Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Heidler, Václav | |
dc.contributor.author | Pecka, Aleš | |
dc.contributor.author | Bublík, Ondřej | |
dc.contributor.author | Vimmr, Jan | |
dc.date.accessioned | 2023-06-26T10:00:08Z | - |
dc.date.available | 2023-06-26T10:00:08Z | - |
dc.date.issued | 2022 | |
dc.identifier.citation | 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 | cs |
dc.identifier.issn | 2696-6999 | |
dc.identifier.uri | 2-s2.0-85146928981 | |
dc.identifier.uri | http://hdl.handle.net/11025/52986 | |
dc.format | 10 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Scipedia S.L. | en |
dc.relation.ispartofseries | ECCOMAS conference proceeding | en |
dc.rights | © Scipedia S.L. | en |
dc.title | Neural network prediction of the flow field in a periodic domain with hypernetwork parametrization | en |
dc.type | konferenční příspěvek | cs |
dc.type | ConferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | 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. | en |
dc.subject.translated | blade cascade | en |
dc.subject.translated | compressible fluid flow | en |
dc.subject.translated | convolution neural network | en |
dc.subject.translated | hypernetwork | en |
dc.subject.translated | Reynolds parametrization | en |
dc.subject.translated | U-Net | en |
dc.identifier.doi | 10.23967/eccomas.2022.192 | |
dc.type.status | Peer-reviewed | en |
dc.identifier.obd | 43939209 | |
dc.project.ID | GA21-31457S/Použití neuronových sítí pro rychlou predikci proudového pole v úlohách interakce tekutiny s tělesem | cs |
Vyskytuje se v kolekcích: | Konferenční příspěvky / Conference papers (NTIS) Konferenční příspěvky / Conference Papers (KME) OBD |
Soubory připojené k záznamu:
Soubor | Velikost | Formát | |
---|---|---|---|
Draft_Sanchez_Pinedo_7235092981732_paper.pdf | 1,55 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/52986
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.