东北大学学报(自然科学版) ›› 2008, Vol. 29 ›› Issue (4): 521-524.DOI: -

• 论著 • 上一篇    下一篇

基于贝叶斯神经网络的SPA-H热轧板力学性能预测

贾涛;刘振宇;胡恒法;王国栋;   

  1. 东北大学轧制技术及连轧自动化国家重点实验室;东北大学轧制技术及连轧自动化国家重点实验室;梅山钢铁公司技术中心;东北大学轧制技术及连轧自动化国家重点实验室 辽宁沈阳110004;辽宁沈阳110004;江苏南京210000;辽宁沈阳110004
  • 收稿日期:2013-06-22 修回日期:2013-06-22 出版日期:2008-04-15 发布日期:2013-06-22
  • 通讯作者: Jia, T.
  • 作者简介:-
  • 基金资助:
    国家“十一五”科技支撑项目(2006BAE03A08)

Mechanical property prediction for hot rolled SPA-H steel using Bayesian neural network

Jia, Tao (1); Liu, Zhen-Yu (1); Hu, Heng-Fa (2); Wang, Guo-Dong (1)   

  1. (1) State Key Laboratory of Rolling and Automation, Northeastern University, Shenyang 110004, China; (2) Technical Research Institute, Meishan Steel Company, Nanjing 210000, China
  • Received:2013-06-22 Revised:2013-06-22 Online:2008-04-15 Published:2013-06-22
  • Contact: Jia, T.
  • About author:-
  • Supported by:
    -

摘要: 研究了基于贝叶斯方法的神经网络及其在SPA-H热轧板力学性能预测中的应用.在网络的目标函数中引入代表网络复杂程度的惩罚项,融入"奥克姆剪刀"理论,防止网络"过训练"的发生.考虑到网络在应用中的实际问题,在前人改进的算法基础上,采用Levenberg-Marquardt算法训练网络,提高了该网络的收敛速度.利用上述网络进行SPA-H集装箱热轧板力学性能预测,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.

关键词: 贝叶斯方法, Levenberg-Marquardt算法, 神经网络, 集装箱板, 力学性能

Abstract: The neural network based on Bayesian method and its application to the mechanical property prediction were studied for hot-rolled SPA-H sheet. Integrated with the Occam's razor theory, a penalty term which could be interpreted as an indication of the complexity of the network was introduced into the objective function to prevent the occurrence of overfitting. Considering the practical problems in the application of the network and based on earlier work which have improved the Bayesian method, the Levenberg-Marquardt algorithm was employed to train the network, thus expediting the convergence rate. The network has been used in the prediction of mechanical properties of hot-rolled SPA-H sheet. Compared with the conventional BP neural network, it has the advantages of faster convergence rate, higher stability and ability for generalization.

中图分类号: