On gradient-based search for multivariable system estimates

被引：71
作者：
Wills, Adrian [1 ]
Ninness, Brett [1 ]
机构：
[1] Univ Newcastle, Sch Elect Engn & Comp Sci, Newcastle, NSW 2308, Australia
来源：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2008年 / 53卷 / 01期
关键词：
gradient-based search (GBS); parameter estimation; system identification;
D O I：
10.1109/TAC.2007.914953
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 addresses the design of gradient-based search algorithms for multivariable system estimation. In particular, the paper here considers so-called "full parametrization" approaches, and establishes that the recently developed "data-driven local coordinate" methods can be seen as a special case within a broader class of techniques that are designed to deal with rank-deficient Jacobians. This informs the design of a new algorithm that, via a strategy of dynamic Jacobian rank determination, is illustrated to offer enhanced performance.
引用
收藏
页码：298 / 306
页数：9
相关论文
共 24 条
[1]  
BERGBOER NH, 2002, P 41 IEEE CDC LAS VE, V1, P616
[2]  
CAINES PE, 1988, LINERA STOCHASTIC SY
[3]  
DEISTLER M, 2005, COMMUNICATION AUG
[4]  
DEISTLER M, 2000, MODEL IDENTIFICATION
[5]  
Dennis, 1996, NUMERICAL METHODS UN
[6]  
Fletcher R., 2013, Practical Methods of Optimization, DOI [10.1002/9781118723203, DOI 10.1002/9781118723203]
[7]   Robust maximum-likelihood estimation of multivariable dynamic systems [J].
Gibson, S ;
Ninness, B .
AUTOMATICA, 2005, 41 (10) :1667-1682
[8]  
Golub GH., 2013, Matrix Computations, DOI 10.56021/9781421407944
[9]  
Hannan E. J., 1988, STAT THEORY LINEAR S
[10]  
LARIMORE WE, 1990, PROCEEDINGS OF THE 29TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-6, P596, DOI 10.1109/CDC.1990.203665
123