Recovering Wiener-Hammerstein nonlinear state-space models using linear algebra

This paper considers Wiener-Hammerstein systems consisting of a cascade of a linear dynamical system, a static nonlinearity and another linear dynamical system. We start from a black-box nonliitear state-space description of the system and develop a method to reconstruct, the parameters of the underlying Wiener-Hammerstein block structure by means of linear algebra operations. First, the static nonlinearity is retrieved by decoupling the nonlinear part of the state-space equations into a single-branch nonlinear function. Front there on, a canonical Wiener-Hammerstein nonlinear state-space model is recovered by using linear algebraic and geometric tools. The method is validated on a simulation example. (C) 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.