Identification of Parallel-Cascade Wiener System using Tensor Decomposition of an associated Volterra kernel

Abstract

In this paper, we propose tensorbased methods for identifying nonlinear Parallel- Cascade Wiener (PCW) systems. Parameters of linear subsystems are first estimated using an approach based on the PARAFAC decomposition of the associated pth-order Volterra kernel. This approach consists in applying the Alternating Least Squares (ALS) algorithm. Then the coefficients of nonlinear subsystems approximated as polynomials are estimated by mean the least square sense from the reconstructed output of the linear subsystems. The proposed parameter estimation method and its performance are illustrated by means of simulation results.