ALGORITHMS FOR IDENTIFICATION IN H-INFINITY WITH UNEQUALLY SPACED FUNCTION MEASUREMENTS

Worst-case identification in H(infinity) is considered in the situation in which corrupted frequency response measurements are available at an arbitrary set of frequencies. Two new classes of algorithms are presented: one yields polynomial models directly, the other is a two-stage algorithm producing rational models. Each has improved convergence rates for the class of exponentially stable discrete-time systems (with errors typically O(epsilon) + O(DELTA(r)) for arbitrarily large r, where epsilon is the noise level and DELTA is the maximum spacing between identification points). A numerical example is given.