An offset-free neural controller based on a non-extrapolating scheme for approximating the inverse process dynamics

dc.contributor.author	Αλεξανδρίδης, Αλέξανδρος	el
dc.contributor.author	Στογιάννος, Μάριος	el
dc.contributor.author	Κυρίου, Αλεξάνδρα	el
dc.contributor.author	Σαρίμβεης, Χαράλαμπος	el
dc.date.accessioned	2015-05-20T20:27:44Z
dc.date.available	2015-05-20T20:27:44Z
dc.date.issued	2015-05-20
dc.identifier.uri	http://hdl.handle.net/11400/10804
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.source	http://www.sciencedirect.com/science/article/pii/S0959152413001078#	el
dc.subject	Intelligent control systems
dc.subject	Neural networks
dc.subject	Radial basis functions
dc.subject	Ευφυή συστήματα ελέγχου
dc.subject	Neuro-control
dc.subject	Νευρωνικά ελέγχου
dc.subject	Νευρωνικά δίκτυα
dc.subject	Inverse dynamics
dc.subject	Αντίστροφη δυναμική
dc.subject	Βάσης ακτινικών συναρτήσεων
dc.subject	Offset-free control
dc.subject	Offset χωρίς έλεγχο
dc.title	An offset-free neural controller based on a non-extrapolating scheme for approximating the inverse process dynamics	en
heal.type	journalArticle
heal.classification	Technology
heal.classification	Electrical engineering
heal.classification	Τεχνολογία
heal.classification	Ηλεκτρολογία Μηχανολογία
heal.classificationURI	http://zbw.eu/stw/descriptor/10470-6
heal.classificationURI	http://skos.um.es/unescothes/C01311
heal.classificationURI	N/A-Τεχνολογία
heal.classificationURI	N/A-Ηλεκτρολογία Μηχανολογία
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh88003681
heal.keywordURI	http://zbw.eu/stw/descriptor/19808-6
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh2002004691
heal.identifier.secondary	doi:10.1016/j.jprocont.2013.04.008
heal.language	en
heal.access	campus
heal.publicationDate	2013-08
heal.bibliographicCitation	Alexandridis, A., Stogiannos, M., Kyriou, A. and Sarimveis, H. (2013). An offset-free neural controller based on a non-extrapolating scheme for approximating the inverse process dynamics. "Journal of Process Control", 23(7), August 2013. pp. 968–979. Available from: http://www.sciencedirect.com/science/article/pii/S0959152413001078#. [Accessed 22/06/2013]	en
heal.abstract	This work presents a novel control scheme based on approximating the inverse process dynamics with a radial basis function (RBF) neural network model, trained with the fuzzy means algorithm. The produced RBF network constitutes an inverse model of the process, which can be applied as an explicit control law. In order to avoid extrapolation in the RBF model predictions, a concept borrowed from chemometrics, namely the applicability domain, is incorporated to the proposed framework. Moreover, an error correction term is added, allowing the inverse neural controller to account for modeling errors and process uncertainty and eliminate offset. The proposed approach is applied to the control of a nonlinear Continuous Stirred Tank Reactor (CSTR) exhibiting multiple equilibrium points, including an unstable one. A comparison with other control schemes on various tests, including set-point tracking, unmeasured disturbance rejection and process uncertainty highlights the advantages of the proposed controller.	en
heal.journalName	Journal of Process Control	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true