Number of the records: 1
Projection-based Bayesian recursive estimation of ARX model with uniform innovations
- 1.
SYSNO ASEP 0084256 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Ostatní články Title Projection-based Bayesian recursive estimation of ARX model with uniform innovations Title Bayesovské rekurzivní odhadování ARX modelu s rovnoměrně rozloženými inovacemi založené na projekci Author(s) Kárný, Miroslav (UTIA-B) RID, ORCID
Pavelková, Lenka (UTIA-B) RIDSource Title Systems and Control Letters. - : Elsevier - ISSN 0167-6911
Roč. 56, 9/10 (2007), s. 646-655Number of pages 10 s. Language eng - English Country NL - Netherlands Keywords ARX model ; Bayesian recursive estimation ; Uniform distribution Subject RIV BC - Control Systems Theory R&D Projects 1ET100750401 GA AV ČR - Academy of Sciences of the Czech Republic (AV ČR) 2C06001 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) 1F43A/003/120 GA MDS - Ministry of Transport (MD) CEZ AV0Z10750506 - UTIA-B (2005-2011) Annotation Autoregressive model with exogenous inputs (ARX) is a widely-used black-box type model underlying adaptive predictors and controllers. Its innovations, stochastic unobserved stimulus of the model, are white, zero mean with time-invariant variance. Mostly, the innovations are assumed to be normal. It induces least squares as the adequate estimation procedure. Light tails of the normal distribution imply that its unbounded support can often be accepted as a reasonable approximate description of physical quantities, which are mostly bounded. In some case, however, this approximation is too crude or does not fit subsequent processing, for instance, robust control design. Then, techniques similar to those dealing with unknown-but-bounded equation errors are used. They intentionally give up stochastic interpretation of innovations and develop various algorithms of a min-max type. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2008
Number of the records: 1