13 papers · 1 filter
Solver-in-the-loop training of deep learning closures for large-eddy simulation of turbulent premixed jet flames
Priyesh Kakka, Jonathan F. MacArt
Large-eddy simulation (LES) turbulence models often fail to capture the effects of chemical heat release and the resulting modulation of turbulence in premixed flames, underscoring…
Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows
Daniel Dehtyriov, Jonathan F. MacArt, Justin Sirignano
Turbulence is ubiquitous in engineering and science, yet direct simulation is prohibitively expensive. The Reynolds-averaged Navier-Stokes (RANS) equations provide savings exceedin…
Dynamic mixed turbulence modeling using a super-resolution generative adversarial approach
Ludovico Nista, Christoph D. K. Schumann, Temistocle Grenga +3
A dynamic mixed super-resolution model (DMSRM) for large-eddy simulations (LESs) is proposed, which combines the traditional dynamic mixed model (DMM) formulation with the generati…
Physics-Based Machine Learning Closures and Wall Models for Hypersonic Transition-Continuum Boundary Layer Predictions
Ashish S. Nair, Narendra Singh, Marco Panesi +2
Modeling rarefied hypersonic flows remains a fundamental challenge due to the breakdown of classical continuum assumptions in the transition-continuum regime, where the Knudsen num…
Active Control of Turbulent Airfoil Flows Using Adjoint-based Deep Learning
Xuemin Liu, Tom Hickling, Jonathan F. MacArt
We train active neural-network flow controllers using a deep learning PDE augmentation method to optimize lift-to-drag ratios in turbulent airfoil flows at Reynolds number $5\times…
ZipGAN: Super-Resolution-based Generative Adversarial Network Framework for Data Compression of Direct Numerical Simulations
Ludovico Nista, Christoph D. K. Schumann, Fabian Fröde +5
The advancement of high-performance computing has enabled the generation of large direct numerical simulation (DNS) datasets of turbulent flows, driving the need for efficient comp…