ROBUST INPUT DESIGN USING SUM OF SQUARES CONSTRAINTS

Abstract

The objective of this paper is to illustrate how recent advances in convex programming can be used in input design in system identification. It is shown that sum of squares techniques and a recent generalization of the KYP lemma can be used to transform input design problems with frequency dependent bounds on the frequency function to convex optimization problems. Another important problem that can be handled with sum of squares is robust input design where initial uncertainty in the true parameters is accounted for.