摘要
给出了板形板厚综合控制模型,提出了基于TH神经网络的动态矩阵设计方法并分析了其收敛特性.使用不变性原理对板形板厚综系统进行了解耦设计,并对板形板厚解耦神经网络预测控制系统,进行了仿真研究.结果表明神经网络可在儿百ns的时间内达到稳定状态,不仅满足了轧钢过程的快速性要求,而且控制精度也得到了提高.
The coupling models for the thickness-crown objects is established. A Dynamic Matrix Controller based on the TH neural networks is given with the conver- gence property. The computer simulations with the AGC-ASC decoupled neural networks predictive control system is complemented and it shows that the stable states of neural networks are reached with on more that one μs, this has not only satisfied the fast prop- erty of rolling process, but also obtained a higher control index.
出处
《北京科技大学学报》
EI
CAS
CSCD
北大核心
1998年第3期301-306,共6页
Journal of University of Science and Technology Beijing
基金
国家"九五"攻关重点项目
关键词
控制
动态矩阵
神经网络
轧制
AG-ASC
control/dynamic matrix control
neural networks
AGC-ASC synthetic system
convergence
