Improved least squares identification algorithm for multivariable Hammerstein systems

The multivariable Hammerstein output error moving average (OEMA) system consists of parallel nonlinear blocks interconnected with a linear OEMA block. Its identification model, which is not a regression form, contains a sum of some bilinear functions about the parameter vectors of the nonlinear part and the linear part. By using the Taylor expansion on a least squares quadratic criterion function, this paper investigates an improved least squares algorithm to identify the parameters of the multivariable Hammerstein OEMA system. The parameter vector is defined as a unified vector of all parameter vectors in the non-regression model of this system; the information vector is defined as the derivative of the noise variable to the unified parameter vector. Numerical simulations indicate that the proposed algorithm is capable of generating accurate parameter estimates, and easy to implement on-line.