] 钱积新[1] 

机构地区：[1]浙江大学系统工程研究所,浙江杭州310027

出　　处：《吉林大学学报（信息科学版）》2004年第4期341-345,共5页Journal of Jilin University（Information Science Edition）

摘　　要：针对模型预测控制系统工程化的需求,结合自主开发的预测控制软件Frontapc,研制开发了预测控制工程软件稳态优化和动态控制两个层次的关键技术:稳态优化部分基于优先级的稳态多目标优化处理技术、保证唯一优化工作点的技术;动态控制部分增强鲁棒性的基于漏斗约束的区间控制技术。最后以该软件在乙醛生产过程精馏工段先进控制系统中的成功应用为例,说明了该预测控制软件在实际工业过程控制系统应用中的有效性。Key technology of steady-state optimization and dynamic control in MPC(Model Predictive Control) engineering software are proposed, based on our self-development MPC software—Frontapc. The priority strategy to handle multi-objective optimization applied in steady-state optimization and the method to achieving the unique optimization steady state are proposed. Zone control strategy cooperated with funnel constrains is presented for the purpose to improve the robust control quality. The efficiency of this MPC software is illustrated by the successful application in distillation control system of acetaldehyde production process.

关 键 词：模型预测控制 稳态优化 动态控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]