Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Deep learning closure models for large-eddy simulation of flows around bluff bodies

Journal Article · · Journal of Fluid Mechanics
DOI:https://doi.org/10.1017/jfm.2023.446· OSTI ID:2424006

Near-wall flow simulation remains a central challenge in aerodynamics modelling: Reynolds-averaged Navier–Stokes predictions of separated flows are often inaccurate, and large-eddy simulation (LES) can require prohibitively small near-wall mesh sizes. A deep learning (DL) closure model for LES is developed by introducing untrained neural networks into the governing equations and trainingin situfor incompressible flows around rectangular prisms at moderate Reynolds numbers. The DL-LES models are trained using adjoint partial differential equation (PDE) optimization methods to match, as closely as possible, direct numerical simulation (DNS) data. They are then evaluated out-of-sample – for aspect ratios, Reynolds numbers and bluff-body geometries not included in the training data – and compared with standard LES models. The DL-LES models outperform these models and are able to achieve accurate LES predictions on a relatively coarse mesh (downsampled from the DNS mesh by factors of four or eight in each Cartesian direction). We study the accuracy of the DL-LES model for predicting the drag coefficient, near-wall and far-field mean flow, and resolved Reynolds stress. A crucial challenge is that the LES quantities of interest are the steady-state flow statistics; for example, a time-averaged velocity component$$\langle {u}_i\rangle (x) = \lim _{t \rightarrow \infty } ({1}/{t}) \int _0^t u_i(s,x)\, {\rm d}s$$. Calculating the steady-state flow statistics therefore requires simulating the DL-LES equations over a large number of flow times through the domain. It is a non-trivial question whether an unsteady PDE model with a functional form defined by a deep neural network can remain stable and accurate on$$t \in [0, \infty )$$, especially when trained over comparatively short time intervals. Our results demonstrate that the DL-LES models are accurate and stable over long time horizons, which enables the estimation of the steady-state mean velocity, fluctuations and drag coefficient of turbulent flows around bluff bodies relevant to aerodynamics applications.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-00OR22725
OSTI ID:
2424006
Journal Information:
Journal of Fluid Mechanics, Journal Name: Journal of Fluid Mechanics Vol. 966; ISSN 0022-1120
Publisher:
Cambridge University Press
Country of Publication:
United States
Language:
English

References (30)

Scientific multi-agent reinforcement learning for wall-models of turbulent flows journal March 2022
Deep neural networks for data-driven LES closure models journal December 2019
Comparative analysis of machine learning methods for active flow control journal March 2023
Minimum-dissipation models for large-eddy simulation journal August 2015
On the role and challenges of CFD in the aerospace industry journal January 2016
A paradigm for data-driven predictive modeling using field inversion and machine learning journal January 2016
Overview of global data assimilation developments in numerical weather-prediction centres journal October 2005
Anisotropic minimum-dissipation (AMD) subgrid-scale model implemented in OpenFOAM: Verification and assessment in single-phase and multi-phase flows journal February 2019
Reynolds averaged turbulence modelling using deep neural networks with embedded invariance journal October 2016
Machine learning strategies for systems with invariance properties journal August 2016
Efficient assimilation of sparse data into RANS-based turbulent flow simulations using a discrete adjoint method journal December 2022
General Circulation Experiments with the Primitive Equations: i. the Basic Experiment* journal March 1963
PDE-constrained models with neural network terms: Optimization and global convergence journal May 2023
High order conservative finite difference scheme for variable density low Mach number turbulent flows journal July 2008
Numerical Calculation of Time-Dependent Viscous Incompressible Flow of Fluid with Free Surface journal January 1965
A dynamic subgrid‐scale eddy viscosity model journal July 1991
Wall-Modeled Large-Eddy Simulation for Complex Turbulent Flows journal January 2018
Application of a fractional-step method to incompressible Navier-Stokes equations journal June 1985
Embedded training of neural-network subgrid-scale turbulence models journal May 2021
A proposed modification of the Germano subgrid‐scale closure method journal March 1992
Optimal LES formulations for isotropic turbulence journal November 1999
Machine Learning for Fluid Mechanics journal September 2019
Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning journal June 2022
DPM: A deep learning PDE augmentation method with application to large-eddy simulation journal December 2020
Evaluation of subgrid-scale models using an accurately simulated turbulent flow journal March 1979
Semi-implicit iterative methods for low Mach number turbulent reacting flows: Operator splitting versus approximate factorization journal December 2016
An Analysis of Numerical Errors in Large-Eddy Simulations of Turbulence journal April 1996
Turbulence Modeling in the Age of Data journal January 2019
A data assimilation model for turbulent flows using continuous adjoint formulation journal October 2018
Large eddy simulation of aircraft at affordable cost: a milestone in computational fluid dynamics journal January 2021

Similar Records

Dynamics and bifurcations of laminar annular swirling and non-swirling jets
Journal Article · 2022 · Journal of Fluid Mechanics · OSTI ID:1872655

A data-driven method for modelling dissipation rates in stratified turbulence
Journal Article · 2023 · Journal of Fluid Mechanics · OSTI ID:2246688

Towards fast and accurate predictions of radio frequency power deposition and current profile via data-driven modelling: applications to lower hybrid current drive
Journal Article · 2022 · Journal of Plasma Physics · OSTI ID:1882254

Related Subjects