An asymptotic unbiased recursive identifier for linear systems

The model reference adaptive system approach together with the positive real lemma for time varying discrete systems are used to construct a recursive identifier with a parallel adjustable model, using an adaptation algorithm having a decreasing gain. The identifier assures an asymptotic unbiased parameter estimation in the presence of noise obscured measurements. Experimental results obtained from simulated data and from the identification of a paper machine are presented. The comparison with the performances of other identification methods is discussed.