计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (16): 210-212.DOI: 10.3778/j.issn.1002-8331.2010.16.061

• 工程与应用 • 上一篇    下一篇

基于IGA优化WNN的产品质量建模方法

焦国帅1,孔金生1,万百五2   

  1. 1.郑州大学 电气工程学院,郑州 450001
    2.西安交通大学 系统工程研究所,西安 710049
  • 收稿日期:2008-12-01 修回日期:2009-02-09 出版日期:2010-06-01 发布日期:2010-06-01
  • 通讯作者: 焦国帅

Products quality modeling method based on WNN optimized by IGA

JIAO Guo-shuai1,KONG Jin-sheng1,WAN Bai-wu2   

  1. 1.Electrical Engineering College,Zhengzhou University,Zhengzhou 450001,China
    2.Graduate School of System Engineering,Xi’an Jiaotong University,Xi’an 710049,China
  • Received:2008-12-01 Revised:2009-02-09 Online:2010-06-01 Published:2010-06-01
  • Contact: JIAO Guo-shuai

摘要: 针对某轧钢厂的热连轧产品质量生产过程,对遗传算法(GA)的交叉和变异操作进行改进,给出了基于改进的遗传算法(IGA)优化小波神经网络(WNN)结构的产品质量建模方法。仿真实例表明:该建模方法既保留了GA的全局搜索能力和WNN学习算法简单有效的特点,又具有网络训练速度快、建模精度高等优点,表明了该方法的有效性。

关键词: 轧钢生产过程, 产品质量建模, 遗传算法, 小波神经网络

Abstract: Aiming at the quality production process of Hot Rolling Mill products of a rolling mill,the crossover and mutation operations of GA get improved,then a products quality modeling method based on the WNN optimized by IGA is presented.Simulation results show that the quality modeling method not only maintains the features of global searching ability of GA and the simplicity and effectiveness of WNN learning algorithm,but also has the advantages of the fast network training speed and the high modeling precision,and then the effectiveness of the proposed method is indicated.

Key words: steel rolling production process, products quality modeling, Genetic Algorithm(GA), Wavelet Neural Network(WNN)

中图分类号: