Data-Dependent analysis of model validation errors for linear system identification

被引:2
作者
Sadamoto, Tomonori [1 ]
Kaneko, Osamu [1 ]
机构
[1] Univ Electrocommun, Grad Sch Informat & Engn, Dept Mech & Intelligent Syst Engn, 1-5-1 Chofugaoka, Chofu, Tokyo 1828585, Japan
关键词
System identification; Prediction error method; Data-dependent analysis; Reachability and observability; FINITE-SAMPLE PROPERTIES;
D O I
10.1016/j.ejcon.2022.100662
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 study addresses the fundamental question of how accurately dynamical systems can be learned using a limited amount of data. First, we show that a state-space model constructed via a prediction error method perfectly fits a dataset, with no assumptions regarding the data themselves. Motivated by this result, we then analyze how accurately the identified model can mimic the true system for any arbitrary input. We derive necessary and sufficient conditions for the validation error to be exactly zero. Moreover, we introduce a notion of approximation to this characterization from the perspectives of both reachability and observability. Subsequently, we show two upper bounds of the l(2)-norm of the validation error, for any unit impulse input and any input signals with an l(2)-norm less than one. The legitimacy of our analyses is investigated through numerical simulations. (C) 2022 The Author(s). Published by Elsevier Ltd on behalf of European Control Association.
引用
收藏
页数:10
相关论文
共 35 条
[1]   Identification of discrete-time MIMO systems using a class of observable canonical-form [J].
Al-Muthairi, NF ;
Bingulac, S ;
Zribi, M .
IEE PROCEEDINGS-CONTROL THEORY AND APPLICATIONS, 2002, 149 (02) :125-130
[2]  
[Anonymous], 2006, IFAC P
[3]   An overview of approximation methods for large-scale dynamical systems [J].
Antoulas, AC .
ANNUAL REVIEWS IN CONTROL, 2005, 29 (02) :181-190
[4]  
Bernstein D., 2009, Matrix Mathematics: Theory, Facts, and Formulas
[5]   Finite sample properties of system identification methods [J].
Campi, MC ;
Weyer, E .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2002, 47 (08) :1329-1334
[6]   Finite-Sample System Identification: An Overview and a New Correlation Method [J].
Care, Algo ;
Csaji, Balazs Cs ;
Campi, Marco C. ;
Weyer, Erik .
IEEE CONTROL SYSTEMS LETTERS, 2018, 2 (01) :61-66
[7]   The role of vector autoregressive modeling in predictor-based subspace identification [J].
Chiuso, Alessandro .
AUTOMATICA, 2007, 43 (06) :1034-1048
[8]  
Chong MS, 2019, 2019 18TH EUROPEAN CONTROL CONFERENCE (ECC), P968, DOI [10.23919/ecc.2019.8795652, 10.23919/ECC.2019.8795652]
[9]   Data informativity for the open-loop identification of MIMO systems in the prediction error framework [J].
Colin, Kevin ;
Bombois, Xavier ;
Bako, Laurent ;
Morelli, Federico .
AUTOMATICA, 2020, 117
[10]   Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness [J].
De Persis, Claudio ;
Tesi, Pietro .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2020, 65 (03) :909-924