Application of Smith Predictor Based on Single Neural Network in Cold Rolling Shape Control

摘要：

In the cold rolling flatness control system, the feedback control signals of the actuator are provided by the shape-meter, which is always located at a certain distance away from the exit of the cold rolling mill. Thus the whole control system is a system with time delay. And the speed as well as precision of close-loop response is affected. A Smith predictor with single neural network PID controller is proposed to offset this disadvantage. The control system shows better controlling performance than without Smith predictor. Experiment results with work-roll bender control system indicate the designed systems effectiveness.

关键词： Shape control Time delay Single Neural network Smith predictor

作者: Wang Yiqun Sun Fu Liu Jian Sun Menghui Xie Yihan

作者单位: College of Mechanical Engineering ofYanshan University, Qinhuangdao, Hebei, 066004, China School of Information Science and Technology, Tsinghua University, Beijing, 100084, China

会议类型: 国际会议

会议名称: The Fifth International Symposium on Fluid Power Transmission and Control(ISFP2007)（2007年国际流体动力传输与控制学术会议）

会议地点: 北戴河

会议语种:英文

页码: 739-742

在线出版日期: 2007-06-06（万方平台首次上网日期，不代表论文的发表时间）