Research on Internal Model Control for Nonlinear System Based on Weighted LS-SVM
-
摘要: 建立了基于加权最小二乘支持向量机(weighted least squares support vector machines,Weighted LS-SVM)的非线性系统的内部模型和逆模型,并提出了一种基于加权LS-SVM的非线性系统的内模控制算法。仿真试验结果表明:加权LS-SVM建立的非线性系统内部模型和逆模型都具有很高的建模精度和较强的泛化能力,基于加权LS-SVM的内模控制算法对非线性系统具有良好的控制性能,较强的抗干扰能力和鲁棒性能。
-
关键词:
- 加权最小二乘支持向量机 /
- 非线性系统 /
- 内模控制
Abstract: An internal model and an inverse model of nonlinear system are established based on Weighted Least Squares Support Vector Machines(Weighted LS-SVM).Then the algorithm of internal model control for nonlinear system based on Weighted LS-SVM is proposed.The simulation results show that the internal model and the inverse model of nonlinear system based on Weighted LS-SVM have high modeling precision and strong generalization ability.And the algorithm of internal model control for nonlinear system based on Weighted LS-SVM has good control performance,strong anti-jamming ability and robustness. -
[1] 宋夫华.支持向量机逆系统方法及其应用研究[D]. 杭州:浙江大学, 2006 [2] 孙宗海.支持向量机及其在控制中的应用研究[D]. 杭州:浙江大学, 2003 [3] 钟伟民.支持向量机在先进控制中的应用研究[D]. 杭州:浙江大学, 2006 [4] 汪辉.增量型支持向量机回归训练算法及在控制中的应用[D]. 杭州:浙江大学, 2006 [5] 陈娟, 董翠英.基于神经网络的非线性系统复合内模控制[J]. 哈尔滨理工大学学报, 2004, 9(1): 17~20 [6] Vapnik V N.The Nature of Statistical Learning Theory[M].New York: Springer-Verlag, 1995 [7] Suykens J A K,Vandewalle J.Least squares support vector ma-chine classifiers[J]. Neural Processing Letters,1999, 9(3):293~300 [8] Suykens J A K, De Brabanter J, Lukas L, Vandewalle J.Weigh-ted least squares support vector machines: robustness and sparseapproximation[J]. Neurocomputing, 2002, 48(1-4):85~105 [9] David H A.Early sample measures of variability[J]. StatisticalScience, 1998, 13(4):368~377 [10] 胡良谋等.基于 SVR 的非线性系统故障诊断研究[J]. 机械科学与技术, 2010, 29(2):225~228
点击查看大图
计量
- 文章访问数: 151
- HTML全文浏览量: 29
- PDF下载量: 10
- 被引次数: 0