ADAPTIVE IDENTIFICATION OF CONTINUOUS-TIME SYSTEMS IN THE PRESENCE OFNOISE

In this paper a new adaptive scheme is proposed to identify SISO linea r systems. The algorithm has its origin in the stochastic approximatio n method well-known in statistics and it differs from a widely studied adaptive identifier only by a time-varying gain term. We show that th is simple modification makes the algorithm robust to the presence of n oise in the estimation process, using methods that emphasize the conne ction with the standard stability analysis used in the deterministic t heory of adaptive systems. The robustness properties are then demonstr ated in a number of simulation studies.