DocumentCode
720056
Title
Study of the minimum experiment length to identify linear dynamic systems: A variance based approach
Author
Schoukens, J. ; Kolumban, S.
Author_Institution
Dept. ELEC, Vrije Univ. Brussel, Brussels, Belgium
fYear
2015
fDate
11-14 May 2015
Firstpage
963
Lastpage
968
Abstract
In this paper the effect of short data lengths in system identification is studied. It addresses the question of the minimum required data length that is needed in order to apply the asymptotic results on the uncertainty analysis. this paper is focused on the IIR-case by analyzing initially a first order system. The conclusions are extended to higher order systems by normalizing all results on the time constant of this system, and by adding a model complexity factor.
Keywords
higher order statistics; identification; linear systems; time-varying systems; uncertain systems; complexity factor; data length; higher order system; linear dynamic system; minimum experiment length; system identification; time varying system; uncertainty analysis; variance based approach; Frequency estimation; IIR-models; Small data sets; system identification; variance analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Instrumentation and Measurement Technology Conference (I2MTC), 2015 IEEE International
Conference_Location
Pisa
Type
conf
DOI
10.1109/I2MTC.2015.7151400
Filename
7151400
Link To Document