| 基于BP神经网络的轧机当量刚度系数的研究 |
| |
| 引用本文： | 邱佰平,宋东球. 基于BP神经网络的轧机当量刚度系数的研究[J]. 自动化技术与应用, 2009, 28(8): 4-7 |
| |
| 作者姓名： | 邱佰平 宋东球 |
| |
| 作者单位： | 1. 深圳达实智能股份有限公司,工业智能化事业部,广东,深圳,518057
2. 中南大学,信息科学与工程学院,湖南,长沙,410083 |
| |
| 摘 要： | 从轧机变刚度定义出发，结合轧辊弹跳方程，建立了轧机当量刚度的数学模型，分析影响轧辊刚度系数的因素，得到轧辊位置补偿系数函数，给出三层BP神经网络的训练算法。仿真结果表明BP神经网络在轧制过程中能够很好地预测轧辊的当量刚度值，轧件出口厚度偏差曲线收敛速度快，显著提高了控制系统性能。
|
| 关 键 词： | 刚度 BP神经网络 厚度控制 训练算法 |
BP Neural Network-Based Prediction of the Equivalent Stiffness Coefficient of the Rolling Mill |
| |
| QIU Bai-ping,SONG Dong-qiu. BP Neural Network-Based Prediction of the Equivalent Stiffness Coefficient of the Rolling Mill[J]. Techniques of Automation and Applications, 2009, 28(8): 4-7 |
| |
| Authors: | QIU Bai-ping SONG Dong-qiu |
| |
| Affiliation: | QIU Bai-ping, SONG Dong-qiu( 1. Intelligent Industry Dept., Shenzhen Das Intellitech Co.,Ltd, Shenzhen 518057 China; 2. School of Information Science and Engineering, Central South University, Changsha 410083 China ) |
| |
| Abstract: | This paper presents the mathematic model of the equivalent stiffness of the roller mill based on the bounce function of the roller. Then the compensation coefficient of the roller position is obtained. A three levels BP neural network is used to predict the equicalent stiffness. |
| |
| Keywords: | stiffness BP neural network gauge control training algorithm |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
