针对板形板厚综合系统具有强耦合、非线性、含纯滞后环节的特点,建立了板形板厚耦合模型,并在对其进行神经网络解耦设计的基础上提出了基于对角递归神经网络(DRNN)整定PID的板形板厚解耦控制方法,然后根据带钢冷轧情况提出神经网络解耦对不同塑性刚度参数的实际适用范围.仿真结果表明,该解耦控制系统具有比传统前馈补偿解耦PID控制效果好、响应速度快、自适应跟随能力强等优点,并且符合实际轧制要求,有效地提高了板形板厚的控制精度.
In view of the process of automatic flatness control and automatic gauge control which is a nonlinear systern with strong coupling and pure time delay,a strip flatness and gauge coupling model is established,then a strip flatness and gauge decoupling control method is developed based on self-tuning PID with diagonal recurrent neural network(DRNN)on the basis of the neural network decoupling design,and a scope is available for the different plastic rigidity parameter.The simulation results indicate that control system has the good decoupling effect,and the speed of response is quick,and has good performances of adaptively tracking target and so on.Meanwhile it meets the actual rolling requirements and enhances effectively strip flatness and gauge control precision.
参考文献
| [1] | 贾春玉,王英华,周会锋.板形板厚综合调节神经模糊智能方法的研究[J].中国机械工程,2003(20):1741-1744. |
| [2] | 令狐克志,何安瑞,杨荃,赵林,郭晓波.热轧带钢板形板厚反馈解耦控制[J].北京科技大学学报,2007(03):338-341. |
| [3] | 彭鹏,杨荃.冷连轧机板形板厚综合解耦控制系统[J].钢铁,2007(08):52-55. |
| [4] | 王莉,陈缅仁,孙一康,封苏伟.基于PID神经元网络的冷连轧板形板厚多变量综合控制[J].冶金自动化,2002(02):15-18. |
| [5] | 连家创;刘宏民.板厚板形控制[M].北京:兵器工业出版社,1996 |
| [6] | Chao-Chee Ku;Lee K.Y. .Diagonal recurrent neural networks for dynamic systems control[J].IEEE Transactions on Neural Networks,1995(1):144-156. |
| [7] | 段慧达 .基于对角递归网络的汽车磷化温度控制的研究[D].北京科技大学,2003. |
| [8] | 黄均安,王跃,李秀珍.多变量系统的神经网络解耦[J].工业仪表与自动化装置,2008(04):11-14. |
| [9] | Ooyen A V;Nienhuis B .Improving the Convergence of the Back Propagation Algorithm[J].Neural Networks,1992,3(01):95. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%