Worst-case parameter estimation with bounded model uncertainties
- 1 January 1997
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 171-175 vol.1
- https://doi.org/10.1109/acc.1997.611779
Abstract
We formulate and solve a new parameter estimationproblem in the presence of bounded model uncertainties.The new method is suitable when a-priori bounds on theuncertain data are available, and its solution guaranteesthat the effect of the uncertainties will never be unnecessarilyover-estimated beyond what is reasonably assumedby the a-priori bounds. This is in contrast to other methods,such as total least-squares and robust estimation,that do not incorporate explicit bounds on the size...Keywords
This publication has 5 references indexed in Scilit:
- Parameter Estimation in the Presence of Bounded Data UncertaintiesSIAM Journal on Matrix Analysis and Applications, 1998
- Best-fit parameter estimation for a bounded errors-in-variables modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- A fast iterative solution for worst-case parameter estimation with bounded model uncertaintiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Linear estimation in Krein spaces. I. TheoryIEEE Transactions on Automatic Control, 1996
- The Total Least Squares ProblemPublished by Society for Industrial & Applied Mathematics (SIAM) ,1991