Year: 2017
Type: article
Abstract: A simple non‐linear system modelling algorithm designed to work with limited a priori knowledge and short data records, is examined. It creates an empirical Volterra series‐based model of a system using an ‐constrained least squares algorithm with . If the system is a continuous and bounded map with a finite memory no longer than some known , then (for a D parameter model and for a number of measurements N ) the difference between the resulting model of the system and the best possible theoretical one is guaranteed to be of order , even for . The performance of models obtained for and 2 is tested on the Wiener–Hammerstein benchmark system. The results suggest that the models obtained for are better suited to characterise the nature of the system, while the sparse solutions obtained for yield smaller error values in terms of input‐output behaviour.
Authors: Przemysław Śliwiński, Anna Marconato, Paweł Wachel, Georgios Birpoutsoukis
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2624804269