[1]孟令启,王建勋,雷明杰,等.中厚板轧机应力状态系数神经网络模型[J].郑州大学学报(工学版),2009,30(02):103-106.
　MENG Lingqi,WANG Jianxun,LEI Mingjie,et al.Neural Network Model of Stress State Coefficient of Medium and Heavy Plate Rolling Mill[J].Journal of Zhengzhou University (Engineering Science),2009,30(02):103-106.
点击复制

中厚板轧机应力状态系数神经网络模型()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
30
期数:
2009年02期
页码:
103-106
栏目:
出版日期:
1900-01-01

文章信息/Info

Title:
Neural Network Model of Stress State Coefficient of Medium and Heavy Plate Rolling Mill
作者:
孟令启; 王建勋; 雷明杰; 等.
郑州大学机械工程学院,河南,郑州,450001, 洛阳钼业集团股份有限公司,河南,洛阳,471500
Author(s):
MENG Lingqi; WANG Jianxun; LEI Mingjie; etc
(1．School of Mechanical Engineering,Zhengzhou University,Zhengzhou 450001，China；2．China Molybdenum Co．Ltd,Luoyang 471500，China
关键词:
应力状态系数;  人工神经网络;  中厚板轧机
Keywords:
stress state coefficient;  artificial neural networks;  Medium and thick plate rolling mills
文献标志码:
A
摘要:
为寻求计算应力状态系数的新方法,以4200轧机轧制的大量实测数据为基础,利用Matlab神经网络工具箱,以轧制前、后钢板厚度为输入神经元,以实测轧制压力并依靠压力公式进行逆运算获得的Qp为输出神经元,建立了轧制变形区的应力状态系数与轧件轧制前后钢板厚度对应关系的BP神经网络模型和GRNN神经网络模型.结果表明,用人工神经网络算法预测应力状态系数是可行的;且通过GRNN神经网络模型和BP模型的对比,说明GRNN网络具有更高的精度和更强的泛化能力.
Abstract:
In order to seek a new method for calculating the stress state coefficient, based on a large number of measured data of 4200 rolling mill, using the Matlab neural network toolbox, taking the thickness of steel plates before and after rolling as input neurons, and taking the Qp obtained by measuring the rolling pressure and relying on the pressure formula for inverse operation as the output neurons, the BP neural network model and GRNN neural network model of the correspondence between the stress state coefficient of the rolling deformation zone and the thickness of the steel plate before and after rolling were established. The results show that it is feasible to predict the stress state coefficient by artificial neural network algorithm. The comparison between the GRNN neural network model and the BP model shows that the GRNN network has higher accuracy and stronger generalization ability.

相似文献/References:

[1]李亦芳,程万里,刘建厅..基于人工神经网络与回归分析的水质预测[J].郑州大学学报(工学版),2008,29(01):106.
　LI Yifang,Cheng Wanli,Liu Jian Hall.Water quality prediction based on artificial neural network and regression analysis[J].Journal of Zhengzhou University (Engineering Science),2008,29(02):106.
[2]马细霞,陈鑫,胡铁成..基于ANFIS模型的年径流预报方法[J].郑州大学学报(工学版),2007,28(03):121.[doi:10.3969/j.issn.1671-6833.2007.03.032]
　Ma Xiaoxia,CHEN Xin,Hu Tiecheng.Annual runoff forecasting method based on ANFIS model[J].Journal of Zhengzhou University (Engineering Science),2007,28(02):121.[doi:10.3969/j.issn.1671-6833.2007.03.032]
[3]郭进军,张雷顺,李平先,等.火灾后新老砼粘结加固劈拉性能的神经网络模拟[J].郑州大学学报(工学版),2003,24(04):55.[doi:10.3969/j.issn.1671-6833.2003.04.013]
　Guo Jinjun,ZHANG Leishun,LI Pingxian,et al.Neural network simulation of new and old concrete bonding reinforcement splitting performance after fire[J].Journal of Zhengzhou University (Engineering Science),2003,24(02):55.[doi:10.3969/j.issn.1671-6833.2003.04.013]

更新日期/Last Update: 1900-01-01