期刊文献+

智能算法在双辊铸轧过程铸轧力计算中的应用

Casting rolling force calculation for twin-roll strip casting using intelligence method
下载PDF
导出
摘要 在双辊铸轧过程中,铸轧力的控制是铸轧过程稳定进行和提高薄带质量的关键.为了控制铸轧力,必须建立铸轧力计算数学模型,本文采用了一种基于贝叶斯方法的前向神经网络训练算法以提高网络的泛化能力,在网络的目标函数中引入了表示网络结构复杂性的惩罚项,融入"奥克姆剪刀"理论,避免了网络训练的过拟合.将上述网络应用于铸轧过程的铸轧力计算,具有很高的计算精度,同时在收敛速度、稳定性和泛化能力方面都优于传统的BP神经网络. In the process of twin- roll strip casting, rolling force control is the key of the stabilization of the process and the improvement of strips quality. In order to control the rolling force, a mathematic model of rolling force must be established. Bayesian regularization was applied to the training of feedforward neural networks in order to improve their generalization capabilities. Coupled with the "Occam' s razor" theory, a penalty item which could be interpreted as an indication of network complexity, was introduced into the performance function to prevent the occurrence of overfitting. The network was applied in Twin- Roll strip casting rolling force calculation with high precision. Compared with the traditional back - propagation neural network, the Bayesian network has a faster convergence rate, better stability and generalization ability.
出处 《材料与冶金学报》 CAS 2009年第2期140-144,共5页 Journal of Materials and Metallurgy
基金 国家973项目资助(2004CB619108)
关键词 贝叶斯方法 神经网络 双辊铸轧 “奥克姆剪刀”理论 Bayesian method neural network Twin - Roll strip casting "Occam' s razor" theory
  • 相关文献

参考文献13

  • 1Klaus SCHWERDTFEGER Benefits. Challenges and limits in new routes for hot strip production [J ]. ISIJ International, 1998, 38(8): 852-861.
  • 2Robson A L,Thompson G L. Direct casting of thin strip[J]. Materials World, 1995, 16 (3) :222-224.
  • 3邸洪双,鲍培玮,苗雨川,王国栋,刘相华.双辊铸轧薄带钢实验研究及工艺稳定性分析[J].东北大学学报(自然科学版),2000,21(3):274-277. 被引量:39
  • 4Bernhard S, Enning M, Rake H. Automation of a laboratory plant for direct casting of thin steel strips [J ]. Control Engineering Practice, 1994,2 (6) : 961 - 967.
  • 5孙斌煜,张洪,孙航临.流函数法在铸轧变形理论分析中的应用[J].中国有色金属学报,1999,9(1):115-117. 被引量:12
  • 6Foresee F D, Hagan M T. Gauss - newton approximation to bayesian learning [ C ]//In: Proceedings of the International Conference on Neural Networks. Houston,Texas. 1997.
  • 7魏东,张明廉,蒋志坚,孙明.基于贝叶斯方法的神经网络非线性模型辨识[J].计算机工程与应用,2005,41(11):5-8. 被引量:28
  • 8Orre R, Lansner A, Bate A, et al. Bayesian neural networks with confidence esumations applied to data mining [ J ]. Computational Statistics & Data Analysis, 2000,34 (4) : 473 -493
  • 9Mackay D J C. A practical bayesian framework for backpropagation networks[J ]. Neural Computation, 1992a, 4 (3) : 448 -472.
  • 10Penny W D, Roberts S J. Bayesian neural networks for classification: how useful is the evidence framework [J ]. Neural Networks, 1999, 12 : 877 -892.

二级参考文献20

  • 1史荣,崔小朝,孙斌煜,陆锁柱.铝带坯连续铸轧凝固过程的数值模拟[J].中国有色金属学报,1996,6(2):98-101. 被引量:10
  • 2孙斌煜 张洪.-[J].中国有色金属学报,1995,5(3):101-101.
  • 3Kruglinski D J 潘爱民 乇国印译.Visual C++技术内幕(第四版)【M】.北京:清华大学出版社,1999.673-677.
  • 4Sartori M A,Antsaklis P J.A simple method to drive bounds on the size and to train multiplayer neural network[J].IEEE Trams on Neural Networks, 1993, 4(5): 740-747.
  • 5Hagan M T,Demuth H B,Beale M. Neural network design[M].NewYork: PWS Publishing Company, 1996, 352-404.
  • 6Hagan M T. Menhaj M B. Training feed-forward networks with the marqurdt algorithm[J]. IEEE Transaction on Neural Networks. 1994,5(6): 989-993.
  • 7孙斌煜,中国有色金属学报,1995年,5卷,3期,101页
  • 8潘文全,工程流体力学,1988年,56页
  • 9谢定裕,流体力学,1987年,48页
  • 10白丙忠,世界金属导报,1996年

共引文献77

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部