Title :
Refined instrumental variable methods for identification of Hammerstein continuous-time Box-Jenkins models
Author :
Laurain, V. ; Gilson, M. ; Garnier, H. ; Young, P.C.
Author_Institution :
Centre de Rech. en Autom. de Nancy, CNRS, Vandoeuvre-les-Nancy, France
Abstract :
This article presents instrumental variable methods for direct continuous-time estimation of a Hammerstein model. The non-linear function is a sum of known basis functions and the linear part is a Box-Jenkins model. Although the presented algorithm is not statistically optimal, this paper further shows the performance of the presented algorithms and the advantages of continuous-time estimation on relevant simulations.
Keywords :
continuous time systems; identification; nonlinear functions; Hammerstein continuous-time Box-Jenkins model identification; direct continuous-time estimation; nonlinear function; nonlinear identification; refined instrumental variable methods; Design methodology; Environmental management; Instruments; Least squares approximation; Linear systems; Neural networks; Piecewise linear techniques; Predictive models; Support vector machine classification; Transfer functions;
Conference_Titel :
Decision and Control, 2008. CDC 2008. 47th IEEE Conference on
Conference_Location :
Cancun
Print_ISBN :
978-1-4244-3123-6
Electronic_ISBN :
0191-2216
DOI :
10.1109/CDC.2008.4738853
