H/sub /spl infin// identification of "soft" uncertainty models

The paper investigates the problem of identifying uncertainty models of SISO, LTI, discrete-time, BIBO stable, unknown systems, using frequency domain measurements corrupted by Gaussian noise of known covariance. An additive uncertainty model is looked for, consisting of a nominal model and an addit...

Full description

Saved in:
Bibliographic Details
Published inProceedings of 35th IEEE Conference on Decision and Control Vol. 3; pp. 2418 - 2423 vol.3
Main Authors Milanese, M., Taragna, M.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1996
Subjects
Estimation error
Frequency domain analysis
Frequency estimation
Frequency measurement
Frequency response
Gaussian noise
Noise measurement
Parameter estimation
Transfer functions
Upper bound
Online AccessGet full text
ISBN9780780335905
0780335902
ISSN0191-2216
DOI10.1109/CDC.1996.573451

Cover

More Information
Summary:The paper investigates the problem of identifying uncertainty models of SISO, LTI, discrete-time, BIBO stable, unknown systems, using frequency domain measurements corrupted by Gaussian noise of known covariance. An additive uncertainty model is looked for, consisting of a nominal model and an additive dynamic perturbation accounting for the modeling errors. The nominal model is chosen within a class of linearly parametrized models with transfer function of given (possibly low) order. An estimate of the parameters minimizing the H/sub /spl infin// modeling error is obtained by minimizing an upper bound of the worst case (with respect to modeling error) second moment of the estimation error. Then, a bound in the frequency domain guaranteeing to include, with probability /spl alpha/, the frequency response error between the estimated nominal model and the unknown system is derived.
ISBN:9780780335905
0780335902
ISSN:0191-2216
DOI:10.1109/CDC.1996.573451