Hammerstein Model Identification Using Particle Swarm Optimization

Mihai Cornoiu (1) , Dominique Beauvois (2)

1 UPB - University Politehnica of Bucharest [Romania]
2 E3S - Supélec Sciences des Systèmes

This paper aims to describe an identification method for Hammerstein systems. The concept of Automatic Choosing Function is used to approximate the nonlinear static component. The specific coefficients of the ACF and also the parameters of the linear dynamic component are estimated using linear least squares. Particle Swarm Optimization is used for selecting the widths of the subdomains and the shape of ACF. The method is validated by numerical experiments.

Domaines: Automatique / Robotique

Mihai Cornoiu, Dominique Beauvois. Hammerstein Model Identification Using Particle Swarm Optimization. 14th IFAC Symposium on Information Control Problems in Manufacturing, May 2012, Bucharest, Romania. pp.1727-1732, ⟨10.3182/20120523-3-RO-2023.00400⟩. ⟨hal-00754936⟩