Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data

Numerical simulations on fluid dynamics problems primarily rely on spatially or/and temporally discretization of the governing equation using polynomials into a finite-dimensional algebraic system. Due to the multi-scale nature of the physics and sensitivity from meshing a complicated geometry, such...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computer methods in applied mechanics and engineering Jg. 361; S. 112732
Hauptverfasser:	Sun, Luning, Gao, Han, Pan, Shaowu, Wang, Jian-Xun
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Amsterdam Elsevier B.V 01.04.2020 Elsevier BV
Schlagworte:	Artificial neural networks Boundary conditions Cardiovascular flows Computational fluid dynamics Computer simulation Data points Deep learning Design optimization First principles Fluid dynamics Fluid flow Hemodynamics Internal flow Label-free Machine learning Mathematical models Meshing Navier-Stokes Navier-Stokes equations Neural networks Partial differential equations Physics Physics-informed machine learning Polynomials Simulation Training Uncertainty Uncertainty quantification Physics-informed machine learning Uncertainty quantification Navier-Stokes Cardiovascular flows Label-free Neural networks
ISSN:	0045-7825, 1879-2138
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!