CINECA IRIS Institutional Research Information System
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishThis paper presents a discrete-time sliding mode control based on neural networks designed for robotic manipulators. Radial basis function neural networks are used to learn about uncertainties affecting the system. The on-line learning algorithm combines the growing criterion and the pruning strategy of the minimal resource allocating network technique with an adaptive extended Kalman filter to update all the parameters of the networks. A method to improve the run-time performance for the real-time implementation of the learning algorithm has been considered. The analysis of the control stability is given and the controller is evaluated on the ERICC robot arm. Experiments show that the proposed controller produces good trajectory tracking performance and it is robust in the presence of model inaccuracies, disturbances and payload perturbations.
| Autori: | |
| Autori: | Corradini, Maria Letizia; Fossi, Valentino; Giantomassi, Andrea; Ippoliti, Gianluca; Longhi, Sauro; Orlando, Giuseppe |
| Titolo: | Minimal resource allocating networks for discrete time sliding mode control of robotic manipulators |
| Numero degli autori: | 6 |
| Data di pubblicazione: | 2012 |
| Rivista: | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS |
| IF: | si |
| Codice identificativo ISI: | WOS:000310388400002 |
| Codice identificativo Scopus: | 2-s2.0-84867959493 |
| Revisione (peer review): | Esperti anonimi |
| Lingua: | Inglese |
| Rilevanza: | Internazionale |
| Volume: | 8 |
| Fascicolo: | 4 |
| Pagina iniziale: | 733 |
| Pagina finale: | 745 |
| Numero di pagine: | 13 |
| Digital Object Identifier (DOI): | http://dx.doi.org/10.1109/TII.2012.2205395 |
| Abstract: | This paper presents a discrete-time sliding mode control based on neural networks designed for robotic manipulators. Radial basis function neural networks are used to learn about uncertainties affecting the system. The on-line learning algorithm combines the growing criterion and the pruning strategy of the minimal resource allocating network technique with an adaptive extended Kalman filter to update all the parameters of the networks. A method to improve the run-time performance for the real-time implementation of the learning algorithm has been considered. The analysis of the control stability is given and the controller is evaluated on the ERICC robot arm. Experiments show that the proposed controller produces good trajectory tracking performance and it is robust in the presence of model inaccuracies, disturbances and payload perturbations. |
| Parole Chiave: | Adaptive filters, discrete-time sliding mode control, minimal resource allocating networks, nonlinear systems, radial basis function networks, robotic manipulators, robust control |
| URL: | http://ieeexplore.ieee.org/document/6221995/ |
| Data di presentazione: | 2016-09-16T20:10:42Z |
| Appare nelle tipologie: | 1.1 Articolo in rivista |
File in questo prodotto:
http://hdl.handle.net/11566/74820
Copyright © 2021