Set Membership (SM) H-infinity identification of mixed parametric and non-p
arametric models is investigated, aimed to estimate a low-order approximati
ng model and an identification error, giving a measure of the unmodelled dy
namics in a form well suited for H-infinity control methodologies. In parti
cular, the problem of estimating the parameters of the parametric part and
the H-infinity bound on the modelling error is solved using frequency domai
n data, supposing l(infinity) bounded measurement errors and that the syste
m to be identified is exponentially stable. The effectiveness of the propos
ed procedure is tested on some numerical examples, showing the advantages o
f the proposed methods over the existing non-parametric H-infinity identifi
cation approaches, in terms of lower model order and of tightness in the mo
delling error bounds. Copyright (C) 1999 John Wiley & Sons, Ltd.