Solving evolutionary problems using recurrent neural networks

dc.contributor.authorPetrášová, Iveta
dc.contributor.authorKarban, Pavel
dc.date.accessioned2023-12-11T11:00:08Z
dc.date.available2023-12-11T11:00:08Z
dc.date.issued2023
dc.description.abstract-translatedA technique for flexible control of induction baking of electrically non-conductive layers (paints, varnishes, resins, etc.) is presented, based on the temperature prediction. As the numerical solution of the full model of the process takes a long time, it is necessary to approximate it with a suitable equivalent model. In this case, recurrent neural networks (RNNs) prove to be a powerful tool for solving the task practically online and providing the input data to control the field current fast enough. The methodology was first tested to predict the current based on the knowledge of the voltage, which can be determined from the analytical solution of the ordinary differential equation that describes the feeding circuit. Subsequently, the methodology was implemented on a system for baking non-conductive layers.en
dc.format
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationPETRÁŠOVÁ, I. KARBAN, P. Solving evolutionary problems using recurrent neural networks . JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2023, roč. 426, č. July 2023, s. nestránkováno. ISSN: 0377-0427cs
dc.identifier.document-number944208200001
dc.identifier.doi10.1016/j.cam.2023.115091
dc.identifier.issn0377-0427
dc.identifier.obd43940812
dc.identifier.uri2-s2.0-85147854346
dc.identifier.urihttp://hdl.handle.net/11025/54959
dc.language.iso
dc.language.isoenen
dc.project.IDSGS-2021-011/Rozvoj technik snižování řádu systému v elektrotechnických aplikacíchcs
dc.publisherElsevieren
dc.relation.ispartofseriesJournal Of Computational And Applied Mathematicsen
dc.rights© Elsevieren
dc.rights.accessopenAccessen
dc.subject.translatedevolutionary problemen
dc.subject.translatedpredictionen
dc.subject.translatedrecurrent neural networksen
dc.subject.translatedLSTMen
dc.subject.translatedinduction heatingen
dc.subject.translatednumerical modelingen
dc.titleSolving evolutionary problems using recurrent neural networksen
dc.typečlánekcs
dc.typearticleen
dc.type.status
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
Petrasova_1-s2.0-S0377042723000353-main.pdf
Size:
1.19 MB
Format:
Adobe Portable Document Format