DocumentCode :
2165260
Title :
Fractional system identification using recursive algorithms approach
Author :
Djouambi, Abdelbaki ; Besancon, Alina Voda ; Charef, Abdelfatah
Author_Institution :
Lab. of Autom. Control of Grenoble, St. Martin d´Hères, France
fYear :
2007
fDate :
2-5 July 2007
Firstpage :
1436
Lastpage :
1441
Abstract :
A new identification method in the time domain of fractional systems described by fractional order linear differential equations is proposed in this paper. The basic idea is to extend the classical recursive least squares method to fractional order systems using fractional order ARX model. Parameter estimation of fractional order ARX model is then performed, through the recursive least squares method (RLS), and then through the recursive instrumental variable method (RIV) based least squares technique. Real-time identification for time-variant fractional systems is also proposed. Numerical examples are presented to exhibit the properties and the performances of the proposed methodology.
Keywords :
least squares approximations; linear differential equations; recursive estimation; time-domain analysis; RIV based least squares technique; RLS method; fractional order ARX model; fractional order linear differential equations; fractional system identification method; parameter estimation; real-time identification; recursive algorithm approach; recursive instrumental variable method; recursive least squares method; time-variant fractional systems; Equations; Least squares approximations; Mathematical model; Noise; Numerical models; Vectors; Recursive identification; fractional systems; least squares method;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control Conference (ECC), 2007 European
Conference_Location :
Kos
Print_ISBN :
978-3-9524173-8-6
Type :
conf
Filename :
7068707
Link To Document :
بازگشت