Regressor and structure selection in NARX models using a structured ANOVA approach

被引：49

作者：

Lind, Ingela ^{[1
]}

Ljung, Lennart ^{[1
]}

机构：

[1] Linkoping Univ, Dept Elect Engn, Div Automat Control, SE-58337 Linkoping, Sweden

来源：

AUTOMATICA | 2008年 / 44卷 / 02期

关键词：

nonlinear system identification; structure identification; analysis of variance;

D O I：

10.1016/j.automatica.2007.06.010

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Regressor selection can be viewed as the first step in the system identification process. The benefits of finding good regressors before estimating complex models are especially clear for nonlinear systems, where the class of possible models is huge. In this article, a structured way of using the tool analysis of variance (ANOVA) is presented and used for NARX model (nonlinear autoregressive model with exogenous input) identification with many candidate regressors. (C) 2007 Elsevier Ltd. All rights reserved.

引用

页码：383 / 395

页数：13

共 26 条

[1] NEW LOOK AT STATISTICAL-MODEL IDENTIFICATION [J].

AKAIKE, H .

IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1974, AC19 (06) :716-723

[2]

AUTIN M, 1992, IEEE INT S CIRC SYST, V1, P296

[3]

BARNETT W, 1978, OULTLIERS STAT DATA

[4] BETTER SUBSET REGRESSION USING THE NONNEGATIVE GARROTE [J].

BREIMAN, L .

TECHNOMETRICS, 1995, 37 (04) :373-384

[5]

CHEN R, 1995, BIOMETRIKA, V82, P369

[6] MULTIVARIATE ADAPTIVE REGRESSION SPLINES [J].

FRIEDMAN, JH .

ANNALS OF STATISTICS, 1991, 19 (01) :1-67

[7] Structural modelling with sparse kernels [J].

Gunn, SR ;

Kandola, JS .

MACHINE LEARNING, 2002, 48 (1-3) :137-163

[8] STRUCTURE IDENTIFICATION OF NONLINEAR DYNAMIC-SYSTEMS - A SURVEY ON INPUT OUTPUT APPROACHES [J].

HABER, R ;

UNBEHAUEN, H .

AUTOMATICA, 1990, 26 (04) :651-677

[9] ORTHOGONAL PARAMETER-ESTIMATION ALGORITHM FOR NON-LINEAR STOCHASTIC-SYSTEMS [J].

KORENBERG, M ;

BILLINGS, SA ;

LIU, YP ;

MCILROY, PJ .

INTERNATIONAL JOURNAL OF CONTROL, 1988, 48 (01) :193-210

[10] Regressor selection with the analysis of variance method - Brief paper [J].

Lind, I ;

Ljung, L .

AUTOMATICA, 2005, 41 (04) :693-700

← 1 2 3 →