|
|||||
|
|
| 一种RBF神经网络在某冷连轧机组轧制力计算中的组合应用 | |
| 引用本文： | 张俊明,刘军,俞小峰,康永林,杨荃. 一种RBF神经网络在某冷连轧机组轧制力计算中的组合应用[J]. 塑性工程学报, 2008, 15(1): 133-137 |
| 作者姓名： | 张俊明 刘军 俞小峰 康永林 杨荃 |
| 作者单位： | 1. 北京科技大学材料科学与工程学院,北京,100083;鞍山钢铁集团鞍钢股份有限公司,鞍山,114011 2. 鞍山钢铁集团鞍钢股份有限公司,鞍山,114011 3. 北京科技大学材料科学与工程学院,北京,100083 4. 北京科技大学机械工程大学院,北京,100083 |
| 摘 要： | 为提高冷连轧机组轧制力计算精度,采用RBF神经网络与数学模型计算轧制力,轧制力偏差在11%以内,远小于单纯使用数学模型;而后组合使用长期数据修正网络、短期数据修正网络、速度修正网络(三者都为RBF神经网络)进一步提高轧制力预报精度。上述方法已成功用于某2130mm冷连轧机组过程控制系统,误差在±5%以内。这充分证明,RBF网络可以成功用于轧制过程控制。 |
| 关 键 词： | 长期数据修正网络 短期数据修正网络 速度修正网络 冷连轧机组轧制力 |
| 文章编号： | 1007-2012（2008）01-0133-05 |
| 收稿时间： | 2006-12-14 |
| 修稿时间： | 2006-12-14 |
Application of the combination of a sort of RBF neural network in roll force calculation of certain tandem cold mill |
|
| ZHANG Jun-ming,LIU Jun,YU Xiao-feng,KANG Yong-lin,YANG Quan. Application of the combination of a sort of RBF neural network in roll force calculation of certain tandem cold mill[J]. Journal of Plasticity Engineering, 2008, 15(1): 133-137 | |
| Authors: | ZHANG Jun-ming LIU Jun YU Xiao-feng KANG Yong-lin YANG Quan |
| Abstract: | To improve precision of roll force calculation of TCM,first RBF neural network and mathematical model is used to calculate roll force,the error is within 11% and is less than using mathematical model only;and then a combination of long-time-data correcting network,short-time-data correcting network and speed correcting network(all of these three are RBF neural networks)is used to improve precision more.The method above has already been used in process control system of certain 2130mm TCM successfully and the error is within 5%.It proves well that RBF neural network can be used in rolling process control successfully. |
| Keywords: | long-time-data correcting network short-time-data correcting network speed correcting network roll force of TCM |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |