Title:	Solving evolutionary problems using recurrent neural networks
Authors:	Petrášová, Iveta Karban, Pavel
Citation:	PETRÁŠOVÁ, 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: 0377-0427
Issue Date:	2023
Publisher:	Elsevier
Document type:	článek article
URI:	2-s2.0-85147854346 http://hdl.handle.net/11025/54959
ISSN:	0377-0427
Keywords in different language:	evolutionary problem;prediction;recurrent neural networks;LSTM;induction heating;numerical modeling
Abstract in different language:	A 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.
Rights:	© Elsevier
Appears in Collections:	Články / Articles (RICE) Články / Articles (KEP) OBD

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.