On the Performance of the Recursive Least Squares Method in the Presence of Bounded Disturbances
1991 (English)In: Proceedings of the 30th IEEE Conference on Decision and Control, 1991, Vol. 1, 762-763 vol.1 p.Conference paper (Refereed)
The author considers the performance of the recursive least squares method when applied to problems where the measured signal is corrupted by noise, which is bounded but otherwise of unknown characteristics. An asymptotic expression for the bound on the parameter estimation error is derived using ideas from bounding ellipsoid algorithms.
Place, publisher, year, edition, pages
1991. Vol. 1, 762-763 vol.1 p.
Recursive identifcation, Uncertainty bounds, Recursive least squares, Asymptotic properties, Bounding ellipsoid, Parameter estimation, Signal processing
IdentifiersURN: urn:nbn:se:liu:diva-94073DOI: 10.1109/CDC.1991.261414ISBN: 0-7803-0450-0OAI: oai:DiVA.org:liu-94073DiVA: diva2:629993
30th IEEE Conference on Decision and Control, Brighton, United Kingdom, December, 1991