System identification by operatorial cancellation of nonlinear terms and application to a class of Volterra models - INRAE - Institut national de recherche pour l’agriculture, l’alimentation et l’environnement
Journal Articles International Journal of Robust and Nonlinear Control Year : 2017

System identification by operatorial cancellation of nonlinear terms and application to a class of Volterra models

Abstract

In this paper, a method is proposed for the identification of some SISO nonlinear models with two ill-known components of different nature: a linear (possibly dynamic) part and a static nonlinear one. This method is well adapted when no a priori information is available about the nonlinear component to be identified. It is based on a difference operator, which enables to cancel the nonlinear term when applied to the model. Only the ill-known linear part remains in the transformed model; it can therefore be identified independently of the nonlinear term. Based on the identified linear component, we have access to a pseudograph of the nonlinear term, whose shape can give precious information for the parameterization of the unknown nonlinear part and its identification. The identification model under consideration is defined in an abstract framework, with very weak hypotheses, so that the proposed approach has a large scope. To highlight the method, a class of dynamic Volterra models including some hybrid models such as dynamic inclusions is considered for application.
Fichier principal
Vignette du fichier
IJRNC_2016.pdf (1.36 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01606015 , version 1 (23-10-2018)

Identifiers

Cite

Céline Casenave, Emmanuel Montseny, Gérard Montseny. System identification by operatorial cancellation of nonlinear terms and application to a class of Volterra models. International Journal of Robust and Nonlinear Control, 2017, 27 (8), pp.1211-1241. ⟨10.1002/rnc.3622⟩. ⟨hal-01606015⟩
155 View
117 Download

Altmetric

Share

More