一类复杂工业过程的智能预报模型及其应用  

Intelligent Prediction Model for a Class of Complex Industrial Process and Its Application

作　　者：严爱军[1] 岳恒[1] 赵大勇[1] 柴天佑[1] 

机构地区：[1]东北大学自动化研究中心,沈阳110004

出　　处：《控制与决策》2005年第7期794-797,802,共5页Control and Decision

基　　金：国家973计划项目(2002CB312201);国家863计划项目(2004AA412030).

摘　　要：针对复杂工业过程中关键变量的测量问题,基于智能技术提出一种由数据采集与处理模块、决策支持模块、预报模块、在线校正模块以及效果评价模块组成的智能预报模型,并将该模型用于竖炉焙烧过程的优化控制与决策中.应用结果表明其维护费用低、实时性好、可靠性及精度高,在很大程度上解决了关键变量测量困难的问题,为选矿厂综合自动化系统的优化控制与优化运行奠定了良好的基础.Based on intelligence technology, an intelligent prediction model is developed, which consists of five modules: data collection and pretreatment, decision-making support, prediction, on-line modification and effect estimate. It is applied in the optimization decision and control for shaft furnace roasting process. Industrial application shows that it solves the problem of the measurement difficulty of the key variables to a great extent, and has low maintenance expense, good real time character, high reliability and perfectly precision. The model provides good foundation for the optimal operation and the optimal control of minerals processing factory.

关 键 词：复杂工业过程 预报模型 应用 综合自动化系统 优化控制 测量问题 处理模块 数据采集 智能技术 决策支持 预报模块 模块组成 在线校正 维护费用 焙烧过程 优化运行 实时性 可靠性 选矿厂 变量 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] S157.1[自动化与计算机技术—控制科学与工程]