A new technique for identification of MISO Hammerstein model

Abstract

A recursive method for identfication of nonlinear multi-input single-output Hammerstein model is presented This is developed along the lines of the basic Kalman filter and has the advantage to esimate recursively parameters of each submodel of the nonlinear system without transformation, which is obtained by the use of a new formulation of the input output difference equation. Parameters number to be estimated is minimal and then computational requirements are considerbly reduced. Efficiency of this algorithm is shown by mean of a numerical example.