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

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.