首页 | 本学科首页   官方微博 | 高级检索  
     

UC轧机二次型板形缺陷模糊神经网络控制
引用本文:陈丽,李建更,乔俊飞,王笑波.UC轧机二次型板形缺陷模糊神经网络控制[J].控制工程,2005,12(5):438-441.
作者姓名:陈丽  李建更  乔俊飞  王笑波
作者单位:1. 北京工业大学,电子信息与控制工程学院,北京,100022
2. 宝钢技术中心自动化所,上海,201900
基金项目:国家自然科学基金与宝钢集团公司联合资助项目(50274003)
摘    要:针对UC轧机中间辊弯辊回路的非线性过程精确控制问题,将模糊控制与神经网络结合,设计模糊神经网络控制器并将其应用于对中间辊弯辊回路的控制中。介绍了由神经网络结构组成的模糊控制器,网络完成模糊化、模糊推理、清晰化操作,模糊规则和系统的输入输出由梯度下降法进行调整。仿真结果表明,这种模糊神经网络控制器能很好地跟踪二次板形的目标设定值,系统的响应快,超调小,鲁棒性强。

关 键 词:板形控制  液压弯辊  模糊神经网络  BP网络
文章编号:1671-7848(2005)05-0438-04
修稿时间:2004年9月30日

Fuzzy Neural Network Control for Shape Defects of Quadratic Form of UC Rolling Mill
CHEN Li,LI Jian-Geng,QIAO Jun-fei,WANG Xiao-bo.Fuzzy Neural Network Control for Shape Defects of Quadratic Form of UC Rolling Mill[J].Control Engineering of China,2005,12(5):438-441.
Authors:CHEN Li  LI Jian-Geng  QIAO Jun-fei  WANG Xiao-bo
Affiliation:CHEN Li 1,LI Jian-geng 1,QIAO Jun-fei 1,WANG Xiao-bo 2
Abstract:The problem of shape defects of quadratic form in the control system of universal crown rolling mill is discussed. To realize accurate control of bending of the intermediate rolls, a fuzzy neural network is presented to control the loops of bending of the intermediate rolls in which fuzzy logic control and neural network are combined. The experimental result shows that the control effect is excellent, with small ultra-regulated and good robustness, reaching the goal of the intelligence control for shape on line.
Keywords:shape control  hydraulic bending roll  fuzzy neural network  BP network
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号