Abstract
This paper presents a new procedure for outbounding recursively the feasible parameter set of a linear model through parallelotopes. The key feature of the algorithm is the uptdating rule based on a frequency domain optimality criterion. The parameter set estimate is updated by requiring that the feasible frequency response set in the complex plane is “minimar in some sense. The updating law is designed so that among all the estimates with “minimal” frequency response set, the minimal volume estimate in the parameter space is selected. Key words. Recursive identification; parallelotope; parametric uncertainty; set membership identification; linear model.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
