Structure selection and parameter set-membership identification for nonlinear systems
-
摘要: 基于支持向量回归和RBF(Radial Basis Function)神经网络,研究了带有未知但有界噪声的非线性系统的集员辨识问题.推导了噪声界以及支持向量个数与ε-不敏感参数之间的关系,给出了利用噪声界选择ε-不敏感参数的方法.描述了通过支持向量回归选择RBF神经网络规模的方法.该方法以Gaussian核函数作为径向基函数,支持向量作为径向基函数的中心构建RBF神经网络.运用改进的OBE(Optimal Bounding Ellipsoid)算法对RBF神经网络的权值进行辨识,得到与给定输入输出数据和噪声界序列一致的一类RBF神经网络.仿真算例验证了算法的有效性.Abstract: Based on support vector regression and radial basis function (RBF) neural network, the set-membership identification for nonlinear systems with unknown-but-bounded noise was investigated. The relationships among the ε-insensitive parameter, noise bounds and the number of support vectors were deduced, and the method of determining the ε-insensitive parameter using the noise bounds was introduced. The algorithm of choosing the scale of RBF neural network via support vector regression was described, in which the Gaussian kernel function was taken as the radial basis function and the support vector as its center parameters. After the structure of the RBF neural network was determined, all the feasible weight vectors of the RBF neural network were found by the optimal bounding ellipsoid (OBE) algorithm and a class of feasible nonlinear models were formed which were consistent with the given noise bound series and the input-output data set. A simulation example shows that the proposed algorithm is effective.
-
[1] Huang Y F.A recursive estimation algorithm using selective updating for spectral analysis and adaptive signal processing [J].IEEE Transaction on Acoustics, Speech, and Signal Processing, 1986, 34 (5): 1331-1334 [2] Belforte G, Bona B.An improved parameter identification algorithm for signals with unknown-but-bounded errors // Barker H A, Young P C.7th IFAC/IFORS Symposium on Identification and System Parameter Estimation.York: Pergamon Press, 1985: 1507-1512 [3] Deller J R Jr, Gollamudi S, Nagaraj S, et al.Convergence analysis of the quasi-OBE algorithm and related performance issues[J].International Journal of Adaptive Control and Signal Processing, 2007, 21(6):499 -527 [4] Chisci L, Garulli A,Zappa G.Recursive state bounding by parallelotopes[J].Automatica, 1996, 32(7):1049-1055 [5] Sun X F, Fan Y Z.Guaranteed sensor fault detection and isolation via recursive rectangular parallelepiped bounding in state-set estimation //Proc 3rd ASCC.Shanghai: , 2000: 3041-3046 [6] Alamo T, Bravo J M,Camacho E F.Guaranteed state estimation by zonotopes[J].Automatica, 2005, 41(6):1035-1043 [7] Walter E,Piet-lahanier H.Exact recursive polyhedral description of the feasible parameter set for bounded-error models[J].IEEE Transactions on Automatic Control, 1989, 34(8): 911-915 [8] Kieffer M,Walter E.Interval analysis for guaranteed non-linear parameter and state estimation[J].Mathematical and Computer Modelling of Dynamical Systems, 2005, 11(2): 171-181 [9] Alamo T, Bravo J M, Redondo M J, et al.A set-membership state estimation algorithm based on DC functions [J].Automatica, 2008, 44(1):216-224 [10] Keesman K J,Stappers R.Nonlinear set-membership estimation: a support vector machine approach[J].Journal of Inverse and Ill-posed Problem, 2004, 12(1): 27-41 [11] Scholte E,Campbell M E.A nonlinear set-membership filter for on-line application[J].International Journal of Robust and Nonlinear Control,2003, 13(15):1337-1358 [12] Cristianini N, Shawe-Taylor J.An introduction to support vector machines and other kernel-based learning methods[M].New York:Cambridge University Press, 2000: 30-32, 114-118 -
点击查看大图
计量
- 文章访问数: 3811
- HTML全文浏览量: 47
- PDF下载量: 954
- 被引次数: 0
下载:
