Two algorithms for the combined state and parameter estimation (CSPE) of a linear, time-invariant system are presented. Retrospective cost subsystem estimation is formulated under the assumption that the initial state is known. A smoother algorithm based on this formulation is developed for the case in which the initial state is unknown. It is numerically demonstrated that these algorithms are more accurate for CSPE than the extended Kalman filter and the unscented Kalman filter.
Retrospective Cost Subsystem Estimation and Smoothing for Linear Systems with Structured Uncertainty
Journal of Aerospace Information Systems ; 15 , 10 ; 566-584
2018-09-06
19 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Retrospective-Cost Subsystem Identification for the Global Ionosphere-Thermosphere Model
British Library Conference Proceedings | 2012
|Eigenstructure Perturbation in Disjointed Domains for Linear Systems with Structured Uncertainty
British Library Conference Proceedings | 1994
|Robust non-linear smoothing for vehicle state estimation
IEEE | 2013
|