基于机理模型和数据驱动混合方法的铝带轧制厚度预测研究  

Research on Aluminum Strip Rolling Thickness Prediction Based on Mechanism Model and Data-driven Hybrid Method

作　　者：张松林 张丰收[1] ZHANG Songlin;ZHANG Fengshou(School of Mechanical and Electrical Engineering,Henan University of Science and Technology,Luoyang 471003,China)

机构地区：[1]河南科技大学机电工程学院,河南洛阳471003

出　　处：《热加工工艺》2022年第17期69-73,共5页Hot Working Technology

基　　金：国家重点专项资助项目(2017YFB0306401)。

摘　　要：基于机理模型和数据驱动的混合模型方法进行了铝板带厚度的预测。采用Deform软件对Al-1100板带轧制工艺过程进行了有限元分析。利用数据驱动的方法对机理模型预测误差值进行修正。研究结果表明:混合模型值与实际值的误差在2.0%范围内,其合格率比机理模型值合格率提高了11.11%;混合模型样本平均误差较机理模型样本平均误差减小了0.46%。混合模型值比机理模型值更接近实际值。Based on the mechanism model and data-driven hybrid model method, the thickness of the aluminum plate was predicted. The finite element analysis of the Al-1100 strip rolling process was carried out by Deform software. The prediction error of mechanism model was corrected by data-driven method. The results show that the error between the mixed model value and the actual value is in the range of 2.0%,and the qualified rate is 11.11% higher than that of the mechanism model value. The average error of the mixed model sample is 0.46% lower than that of mechanism model sample. The hybrid model value is closer to the actual value than the mechanism model value.

关 键 词：板形厚度 DEFORM软件 机理模型 数据驱动 

分 类 号：TG339[金属学及工艺—金属压力加工]