SUMMARY

The paper deals with recovering non-linearities in the Hammerstein systems by using multiresolution approximation- a basic concept of wavelet theory. The systems are driven by random signals and are disturbed by additive, white or coloured, random noise. The a priori information about system components is non-parametric and a delay in the dynamical part of systems is admitted. A non-parametric identification algorithm for estimating non-linear characteristics of static parts is proposed and investigated. The algorithm is based on the Haar multiresolution approximation. The pointwise convergence and pointwise asymptotic rate of convergence of the algorithm are established. It is shown that neither the form nor the convergence conditions of the algorithm need any modification for the noise being not white but correlated. Also the asymptotic rate of convergence is the same for white and coloured noise. The theoretical results are confirmed by computer simulations. KEY WORDS: Hammerstein system; non-linearity recovering; non-parametric identification; multiresolution approximatio