Learning by neural networks under physical constraints for simulation in fluid mechanics

DOI10.1016/j.compfluid.2022.105632OpenAlexW4225512251WikidataQ114952441 ScholiaQ114952441MaRDI QIDQ2101998

Yuekun Yang, Youssef Mesri

Publication date: 7 December 2022

Published in: Computers and Fluids (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.compfluid.2022.105632

zbMATH Keywords

fluid dynamicsdeep learningone-hot matrixphysical informed neural networks (PINN)Q-criterion

Mathematics Subject Classification ID

Fluid mechanics (76-XX)

Uses Software

• Cimlib
• NSFnets

Cites Work

• Parallel and adaptive VMS finite elements formulation for aerothermal problems
• Inferring solutions of differential equations using noisy multi-fidelity data
• NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations
• On coherent-vortex identification in turbulence
• Advanced parallel computing in material forming with CIMLib
• Coherent structures in uniformly sheared turbulent flow
• Hairpin vortex organization in wall turbulence
• Three-dimensional vortex organization in a high-Reynolds-number supersonic turbulent boundary layer
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• Direct numerical simulation of turbulence in a nominally zero-pressure-gradient flat-plate boundary layer
• Reynolds- and Mach-number effects in canonical shock–turbulence interaction
• Self-similar vortex clusters in the turbulent logarithmic region
• Analytical theories of turbulence

This page was built for publication: Learning by neural networks under physical constraints for simulation in fluid mechanics