A cooperative neural network control structure and its application for systems having dead-zone nonlinearities

Basit Öğe Kaydı
dc.authorid0000-0002-3234-281X
dc.contributor.authorDinçmen, Erkinen_US
dc.date.accessioned2022-01-30T23:30:06Z
dc.date.available2022-01-30T23:30:06Z
dc.date.issued2022-03
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Makine Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Mechanical Engineeringen_US
dc.description.abstractAn adaptive control structure utilizing two feed-forward neural networks (NN) is proposed to deal with systems having unknown nonlinearities. One of the networks is trained to mimic the nonlinear system dynamics. Its training will be repeated with periods in order to keep it an updated valid model of the system all the times since the parameters and/or nonlinearities of the system may change during time. The other network, which is the Controller NN, adapts itself continuously by collaborating with the Model NN. The stability-convergence analysis of both networks is performed via Lyapunov method. An example system is chosen to show the applicability of the control algorithm. This example system is created by combining a linear dynamics model with a dead-zone function to represent a nonlinear system to be controlled. It should be noted that the proposed control structure can be used in any nonlinear system without knowing the system dynamics. The only information required by Model NN is the training set consisting input-output data pairs of the system. The Model NN is trained offline with this training set, and afterward the Controller NN adapts its weights online continuously during the control task with the help of Model NN. The performances of PD and PID controllers are also given for comparison purposes.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationDinçmen, E. (2022). A cooperative neural network control structure and its application for systems having dead-zone nonlinearities. Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, 46(1), 187-203. doi:10.1007/s40998-021-00475-0en_US
dc.identifier.doi10.1007/s40998-021-00475-0
dc.identifier.endpage203
dc.identifier.issn2228-6179
dc.identifier.issn2364-1827
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85123477263
dc.identifier.scopusqualityQ2
dc.identifier.startpage187
dc.identifier.urihttps://hdl.handle.net/11729/3420
dc.identifier.urihttp://dx.doi.org/10.1007/s40998-021-00475-0
dc.identifier.volume46
dc.identifier.wosWOS:000745612900002
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakScience Citation Index Expanded (SCI-EXPANDED)en_US
dc.institutionauthorDinçmen, Erkinen_US
dc.institutionauthorid0000-0002-3234-281X
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherSpringer International Publishing Agen_US
dc.relation.ispartofIranian Journal Of Science And Technology-Transactions Of Electrical Engineeringen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectActuatoren_US
dc.subjectAdaptive controlen_US
dc.subjectDead zoneen_US
dc.subjectDiscrete-time-systemsen_US
dc.subjectDynamic surface controlen_US
dc.subjectIdentificationen_US
dc.subjectMachine learningen_US
dc.subjectNeural network controlen_US
dc.subjectTracking controlen_US
dc.titleA cooperative neural network control structure and its application for systems having dead-zone nonlinearitiesen_US
dc.typeArticleen_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
A_Cooperative_Neural_Network_Control_Structure_and_Its_Application_for_Systems_Having_Dead_Zone_Nonlinearities.pdf
Boyut:
774.19 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Makale Koleksiyonu | Makine Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu