金属加工（热加工）Issue(9)：21-29,9.
基于Arrhenius模型的Q195钢热轧过程轧制力预测
Hot-rolling force prediction for Q195 steel based on Arrhenius model
摘要
Abstract
In the production of hot-rolled thin plates,Q195 steel is prone to shape defects like edge waves due to uneven distribution of rolling forces,making precise prediction of rolling forces crucial for process optimization.This paper obtained stress-strain data at various temperatures and strain rates using the Gleeble-3800 thermal simulator,constructing a hyperbolic sine Arrhenius constitutive model.Innovatively,a BP neural network was introduced for stress compensation,achieving a determination coefficient of 0.99967 in flow stress prediction.Based on this,a VUMAT user-defined material subroutine suitable for ABAQUS was developed,and a single-pass hot rolling finite element model was established using actual factory process parameters.Comparison of simulation results with factory-measured data revealed that the predicted average rolling force error is only 1.239％,demonstrating significantly higher accuracy than the original Arrhenius model and the Johnson-Cook model.This fully validates the accuracy and reliability of the proposed modeling approach in practical engineering applications.关键词
Q195钢/Arrhenius本构模型/有限元模型/轧制力预测/BP神经网络Key words
Q195 steel/Arrhenius constitutive model/finite element model/rolling force prediction/BP neural network引用本文复制引用
时赛楠,李京阳,白韶斌,张红旭,夏云峰,邢彤..基于Arrhenius模型的Q195钢热轧过程轧制力预测[J].金属加工（热加工）,2026,(9):21-29,9.基金项目
国家自然科学基金项目(52205402) （52205402）
山西省基础研究计划青年项目(202203021212318). （202203021212318）
