Dual systems identification methods based on Koopman operator theory

Alexandre Mauroy, Jorge Goncalves

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférenceArticle dans les actes d'une conférence/un colloque

Résumé

We report our recent developments on Koopman operator lifting techniques for system identification and parameter estimation. We present two methods, which are based on the key idea of identifying the Koopman operator in a lifted space of observables, but rely on two different finite-dimensional approximations of the Koopman operator. The first method is a parametric technique which reconstructs the vector field using a dictionary of library functions. The second method can be seen as a dual approach and provides estimates of the vector field at the data points. We compare the performances of these two methods and consider large
dimensional systems. Theoretical convergence results are also provided.
langue originaleAnglais
titreProceedings of the SICE Conference
Pages64-67
Nombre de pages4
étatPublié - sept. 2018

Empreinte digitale

Identification (control systems)
Glossaries
Parameter estimation
Mathematical operators

Citer ceci

Mauroy, A., & Goncalves, J. (2018). Dual systems identification methods based on Koopman operator theory. Dans Proceedings of the SICE Conference (p. 64-67)
Mauroy, Alexandre ; Goncalves, Jorge. / Dual systems identification methods based on Koopman operator theory. Proceedings of the SICE Conference. 2018. p. 64-67
@inproceedings{b4084a67deb141428e0165418a07b0f5,
title = "Dual systems identification methods based on Koopman operator theory",
abstract = "We report our recent developments on Koopman operator lifting techniques for system identification and parameter estimation. We present two methods, which are based on the key idea of identifying the Koopman operator in a lifted space of observables, but rely on two different finite-dimensional approximations of the Koopman operator. The first method is a parametric technique which reconstructs the vector field using a dictionary of library functions. The second method can be seen as a dual approach and provides estimates of the vector field at the data points. We compare the performances of these two methods and consider largedimensional systems. Theoretical convergence results are also provided.",
keywords = "Nonlinear systems identification, parameter estimation, Koopman operator, lifting techniques",
author = "Alexandre Mauroy and Jorge Goncalves",
year = "2018",
month = "9",
language = "English",
pages = "64--67",
booktitle = "Proceedings of the SICE Conference",

}

Mauroy, A & Goncalves, J 2018, Dual systems identification methods based on Koopman operator theory. Dans Proceedings of the SICE Conference. p. 64-67.

Dual systems identification methods based on Koopman operator theory. / Mauroy, Alexandre; Goncalves, Jorge.

Proceedings of the SICE Conference. 2018. p. 64-67.

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférenceArticle dans les actes d'une conférence/un colloque

TY - GEN

T1 - Dual systems identification methods based on Koopman operator theory

AU - Mauroy, Alexandre

AU - Goncalves, Jorge

PY - 2018/9

Y1 - 2018/9

N2 - We report our recent developments on Koopman operator lifting techniques for system identification and parameter estimation. We present two methods, which are based on the key idea of identifying the Koopman operator in a lifted space of observables, but rely on two different finite-dimensional approximations of the Koopman operator. The first method is a parametric technique which reconstructs the vector field using a dictionary of library functions. The second method can be seen as a dual approach and provides estimates of the vector field at the data points. We compare the performances of these two methods and consider largedimensional systems. Theoretical convergence results are also provided.

AB - We report our recent developments on Koopman operator lifting techniques for system identification and parameter estimation. We present two methods, which are based on the key idea of identifying the Koopman operator in a lifted space of observables, but rely on two different finite-dimensional approximations of the Koopman operator. The first method is a parametric technique which reconstructs the vector field using a dictionary of library functions. The second method can be seen as a dual approach and provides estimates of the vector field at the data points. We compare the performances of these two methods and consider largedimensional systems. Theoretical convergence results are also provided.

KW - Nonlinear systems identification

KW - parameter estimation

KW - Koopman operator

KW - lifting techniques

M3 - Conference contribution

SP - 64

EP - 67

BT - Proceedings of the SICE Conference

ER -

Mauroy A, Goncalves J. Dual systems identification methods based on Koopman operator theory. Dans Proceedings of the SICE Conference. 2018. p. 64-67