Skip to Main content Skip to Navigation

Contribution à l'estimation ensembliste des systèmes linéaires et non-linéaires

Abstract : The aim of this thesis is the design of ellipsoidal approximation techniques for the set-membership identification and state estimation of linear and nonlinear multivariable systems. Firstly, a recursive solution for the identification of linear models has been proposed. The use of a judicious parametrization allows to characterize the ellipsoid that bounds the set of all the possible values of the unknown parameters and to ensure consistency of the estimated parameters with the data and respecting the boundedness constraints. A generalization to the nonlinear case has been done by linearizing the nonlinear model around the vector of the estimated parameters and by taking into account the linearization errors. Next, a state estimation method for linear and nonlinear systems with bounded noises is presented. A prediction step takes into account the dynamical behavior of the model corrupted by the noises while the correction step includes the information contained in the noisy outputs.
Document type :
File URL :
Complete list of metadata
Contributor : Thèses Ul Connect in order to contact the contributor
Submitted on : Thursday, March 29, 2018 - 10:45:19 AM
Last modification on : Saturday, October 16, 2021 - 11:14:14 AM


  • HAL Id : tel-01746812, version 1



Yasmina Becis-Aubry. Contribution à l'estimation ensembliste des systèmes linéaires et non-linéaires. Autre. Université Henri Poincaré - Nancy 1, 2003. Français. ⟨NNT : 2003NAN10190⟩. ⟨tel-01746812⟩



Record views