摘要
为了提高冷轧带钢轧制力的预报精度,提出一种有限元法结合神经网络的计算方法,建立冷轧带钢轧制力预报模型。采用弹塑性有限元法对冷轧带钢轧制过程进行数值模拟,得到摩擦因数、压下率、前张应力、后张应力和变形抗力等对轧制力的影响规律。将有限元模拟结果作为训练样本,建立冷轧带钢轧制力的BP神经网络预报模型。结果表明:预报结果与仿真结果吻合良好。
A prediction model of the rolling force for cold rolling mill based on FEM （finite element method） and ANN （artificial neural network） was put forward to improve the prediction precision of the rolling force for cold rolling mill. The cold strip rolling was simulated with elastic-plastic finite element method. From the simulation results, the influence of friction coefficient, reduction, forward tension, backward tension, deformation resistance on the rolling force was identified. With the numerical simulation results, a BP artificial neural network prediction model for cold strip rolling was set up. The results show that prediction results are in accordance with the simulation results.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2013年第11期4456-4460,共5页
Journal of Central South University:Science and Technology
基金
国家自然科学基金资助项目(51027003)
关键词
有限元法
神经网络
冷轧
轧制力
finite element method
artificial neural network
cold rolling
rolling force
