Convergence properties of an iterative prediction approach to nonlinear SEM parameter estimation

This work extends to the nonlinear framework some previous results concerning the convergence of simulation error minimization (SEM) methods for parameter estimation based on an iterative predictor estimation with increasing prediction horizon. Conditions for the applicability of the approach to various model classes, including bilinear, Hammerstein, Wiener and LPV models, are also discussed. The effectiveness of the iterative predictor estimation approach is then shown by means of a simulation example.