Parameter Estimation of Parallel Wiener-Hammerstein Systems by Decoupling their Volterra Representations

Abstract Nonlinear dynamic systems are often approximated by a Volterra series, which is generalization of the Taylor series for with memory. However, lacks physical interpretation. To take advantage representation while aiming an interpretable block-oriented model, we establish link between and parallel Wiener-Hammerstein based on decoupling multivariate polynomials. The true through constrained model (block-)Toeplitz structure factors sets identical internal branches. solution modified problem then reveals directly parameters system. due to uniqueness properies plain algorithm, even if not imposed, method still leads (in exact case).