An extended identification methods for multivariable Hammerstein system

Hammerstein typed nonlinear models can be used to represent nonlinear systems in the areas of chemical and biological processes, signal processing, etc. This work proposes two methods of parametric identification of multivariable Hammerstein model. The first method is an extended of the Hammerstein model in the mutivariable case. Each output of the system is a summation of partial outputs. Each of them shows the response of sub-Hammerstein model. In the second method, each output multivariable system corresponds to a linear model, which at its input are introduced nonlinear function. The system identification process uses the available inputs and outputs, with the recursive least squares algorithm (RLS). These methods are tested and illustrated on a quadruple-tank process.