Identification of Parallel Wiener-Hammerstein Systems

This paper is focused on the problem of system identification for a class of nonlinear systems constituted of a Wiener subsystem and Hammerstein subsystem connected in parallel. Most of existing works on the identification of compound systems, involving Wiener and Hammerstein subsystems, have been focused on series connections. Presently, we present a frequency identification approach to determine estimates of the different components of the considered parallel Wiener-Hammerstein system. The approach comes in two versions. The first one consists in using repeatedly a one-frequency sine input experiment, with different frequencies in the various experiments. The second version consists in performing a signal experiment involving a sufficiently rich multi-sine excitation. The applicability of the approach and its relevance are highlighted by simulation. Copyright (C) 2022 The Authors.