东北大学学报(自然科学版) ›› 2009, Vol. 30 ›› Issue (9): 1217-1220.DOI: -

• 论著 •    下一篇

基于改进AdaBoost的LF炉成分软测量建模

孙凤琪;   

  1. 东北大学理学院;
  • 收稿日期:2013-06-22 修回日期:2013-06-22 出版日期:2009-09-15 发布日期:2013-06-22
  • 通讯作者: Sun, F.-Q.
  • 作者简介:-
  • 基金资助:
    吉林省科技发展计划项目(20040803)

A new soft sensor modeling method based on improved AdaBoost algorithm for molten steel composition in LF

Sun, Feng-Qi (1)   

  1. (1) School of Sciences, Northeastern University, Shenyang 110004, China
  • Received:2013-06-22 Revised:2013-06-22 Online:2009-09-15 Published:2013-06-22
  • Contact: Sun, F.-Q.
  • About author:-
  • Supported by:
    -

摘要: 针对现有软测量模型更新方法的不足,将增量学习思想与AdaBoost集成学习思想相结合,提出了一种具有增量学习性能的改进AdaBoost集成学习算法.并将该改进的AdaBoost与BP神经网络一起形成了集成BP神经网络,建立了基于改进AdaBoost集成BP网络的软测量模型.该软测量建模新方法可以提高单一BP网络的精度,同时还能保证建模具有增量学习的更新性能.使用该软测量建模新方法建立抚钢60t LF炉钢水成分软测量模型,取得了较好的预测效果,可以满足实际生产的需要.

关键词: AdaBoost, 神经网络, 软测量, 集成算法, 增量学习

Abstract: To make up for the shortages of existing updating methods of soft sensor modeling, a new improved AdaBoost algorithm available to increment learnability was proposed by combining the increment learning with AdaBoost algorithm for ensemble learning. Then, an ensemble BP network was formed by integrating the new improved AdaBoost with BP neural network so as to develop a soft sensor model which will not only improve the accuracy by using single BP network but also ensure the updating ability for increment learning. A soft sensor model of molten steel composition in a 60-ton LF (ladle furnace) in Fu-Steel was developed according to the new method proposed, and its prediction result showed that it can meet the requirements for production.

中图分类号: