基于案例推理的层流冷却过程建模  

Modeling of the laminar cooling process with case-based reasoning

作　　者：谭明皓[1] 柴天佑[1] 

机构地区：[1]东北大学自动化研究中心,辽宁沈阳110004

出　　处：《控制理论与应用》2005年第2期248-253,260,共7页Control Theory & Applications

基　　金：国家重点基础研究发展计划资助项目(2002cb312201);国家863高技术计划资助项目(2002AA412140).

摘　　要：针对具有非线性,参数时变,分布参数等综合复杂特性的热轧层流冷却过程,将机理建模方法与案例推理技术相结合,通过使用层流冷却过程中带钢的运行工况构造案例,在案例库中检索与其匹配的历史案例,利用实际工况的特征与匹配工况的特征经过推理给出当前工况的模型参数,从而确定层流冷却过程的动态模型.利用这一模型可以预测整个冷却过程中带钢的温度变化过程.通过某钢铁公司热轧层流冷却过程实际数据的实验比较表明所提出的建模方法是有效的.A hybrid modeling approach integrating case_based reasoning (CBR) into the first principles process model is developed for the laminar cooling process,which is difficult to describe with accurate mathematical models due to its complex nature(e.g.,highly nonlinear,time varying,and spatially varying).The past cases most similar to the current operating condition are retrieved from the case base.The model parameters of the finite difference model for the current operating condition are found by reusing the solutions of the retrieved cases.The finite difference model can predict the through_thickness temperature evolutions of the moving strip during the cooling process.Experimental studies based on the industrial data from a steel company show the effectiveness of the proposed modeling approach.

关 键 词：层流冷却过程 智能建模 机理模型 案例推理 

分 类 号：TG335.11[金属学及工艺—金属压力加工]