© 1996 by Institute of Mathematics and its Applications
On-line H2, H
, and pointwise uncertainty-bound quantification in identification of restricted-complexity models
Department of Electrical and Computer Engineering, University of Iowa Iowa City, IA 52242
This paper considers the problem of on-line uncertainty-bound quantification in identification of restricted complexity models. Algorithms are presented which provide hard and tight upper bound on the unknown model uncertainty in H2, H
, and pointwise sense respectively. The algorithms proposed are very simple, on-line, and recursive. This allows robust control and adaptive identification to be combined.