Estimation of an N-L-N Hammerstein-Wiener model

Y. Zhu

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

140 Citaten (Scopus)
2 Downloads (Pure)

Samenvatting

Estimation of a single-input single-output block-oriented model is studied. The model consists of a linear block embedded between two static nonlinear gains. Hence, it is called N-L-N Hammerstein-Wiener model. First, the model structure is motivated and the disturbance model is discussed. The paper then concentrates on parameter estimation. A relaxation iteration scheme is proposed by making use of a model structure in which the error is bilinear-in-parameters. This leads to a simple algorithm which minimizes the original loss function. The convergence and consistency of the algorithm are studied. In order to reduce the variance error, the obtained linear model is further reduced using frequency weighted model reduction. Simulation study will be used to illustrate the method. © 2002 Elsevier Science Ltd. All rights reserved.
Originele taal-2Engels
Pagina's (van-tot)1607-1614
Aantal pagina's8
TijdschriftAutomatica
Volume38
Nummer van het tijdschrift9
DOI's
StatusGepubliceerd - 2002

Vingerafdruk Duik in de onderzoeksthema's van 'Estimation of an N-L-N Hammerstein-Wiener model'. Samen vormen ze een unieke vingerafdruk.

Citeer dit