A BLIND APPROACH TO THE HAMMERSTEIN–WIENER MODEL IDENTIFICATION.pdfVIP

Automatica 38 (2002) 967–979 /locate/automatica A blind approach to the Hammerstein–Wiener model identication Er-Wei Bai ∗ Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA 52242, USA Received 6 March 2001; received in revised form 6 August 2001; accepted 30 November 2001 Abstract In this paper, we propose a blind approach to the sampled Hammerstein–Wiener model identication. By using the blind approach, it is shown that all internal variables can be recovered solely based on the output measurements. Then, identication of linear and nonlinear parts can be carried out. No a priori structural knowledge about the input nonlinearity is assumed and no white noise assumption is imposed on the input. ? 2002 Elsevier Science Ltd. All rights reserved. Keywords System identication; Parameter estimation; Nonlinear systems; Hammerstein systems; Wiener systems; Hammerstein–Wiener systems 1. Introduction output nonlinearity for identication purpose. Unlike in the Hammerstein model case, the commonly used polynomial The Hammerstein and Wiener models are special kinds representation for the output nonlinearities makes identi- of nonlinear systems where the nonlinear block is static and cation in terms of unknown parameters very hard. The follows or is followed by a linear system. These models main technique used for Wiener model identication is have applications in many engineering