An adaptive algorithm for hammerstein filter system identification

This paper develops an affine projection-based variable stepsize adaptive algorithm for updating the coefficients of a Hammerstein nonlinear system. The variable step-size adaptive Hammerstein algorithm, recursively updates the stepsize using a new criterion that provides a measure of how close the Hammerstein filter is to optimum performance. Experimental results show that the algorithm converges to the true unknown system in the mean square sense. Results also show the superior convergence of our proposed algorithm in comparison to existing adaptive Hammerstein algorithms.