基于最小二乘支持向量机的非线性通用模型自适应控制  

Nonlinear Common Model Adaptive Control Based on Least Squares Support Vector Machines

作　　者：尹越栋[1] 郭丙君[1] 

机构地区：[1]华东理工大学信息科学与工程学院,上海200237

出　　处：《华东理工大学学报（自然科学版）》2009年第6期922-925,共4页Journal of East China University of Science and Technology

摘　　要：将模型参考自适应控制方法应用到基于最小二乘支持向量机的通用模型控制策略中,将非线性过程模型应用逆系统的方法可以在控制算法中直接嵌入过程模型,从而克服了通用模型控制器要求过程一阶微分模型应该有显式解的局限性,保证了通用模型控制策略的可实现性。另一方面,加入模型参考自适应环节,提高了该控制器的实时性和鲁棒性,其参数具有明显的物理意义,参数整定方便。仿真实验结果验证了该控制策略的有效性和更好的鲁棒性。By using model reference adaptive control,this paper proposes a common model adaptive control based on least squares support vector machines（LSSVM）.In this proposed method,the process model is embed into the controller by the inverted control method so as to overcome the weakness of requiring explicit solutions for the first-order differential equation about the controlled process in the common model control（CMC）.Besides,the introducing of model reference adaptive may improve the reliability and robustness of the controlled systems.The parameters of CMAC based on least squares support vector machines have explicit physics meaning and easily tunes.The simulation results illustrate the effectiveness and robustness of the proposed method.

关 键 词：通用模型控制 最小二乘支持向量机 模型参考自适应 鲁棒性 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]