Physics-guided deep learning for generating turbulent inflow conditions

DOI10.1017/jfm.2022.61OpenAlexW4211029392MaRDI QIDQ5029513

Linqi Yu, Heechang Lim, Mustafa Z. Yousif

Publication date: 14 February 2022

Published in: Journal of Fluid Mechanics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1017/jfm.2022.61

zbMATH Keywords

machine learningturbulent boundary layersturbulence simulation

Mathematics Subject Classification ID

Fluid mechanics (76-XX)

Related Items (2)

An efficient and low-divergence method for generating inhomogeneous and anisotropic turbulence with arbitrary spectra ⋮ A transformer-based synthetic-inflow generator for spatially developing turbulent boundary layers

Uses Software

• TensorFlow
• Adam

Cites Work

• Unnamed Item
• Assessment of the vortex method for large eddy simulation inlet conditions
• Generation of turbulent inflow data for spatially-developing boundary layer simulations
• A digital filter based generation of inflow data for spatially developing direct numerical or large eddy simulations.
• A practical method for calculating largest Lyapunov exponents from small data sets
• Generation of inflow data for inhomogeneous turbulence
• Turbulent boundary layers at moderate Reynolds numbers: inflow length and tripping effects
• Inflow Turbulence Generation Methods
• Machine Learning for Fluid Mechanics
• Direct numerical simulation of turbulent channel flow up to Reτ=590
• Direct simulation of a turbulent boundary layer up to R_θ = 1410
• Direct numerical simulation of turbulent flow over a backward-facing step
• Data-driven prediction of unsteady flow over a circular cylinder using deep learning
• Turbulent inflow conditions for large-eddy simulation based on low-order empirical model

This page was built for publication: Physics-guided deep learning for generating turbulent inflow conditions