Two Iterative Learning Identification Algorithms for Discrete Time-Varying Systems

This paper presents iterative learning identification for estimating time-varying parameters of a class of discrete time-varying systems over finite intervals. Two prototype algorithms of iterative learning identification; iterative learning Bayes and stochastic Newton algorithms, are proposed with detail. Different from the bounded convergence performance obtained by conventional tracking algorithms, complete estimation for the time-varying unknowns is achieved through iterative learning, and the parameter estimation error converges to zero over the entire time interval. Numerical simulation results demonstrate the proposed learning algorithms' validity and efficiency.