Web projektu DAR

Research Centre
Data - Algorithms - Decision Making

Established in 2005 under support of MŠMT ČR (project 1M0572)

Publications

Design of derivative-free smoothers and predictors

Typ:

Conference paper

Authors:

Šimandl M., Duník J.

Proceedings name:

Preprints of the 14th IFAC Symposium on System Identification

Serie:

Newcastle, Australia

Year:

2006

Pages:

1240-1245

Contact:

Ing. Jindřich Duník, Ph.D. (FAV Západočeská univerzita, katedra kybernetiky)

Keywords:

stochastic systems, nonlinear systems, state estimation

URL (www page):

http://sysid2006.org/

attachment1:

clanek_SYSID06_JD.pdf [file]

attachment2:

prezentace_SYSID06_JD.pdf [file]

Anotation:

Local state estimation approaches for nonlinear stochastic systems are treated. The unscented transformation and the Stirling’s polynomial interpolation, used in the design of the derivative-free Kalman filters, are briefly discussed. These approximation techniques are exploited to the design of the derivative-free smoothers and predictors. Some aspects of the different types of the derivative-free smoothers are analysed. The estimation qualities of the proposed estimators are illustrated in a numerical example.