Parameter bounds for discrete-time Hammerstein models with bounded output errors

Author

Cerone, V. ; Regruto, D.

Author_Institution

Dipt. di Autom.a e Informatica, Torino, Italy

Volume

48

Issue

10

fYear

2003

Firstpage

1855

Lastpage

1860

Abstract

In this note, we present a two-stage procedure for deriving parameters bounds in Hammerstein models when the output measurement errors are bounded. First, using steady-state input-output data, parameters of the nonlinear part are tightly bounded. Then, for a given input transient sequence we evaluate tight bounds on the unmeasurable inner signal which, together with noisy output measurements are used for bounding the parameters of the linear dynamic block.

Keywords

discrete time systems; measurement errors; nonlinear systems; parameter estimation; bounded output errors; discrete-time Hammerstein models; linear dynamic block parameter bounds; noisy output measurements; nonlinear part parameters; output measurement errors; parameter bounds; steady-state I/O data; steady-state input-output data; tight bounds; transient sequence; unmeasurable inner signal; Gain; Linear programming; Measurement errors; Nonlinear dynamical systems; Nonlinear systems; Output feedback; Parameter estimation; Signal processing; Steady-state; White noise;

fLanguage

English

Journal_Title

Automatic Control, IEEE Transactions on

Publisher

ieee

ISSN

0018-9286

Type

jour

DOI

10.1109/TAC.2003.817945

Filename

1235396