File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Servo controller design using neural networks

TitleServo controller design using neural networks
Authors
KeywordsBack Propagation
Controller Design
Neural Networks
Issue Date1993
PublisherSpringer New York LLC. The Journal's web site is located at http://springerlink.metapress.com/openurl.asp?genre=journal&issn=0924-669X
Citation
Applied Intelligence, 1993, v. 3 n. 2, p. 131-141 How to Cite?
AbstractThe dynamics of a physical plant may be difficult to express as concise mathematical equations. In practice there exist uncertainties that cannot be modeled with the system equations. Hence, robustness against system uncertainties is essential in a control system design. In this article, multilayered neural networks (MNNs) are used to compensate for model uncertainties of a dynamical system. Neural network models are used along with a classical linear servo controller derived from the linear state space equations. These models are trained so that system uncertainties are compensated. The design of a servo system indicates the enhanced performance of the neural-network-based servo controller as compared to the classical servo controller. © 1993 Kluwer Academic Publishers.
Persistent Identifierhttp://hdl.handle.net/10722/155494
ISSN
2015 Impact Factor: 1.215
2015 SCImago Journal Rankings: 0.777
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorPatil, Sen_US
dc.contributor.authorPang, GKHen_US
dc.date.accessioned2012-08-08T08:33:46Z-
dc.date.available2012-08-08T08:33:46Z-
dc.date.issued1993en_US
dc.identifier.citationApplied Intelligence, 1993, v. 3 n. 2, p. 131-141en_US
dc.identifier.issn0924-669Xen_US
dc.identifier.urihttp://hdl.handle.net/10722/155494-
dc.description.abstractThe dynamics of a physical plant may be difficult to express as concise mathematical equations. In practice there exist uncertainties that cannot be modeled with the system equations. Hence, robustness against system uncertainties is essential in a control system design. In this article, multilayered neural networks (MNNs) are used to compensate for model uncertainties of a dynamical system. Neural network models are used along with a classical linear servo controller derived from the linear state space equations. These models are trained so that system uncertainties are compensated. The design of a servo system indicates the enhanced performance of the neural-network-based servo controller as compared to the classical servo controller. © 1993 Kluwer Academic Publishers.en_US
dc.languageengen_US
dc.publisherSpringer New York LLC. The Journal's web site is located at http://springerlink.metapress.com/openurl.asp?genre=journal&issn=0924-669Xen_US
dc.relation.ispartofApplied Intelligenceen_US
dc.subjectBack Propagationen_US
dc.subjectController Designen_US
dc.subjectNeural Networksen_US
dc.titleServo controller design using neural networksen_US
dc.typeArticleen_US
dc.identifier.emailPang, GKH:gpang@eee.hku.hken_US
dc.identifier.authorityPang, GKH=rp00162en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1007/BF00871893en_US
dc.identifier.scopuseid_2-s2.0-5244354794en_US
dc.identifier.volume3en_US
dc.identifier.issue2en_US
dc.identifier.spage131en_US
dc.identifier.epage141en_US
dc.identifier.isiWOS:A1993MN02200002-
dc.publisher.placeUnited Statesen_US
dc.identifier.scopusauthoridPatil, S=27067952800en_US
dc.identifier.scopusauthoridPang, GKH=7103393283en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats