Název:	Neural network prediction of the flow field in a periodic domain with hypernetwork parametrization
Autoři:	Heidler, Václav Pecka, Aleš Bublík, Ondřej Vimmr, Jan
Citace zdrojového dokumentu:	HEIDLER, V. PECKA, A. BUBLÍK, O. VIMMR, J. NEURAL NETWORK PREDICTION OF THE FLOW FIELD IN A PERIODIC DOMAIN WITH HYPERNETWORK PARAMETRIZATION. In ECCOMAS conference proceeding. Barcelona: Scipedia S.L., 2022. s. 1-10. ISBN: neuvedeno , ISSN: 2696-6999
Datum vydání:	2022
Nakladatel:	Scipedia S.L.
Typ dokumentu:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85146928981 http://hdl.handle.net/11025/52986
ISSN:	2696-6999
Klíčová slova v dalším jazyce:	blade cascade;compressible fluid flow;convolution neural network;hypernetwork;Reynolds parametrization;U-Net
Abstrakt v dalším jazyce:	This paper is concerned with fast flow field prediction in a blade cascade for variable blade shapes as well as variable Reynolds number using the machine-learning architecture called convolutional neural network. To generate flow field for a specific Reynolds number, an encoder-decoder convolutional neural network, also called U-Net, is used. The values 500, 1000 and 1500 of the Reynolds number are chosen as the training set. Three U-Nets were trained on CFD results for 100 blade profiles, each U-Net for a different Reynolds number. In order to get a prediction for variable Reynolds number, a so-called hypernetwork in employed. The hypernetwork essentially interpolates between the two trained U-Nets. The architecture of the hypernetwork is fully-connected feedforward neural network with one input neuron correspond-ing to the Reynolds number, one hidden layer and the output layer corresponds to the weights for the interpolated U-Net. The concept of the hypernetwork-based parametrization is tested on a problem of compressible fluid flow through a blade cascade with three unseen blade profiles and unseen Reynolds number.
Práva:	© Scipedia S.L.
Vyskytuje se v kolekcích:	Konferenční příspěvky / Conference papers (NTIS) Konferenční příspěvky / Conference Papers (KME) OBD

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.