Filtering based multi-innovation extended stochastic gradient algorithm for Hammerstein nonlinear system modeling

This paper considers parameter estimation problems of Hammerstein finite impulse response moving average (FIR-MA) systems. In order to provide highly accurate parameter estimates and improve the convergence rate, a data filtering based multi-innovation extended stochastic gradient algorithm is presented to estimate the parameters of Hemmerstein FIR-MA systems by using the current innovation and past innovations. The simulation results show that the proposed algorithm can effectively estimate the parameters of the Hammerstein FIR-MA systems.