Optimal experimental design and some related control problems

被引：162
作者：
Pronzato, Luc [1 ]
机构：
[1] Univ Nice Sophia Antipolis, CNRS, Lab 13S, Nice, France
来源：
AUTOMATICA | 2008年 / 44卷 / 02期
关键词：
parameter estimation; design of experiments; adaptive control; active control; active learning;
D O I：
10.1016/j.automatica.2007.05.016
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper traces the strong relations between experimental design and control, such as the use of optimal inputs to obtain precise parameter estimation in dynamical systems and the introduction of suitably designed perturbations in adaptive control. The mathematical background of optimal experimental design is briefly presented, and the role of experimental design in the asymptotic properties of estimators is emphasized. Although most of the paper concerns parametric models, some results are also presented for statistical learning and prediction with nonparametric models. (C) 2007 Elsevier Ltd. All rights reserved.
引用
收藏
页码：303 / 325
页数：23
相关论文
共 197 条
[71]   For model-based control design, closed-loop identification gives better performance [J].
Hjalmarsson, H ;
Gevers, M ;
deBruyne, F .
AUTOMATICA, 1996, 32 (12) :1659-1673
[72]   On sequential designs in nonlinear problems [J].
Hu, I .
BIOMETRIKA, 1998, 85 (02) :496-503
[73]   Strong consistency of Bayes estimates in stochastic regression models [J].
Hu, IC .
JOURNAL OF MULTIVARIATE ANALYSIS, 1996, 57 (02) :215-227
[74]   Strong consistency in stochastic regression models via posterior covariance matrices [J].
Hu, IC .
BIOMETRIKA, 1997, 84 (03) :744-749
[75]   Strong consistency of Bayes estimates in nonlinear stochastic regression models [J].
Hu, IC .
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1998, 67 (01) :155-163
[76]  
Huber P. J., 1981, ROBUST STAT
[77]  
Ivanov AV, 2004, MATH METHODS STAT, V13, P153
[78]   Input design via LMIs admitting frequency-wise model specifications in confidence regions [J].
Jansson, H ;
Hjalmarsson, H .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2005, 50 (10) :1534-1549
[79]   Mixed H∞ and H2 input design for identification [J].
Jansson, H ;
Hjalmarsson, H .
2004 43RD IEEE CONFERENCE ON DECISION AND CONTROL (CDC), VOLS 1-5, 2004, :388-393
[80]  
Jansson H., 2005, P 16 IFAC WORLD C AU
3456789101112