Research on a theory-intelligent dynamic matrix model of flatness control for cold-rolled strips
To increase the precision of flatness control considering the essential principles of the rolling process and measured data from the rolling process,a theory-intelligent dynamic matrix model of flatness control was built using theory and intelligent methods synthetically.The network model for rapidly calculating the theory effective matrix is built with a BP (Back Propagation) network optimized by the particle swarm algorithm.The network model for rapidly calculating the measurement effective matrix is built with an RBF network optimized by the cluster algorithm.The flatness control model can track the practical situation of the rolling process by online self-learning.The scheme for the flatness control calculation was built by combining the theory control matrix and the measurement control matrix.The results of the simulation experiment indicate that the built theory-intelligent dynamic matrix model of flatness control demonstrated a stable control process and a high precision and provides a new method for researching the flatness online control model.
Flatness control Dynamic matrix Theory model Neural network Particle swarm Cluster
LIU Hong-min SHAN Xiu-ying JIA Chun-yu SUN Jian-liang
National Engineering Research Center for Equipment and Technology of Cold Strip Rolling,Mechanical Engineering College,Yanshan University,Qinhuangdao,066004,China;State Key Laboratory of Metastable Materials Science and Technology,Yanshan University,Qinhuangdao,066004,China
国际会议
Asia Steel International conference 2012(第五届亚洲钢铁大会)
北京
英文
1-6
2012-09-23（万方平台首次上网日期，不代表论文的发表时间）