A bayesian approach to closed-loop system identification
| Authors: | Thil Stéphane, Université Henri Poincaré, Nancy 1, France
Gilson Marion, Université Henri Poincaré, Nancy 1, France |
|---|
| Topic: | 1.1 Modelling, Identification & Signal Processing |
|---|
| Session: | Interplay between Identification and Control |
|---|
| Keywords: | Closed-loop identification, Bayesian technique, MCMC methods, non-informative data records. |
|---|
Abstract
The challenging issue of identifying a closed-loop system from shortand/or non-informative data records is addressed. A bayesian approach is developed withinthis framework. It is shown that accurate estimates and realistic confidence intervalscan be obtained by taking into account prior knowledge on the system. The performances ofthe proposed method are illustrated with a simulation example.
