Parameter identification of a class of discrete time bilinear stochastic models

The main objective of the paper is to present a practical solution to the problem of parameter identification of discrete time bilinear stochastic models whose output is assumed to be corrupted by white Gaussian noise. Due to the fundamental properties of Walsh functions operational matrices, the identification problem can be handled as a simple reducible solution of a set of linear algebraic equations. Computational examples are presented to illustrate the applicability of the proposed method. The simulation results are accurate and convenient