计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (27): 220-221.

• 工程与应用 • 上一篇    下一篇

基于遗传算法的多模型自适应控制

康运锋1,李晓理1,艾 博2   

  1. 1.京科技大学 信息工程学院 自动化系,北京 100083
    2.北京师范大学 数学科学学院,北京 100875
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-09-21 发布日期:2007-09-21
  • 通讯作者: 康运锋

Multiple model adaptive control based on genetic algorithm

KANG Yun-feng1,LI Xiao-li1,AI Bo2   

  1. 1.Department of Automation,Information and Engineering School,University of Science and Technology Beijing,Beijing 100083,China
    2.School of Mathematic Science,Beijing Normal University,Beijing 100875,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-21 Published:2007-09-21
  • Contact: KANG Yun-feng

摘要: 利用多个固定模型(或元素模型)来逼近含未知参数的被控系统,基于每一个元素模型建立最优控制器,并由各局部模型控制器的加权和构成被控系统的控制器。对于这种多模型自适应控制器,在每一个采样时刻,每一个元素模型的权值将由遗传算法计算得出。仿真结果表明,采用该文提出的控制器,当被控对象的模型参数剧烈变化时系统输出依然可以很好地跟踪设定值。

关键词: 遗传算法, 多模型, 自适应控制

Abstract: Multiple fixed or component models are used to approximate the controlled system with unknown parameters.The controller of system can be formed as weighted sum of the output of controller based on each component model.To form this kind of multiple model adaptive controller,the weight associated with each model will be calculated in every sample time by genetic algorithm.The effectiveness of the proposed method can be shown by simulation study.The output of the system can also trace the set-point value very well when the parameters of the system change abruptly.

Key words: Genetic algorithm, multiple model, adaptive control