Identification of Hammerstein model using radial basis function networks and genetic algorithm

This paper deals with an identification method of Hammerstein model by using radial basis function (RBF) networks and genetic algorithm (GA). An unknown nonlinear static part to be estimated is approximately represented by an RBF network. The weighting parameters of the RBF network and the system parameters of the linear dynamic part are estimated by the linear least-squares method. The adjusting parameters for the RBF network structure, i.e. the number, centers and widths of the RBF are properly determined by using the GA, in which the Akaike information criterion (AIC) is utilized as the fitness value function. Simulation results are shown to illustrate the proposed method.