A novel two-stage ellipsoid filtering-based system modeling algorithm for a Hammerstein nonlinear model with an unknown noise term

摘要

This paper considers the system modeling problem for the Hammerstein nonlinear model with unknown but bounded noise. A two-stage ellipsoid filtering-based modeling algorithm is proposed and the unknown noise term is wrapped in an ellipsoid during each recursive step. The normalized ellipsoid is varying and its center, as well as its volume, is updated by using the volume minimization criteria of the ellipsoid. Finally, the given simulations visually illustrate the feasible parameter set variation process and the motion trail of the ellipsoids, which shows the effectiveness and the accuracy of the proposed algorithm.