APPLICATION OF A PERTURBATION THEORY FOR EVALUATION ALGORITHMS FOR IDENTIFICATION OF A CONTINUOUS PLANT FROM DISCRETE DATA

Abstract

A perturbation theory for evaluation algorithms of arithmetic expressions is applied to the generalized least-squares identification of the continuous parameters by using nonperiodic discrete data. The sampling instants are distributed in such a way that a sequence of the elemental arithmetic expressions of the identification algorithm are suboptimized according to bang-bang rules on the extrema of appropriate variation intervals. The weighting scalars in the generalized least-squares method are updated with the same purpose.