Recovering Wiener-Hammerstein nonlinear state-space models using linear algebra*. Issue 28 (2015)

• Record Type: Journal Article
• Authors: Dreesen, Philippe; Ishteva, Mariya; Schoukens, Johan
• Is Part Of: IFAC-PapersOnLine. Volume 48:Issue 28(2015)
• Page Start: 951
• Page End: 956
• Publication Date: 2015
• Subjects: block-oriented system identification -- nonlinear system identification -- state-space models -- Wiener-Hammerstein systems; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2015.12.253
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: 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 nonlinear 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. From 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.