RECURSIVE PREDICTION ERROR IDENTIFICATION USING THE NONLINEAR WIENER MODEL

The nonlinear Wiener model, consisting of a linear dynamic block in ca scade with a static nonlinearity, is considered. A recursive predictio n error identification algorithm, based on the Wiener model, is derive d. The linear dynamic block is modelled as a SISO transfer function op erator, and the static nonlinearity is approximated with a piecewise l inear function. A theoretical analysis of the method is carried out, a nd conditions for local convergence to the true parameter vector are g iven. In particular, the analysis shows that the input signal should b e such that there is signal energy in the whole range of the piecewise linear approximation. A numerical example illustrates the performance of the algorithm further. Practical guidelines on how to apply the al gorithm are also included in the paper.