FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313643717> ?p ?o ?g. }

• W4313643717 abstract "Various aspects of machine learning (ML) are explored to resolve limitations appearing in current ML-based subgrid scale (SGS) stress modeling. Graph neural network (GNN), applied in the present study, allows flexible and rigorous use of spatial convolution regardless of the proximity to physical boundaries and mesh uniformity. Along with GNN, the proposed feature scaling method relies only on the local quantities and can be applied for a range of flow configurations. A data augmentation method is also proposed to consider the rotational invariant. All these techniques are implemented in the present model, and the model is compared with versions of corresponding ML-based models including a typical multilayer perceptron (MLP) for various flow configurations. The results showed that both GNN and MLP models yield reasonable prediction overall. However, GNN shows superior performance near-wall due to spatial convolution. Although the present method implements the rotational invariant discretely, the augmentation method is found to produce consistent performance for any rotated coordinates. The minimal flow configuration, which can train a model to predict a range of flow configurations, is also explored. It is found that a model trained based on turbulent channel flows alone yields a close level of prediction robustness to the ones trained with multiple flow configurations. The developed GNN model is implemented in OpenFOAM, and large eddy simulation (LES) results are compared with corresponding direct numerical simulation data. With these proposed techniques, ML-based SGS models can be improved in terms of robustness and usability for a range of LES applications." @default.
• W4313643717 created "2023-01-07" @default.
• W4313643717 creator A5003724334 @default.
• W4313643717 creator A5006523100 @default.
• W4313643717 creator A5039930384 @default.
• W4313643717 creator A5043392427 @default.
• W4313643717 creator A5047600710 @default.
• W4313643717 date "2023-01-01" @default.
• W4313643717 modified "2023-10-16" @default.
• W4313643717 title "Exploration of robust machine learning strategy for subgrid scale stress modeling" @default.
• W4313643717 cites W1550671346 @default.
• W4313643717 cites W1553608069 @default.
• W4313643717 cites W1595241212 @default.
• W4313643717 cites W1966617633 @default.
• W4313643717 cites W1990121322 @default.
• W4313643717 cites W1990563418 @default.
• W4313643717 cites W2012323802 @default.
• W4313643717 cites W2021269264 @default.
• W4313643717 cites W2039156010 @default.
• W4313643717 cites W2054101073 @default.
• W4313643717 cites W2074447412 @default.
• W4313643717 cites W2084742709 @default.
• W4313643717 cites W2086209713 @default.
• W4313643717 cites W2088146531 @default.
• W4313643717 cites W2091345137 @default.
• W4313643717 cites W2132926613 @default.
• W4313643717 cites W2145339207 @default.
• W4313643717 cites W2153571053 @default.
• W4313643717 cites W2169376632 @default.
• W4313643717 cites W2564800775 @default.
• W4313643717 cites W2787860880 @default.
• W4313643717 cites W2793628078 @default.
• W4313643717 cites W2808149866 @default.
• W4313643717 cites W2902480423 @default.
• W4313643717 cites W2902987217 @default.
• W4313643717 cites W2919115771 @default.
• W4313643717 cites W2979648346 @default.
• W4313643717 cites W3035928882 @default.
• W4313643717 cites W3080891795 @default.
• W4313643717 cites W3099258581 @default.
• W4313643717 cites W3101316902 @default.
• W4313643717 cites W3129530645 @default.
• W4313643717 cites W3134546754 @default.
• W4313643717 cites W3138622289 @default.
• W4313643717 cites W4210257598 @default.
• W4313643717 cites W4280634758 @default.
• W4313643717 cites W4283652414 @default.
• W4313643717 cites W4285500432 @default.
• W4313643717 doi "https://doi.org/10.1063/5.0134471" @default.
• W4313643717 hasPublicationYear "2023" @default.
• W4313643717 type Work @default.
• W4313643717 citedByCount "0" @default.
• W4313643717 crossrefType "journal-article" @default.
• W4313643717 hasAuthorship W4313643717A5003724334 @default.
• W4313643717 hasAuthorship W4313643717A5006523100 @default.
• W4313643717 hasAuthorship W4313643717A5039930384 @default.
• W4313643717 hasAuthorship W4313643717A5043392427 @default.
• W4313643717 hasAuthorship W4313643717A5047600710 @default.
• W4313643717 hasConcept C104317684 @default.
• W4313643717 hasConcept C11413529 @default.
• W4313643717 hasConcept C121332964 @default.
• W4313643717 hasConcept C154945302 @default.
• W4313643717 hasConcept C185592680 @default.
• W4313643717 hasConcept C33098168 @default.
• W4313643717 hasConcept C41008148 @default.
• W4313643717 hasConcept C50644808 @default.
• W4313643717 hasConcept C55493867 @default.
• W4313643717 hasConcept C60908668 @default.
• W4313643717 hasConcept C63479239 @default.
• W4313643717 hasConcept C81363708 @default.
• W4313643717 hasConceptScore W4313643717C104317684 @default.
• W4313643717 hasConceptScore W4313643717C11413529 @default.
• W4313643717 hasConceptScore W4313643717C121332964 @default.
• W4313643717 hasConceptScore W4313643717C154945302 @default.
• W4313643717 hasConceptScore W4313643717C185592680 @default.
• W4313643717 hasConceptScore W4313643717C33098168 @default.
• W4313643717 hasConceptScore W4313643717C41008148 @default.
• W4313643717 hasConceptScore W4313643717C50644808 @default.
• W4313643717 hasConceptScore W4313643717C55493867 @default.
• W4313643717 hasConceptScore W4313643717C60908668 @default.
• W4313643717 hasConceptScore W4313643717C63479239 @default.
• W4313643717 hasConceptScore W4313643717C81363708 @default.
• W4313643717 hasFunder F4320334789 @default.
• W4313643717 hasIssue "1" @default.
• W4313643717 hasLocation W43136437171 @default.
• W4313643717 hasOpenAccess W4313643717 @default.
• W4313643717 hasPrimaryLocation W43136437171 @default.
• W4313643717 hasRelatedWork W2735477435 @default.
• W4313643717 hasRelatedWork W2748454020 @default.
• W4313643717 hasRelatedWork W2807436399 @default.
• W4313643717 hasRelatedWork W3001728219 @default.
• W4313643717 hasRelatedWork W3016958897 @default.
• W4313643717 hasRelatedWork W3045739591 @default.
• W4313643717 hasRelatedWork W3181746755 @default.
• W4313643717 hasRelatedWork W4283379348 @default.
• W4313643717 hasRelatedWork W4312417841 @default.
• W4313643717 hasRelatedWork W4385415357 @default.
• W4313643717 hasVolume "35" @default.
• W4313643717 isParatext "false" @default.
• W4313643717 isRetracted "false" @default.

• next