Levenberg-Marquardt iterative algorithm for Hammerstein nonlinear systems

In this paper, we study the identification problem of Hammerstein nonlinear systems. A Levenberg-Marquardt iterative (LMI) algorithm is developed for Hammerstein nonlinear systems. The basic idea is to establish a Hammerstein nonlinear model by means of the key-term separation principle and then derive the LMI algorithm by replacing the unmeasurable variables in the information vector with their corresponding iterative estimates for the proposed model. Finally, the simulation results show the effectiveness of the LMI algorithm.