Constant Parameter Identification: An Accelerated Heavy-Ball-based Approach
Résumé
This paper contributes to designing a parameter identification algorithm for linear regression systems with constant unknown parameters. The proposed algorithm is based on an accelerated version of the heavy-ball method and uses a nonlinear version of Kreisselmeier's regressor extension. Moreover, it can identify constant parameters in a finite time under a persistent excitation condition. The local stability analysis is developed using a Lyapunov function approach. The applicability and effectiveness of the proposed parameter identification algorithm are illustrated through simulation results.
Domaines
AutomatiqueOrigine | Fichiers produits par l'(les) auteur(s) |
---|