Skip navigation
Please use this identifier to cite or link to this item:

Title: Nonlinear system identification using constellation based multiple model adaptive estimators
Authors: Martins, João Carlos
Caeiro, José Jasnau
Sousa, Leonel Augusto
Keywords: Dynamic systems identification: suboptimal state estimation
Multiple model adaptive estimator
Parameter estimation
Extended Kalman filter
Unscented Kalman filter
Issue Date: Nov-2014
Publisher: IEEE
Citation: [IEEE style] J. C. Martins, J. J. Caeiro, L. A. Sousa, “ Nonlinear system identification using constellation based multiple model adaptive estimators,“ in European Signal Processing Conference, 2014, pp. 1217- 1221.
Abstract: This paper describes the application of the constellation based multiple model adaptive estimation (CBMMAE) algorithm to the identification and parameter estimation of nonlinear systems. The method was successfully applied to the identification of linear systems both stationary and nonstationary, being able to fine tune its parameters. The method starts by establishing a minimum set of models that are geometrically arranged in the space spanned by the unknown parameters, and adopts a strategy to adaptively update the constellation models in the parameter space in order to find the model resembling the system under identification. By downscaling the models parameters the constellation is shrunk, reducing the uncertainty of the parameters estimation. Simulations are presented to exhibit the application of the framework and the performance of the algorithm to the identification and parameters estimation of nonlinear systems.
Description: 22nd European Signal Processing Conference, Lisbon: Set 1-5, 2014
Peer reviewed: yes
ISBN: 978-099286261-9
Appears in Collections:D-ENG - Comunicações com peer review

Files in This Item:
File Description SizeFormat 
NONLINEAR SYSTEM.pdf303.12 kBAdobe PDFView/Open

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Currículo DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.