计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (28): 187-189.DOI: 10.3778/j.issn.1002-8331.2008.28.062

• 工程与应用 • 上一篇    下一篇

基于IGA-SVM的发酵过程建模及优化控制

王鲜芳1,2,潘 丰1   

  1. 1.江南大学 通信与控制工程学院,江苏 无锡 214122
    2.河南科技学院 信息工程系,河南 新乡 453003
  • 收稿日期:2008-04-10 修回日期:2008-05-19 出版日期:2008-10-01 发布日期:2008-10-01
  • 通讯作者: 王鲜芳

Modelling and Optimized Controlling of fermentation process based on IGA-SVM

WANG Xian-fang1,2,PAN Feng1   

  1. 1.School of Communication and Control Engineering,Jiangnan University,Wuxi,Jiangsu 214122,China
    2.Department of Information Engineering,Henan Institute of Science and Technology,Xinxiang,Henan 453003,China
  • Received:2008-04-10 Revised:2008-05-19 Online:2008-10-01 Published:2008-10-01
  • Contact: WANG Xian-fang

摘要: 利用免疫遗传算法(IGA,Immune Genetic Algorithm)的全局搜索功能和支持向量机(SVM,Support Vector Machine)泛化能力强的特点,选择合适的状态变量,对发酵过程建立动态时变模型。利用该模型和算法对一些不能在线测量的生化状态变量进行在线预估,并对一些关键的操作变量进行了优化。通过对谷氨酸发酵过程的实际应用,验证了该方法的有效性。

关键词: 免疫遗传算法, 支持向量机, 状态变量, 智能控制

Abstract: Utilizing the global search ability of Immune Genetic Algorithm(IGA) and the high generalization ability of Support Vector Machine(SVM),selecting the appropriate state variables,a dynamic time-varying model has been built.Some biochemical state variables which can not be measured on-line would be pre-estimated by using this method,and some operational variables would be optimized.It is proved that the method is efficiency through the practical application of glutamic acid fermentation process.

Key words: Immune Genetic Algorithm(IGA), Support Vector Machine(SVM), state variables, intelligence control