Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《China Mechanical Engineering》 2006-01
Add to Favorite Get Latest Update

Identification of Coiling Temperature Model of Hot Roll Based on Neural Network

Wang Yiqun Wang Haifang Sun Xuguang Zhang Wei Yanshan University,Qinhuangdao,Hebei,066004  
The model of conventional coiling temperature is highly nonlinear. The coiling temperature of hot rolled strip was exactly predicted based on neural network(NN) by means of its approximation to any non-linear system and its ability of prediction. Additional momentum method, which is an improved BP algorithm, was used in the NN. And the predicted coiling temperature was applied to identify characteristic parameters of the static model of coiling temperature with aid of traditional least square method. Finally, identification results are illustrated and verified by referenced values.
【Fund】: 国家自然科学基金资助项目(60474044);; 河北省自然科学基金资助项目(E2004000221)
【CateGory Index】: TG335.11
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved