Title:	The principle of prediction of complex time-dependent nonlinear problems using RNN
Authors:	Karban, Pavel Petrášová, Iveta Doležel, Ivo
Citation:	KARBAN, P. PETRÁŠOVÁ, I. DOLEŽEL, I. The principle of prediction of complex time-dependent nonlinear problems using RNN. In Proceedings of the 23rd International Conference on Computational Problems of Electrical Engineering, CPEE 2022. Piscataway: IEEE, 2022. s. nestránkováno. ISBN: 979-8-3503-9625-6
Issue Date:	2022
Publisher:	IEEE
Document type:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85142158137 http://hdl.handle.net/11025/51682
ISBN:	979-8-3503-9625-6
Keywords in different language:	surrogate model;recurrent neural networks;LSTM;analytical model;dynamic nonlinear problem
Abstract in different language:	An approach based on recurrent neural networks (RNNs) is applied to verify the possibility of using surrogate models for the prediction of dynamic nonlinear problems. Modeling complex time dependencies is currently still a challenge, when the structure of the neural network needs to be adapted to the dynamics of the problem. In this paper, the possibility of using prediction in space-time problems is illustrated by the possibility of using it to predict the course of the current in a simple RL circuit that is powered by a voltage source.
Rights:	Plný text je přístupný v rámci univerzity přihlášeným uživatelům © IEEE
Appears in Collections:	Konferenční příspěvky / Conference papers (RICE) Konferenční příspěvky / Conference Papers (KEP) OBD

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