Improvement of Shape Recognition Performance of Sendzimir Mill Control Systems Using Echo State Neural Networks
Jung-hyun PARK1,Seong-ik HAN2,Jong-shik KIM1
1. School of Mechanical Engineering, Pusan National University, Busan 609735, Korea 2. School of Electrical Engineering, Pusan National University, Busan 609735, Korea
Improvement of Shape Recognition Performance of Sendzimir Mill Control Systems Using Echo State Neural Networks
Jung-hyun PARK1,Seong-ik HAN2,Jong-shik KIM1
1. School of Mechanical Engineering, Pusan National University, Busan 609735, Korea 2. School of Electrical Engineering, Pusan National University, Busan 609735, Korea
ժҪ High rigidity twenty-high Sendzimir mills (ZRMs) are widely used for rolling stainless steels, silicon sheets, etc. A ZRM uses a small diameter work roll to produce massive rolling forces. Since a work roll with a small diameter can be bent easily, strips often have complex shapes with mixed quarter and deep edge waves in the shape of plates. In order to solve this problem, fuzzy neural network controls are generally used for shape recognition in ZRM control systems. Among various neural network types, the multi-layer perceptron (MLP) is typically used in current ZRMs. However, an MLP causes the loss of a large amount of shape recognition data. To improve the shape recognition performance of ZRM control systems, echo state networks (ESNs) are proposed to be used. Through simulation results, it is found that shape recognition performance could be improved using the proposed ESN method.
Abstract��High rigidity twenty-high Sendzimir mills (ZRMs) are widely used for rolling stainless steels, silicon sheets, etc. A ZRM uses a small diameter work roll to produce massive rolling forces. Since a work roll with a small diameter can be bent easily, strips often have complex shapes with mixed quarter and deep edge waves in the shape of plates. In order to solve this problem, fuzzy neural network controls are generally used for shape recognition in ZRM control systems. Among various neural network types, the multi-layer perceptron (MLP) is typically used in current ZRMs. However, an MLP causes the loss of a large amount of shape recognition data. To improve the shape recognition performance of ZRM control systems, echo state networks (ESNs) are proposed to be used. Through simulation results, it is found that shape recognition performance could be improved using the proposed ESN method.
ͨѶ����:
Jong Shik Kim
E-mail: jskim@pnu.edu; jskim@pusan.ac.kr
����:
Jung-hyun PARK,Seong-ik HAN,Jong-shik KIM. Improvement of Shape Recognition Performance of Sendzimir Mill Control Systems Using Echo State Neural Networks[J]. �й������ڿ���, 2014, 21(3): 321-327.
Jung-hyun PARK,Seong-ik HAN,Jong-shik KIM. Improvement of Shape Recognition Performance of Sendzimir Mill Control Systems Using Echo State Neural Networks. Chinese Journal of Iron and Steel, 2014, 21(3): 321-327.
2014, Vol. 21 
