HAL : hal-00514429, version 2

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

49th IEEE Conference on Decision and Control, CDC 2010, Atlanta, GA : États-Unis (2010)

Versions disponibles :

v1 (02-09-2010)

v2 (16-09-2010)

Nonlinear Hybrid System Identification with Kernel Models

Fabien Lauer 1, Gérard Bloch 2, René Vidal 3

(15/12/2010)

This paper focuses on the identification of nonlinear hybrid systems involving unknown nonlinear dynamics. The proposed method extends the framework of [1] by introducing nonparametric models based on kernel functions in order to estimate arbitrary nonlinearities without prior knowledge. In comparison to the previous work of [2], which also dealt with unknown nonlinearities, the new algorithm assumes the form of an unconstrained nonlinear continuous optimization problem, which can be efficiently solved for moderate numbers of parameters in the model, as is typically the case for linear hybrid systems. However, to maintain the efficiency of the method on large data sets with nonlinear kernel models, a preprocessing step is required in order to fix the model size and limit the number of optimization variables. A support vector selection procedure, based on a maximum entropy criterion, is proposed to perform this step. The efficiency of the resulting algorithm is demonstrated on large-scale experiments involving the identification of nonlinear switched dynamical systems.

1 :	ABC (Apprentissage et Biologie Computationnelle) (LORIA)
	CNRS : UMR7503 – INRIA – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine
2 :	Centre de recherche en automatique de Nancy (CRAN)
	CNRS : UMR7039 – Université Henri Poincaré - Nancy I – Institut National Polytechnique de Lorraine (INPL)
3 :	Center for Imaging Science (CIS)
	Johns Hopkins University

Équipe de recherche : ACOS;ABC

Domaine

:

Sciences de l'ingénieur/Automatique / Robotique Informatique/Automatique Informatique/Apprentissage Informatique/Modélisation et simulation Informatique/Réseau de neurones Statistiques/Autres

Mots Clés : Nonlinear Hybrid System Identification – Kernel Models – continuous optimization – large data sets – support vector selection – fixed-size Least Squares SVM (LS-SVM)

hal-00514429, version 2

http://hal.archives-ouvertes.fr/hal-00514429

oai:hal.archives-ouvertes.fr:hal-00514429

Contributeur : Gérard Bloch <>

Soumis le : Jeudi 16 Septembre 2010, 12:54:17

Dernière modification le : Mardi 31 Mai 2011, 16:47:33