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

DOI10.1017/jfm.2023.446arXiv2208.03498OpenAlexW4382894956MaRDI QIDQ6114185

Justin A. Sirignano, Jonathan F. MacArt

Publication date: 11 July 2023

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

Full work available at URL: https://arxiv.org/abs/2208.03498

zbMATH Keywords

neural networkdrag coefficientdirect numerical simulation dataadjoint partial differential equation optimization methodnear-wall/far-field mean flowrectangular prism body

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Direct numerical and large eddy simulation of turbulence (76F65) Basic methods in fluid mechanics (76M99)

Related Items (2)

Physics-agnostic and physics-infused machine learning for thin films flows: modelling, and predictions from small data ⋮ Four-dimensional variational data assimilation of a turbulent jet for super-temporal-resolution reconstruction

Cites Work

• Anisotropic minimum-dissipation (AMD) subgrid-scale model implemented in openfoam: verification and assessment in single-phase and multi-phase flows
• Machine learning strategies for systems with invariance properties
• High order conservative finite difference scheme for variable density low Mach number turbulent flows
• Application of a fractional-step method to incompressible Navier-Stokes equations
• Semi-implicit iterative methods for low Mach number turbulent reacting flows: operator splitting versus approximate factorization
• An analysis of numerical errors in large-eddy simulations of turbulence
• Efficient assimilation of sparse data into RANS-based turbulent flow simulations using a discrete adjoint method
• DPM: a deep learning PDE augmentation method with application to large-eddy simulation
• Stable \textit{a posteriori} LES of 2D turbulence using convolutional neural networks: backscattering analysis and generalization to higher \(Re\) via transfer learning
• A paradigm for data-driven predictive modeling using field inversion and machine learning
• PDE-constrained models with neural network terms: optimization and global convergence
• Machine Learning for Fluid Mechanics
• Numerical Calculation of Time-Dependent Viscous Incompressible Flow of Fluid with Free Surface
• A dynamic subgrid-scale eddy viscosity model
• Evaluation of subgrid-scale models using an accurately simulated turbulent flow
• Wall-Modeled Large-Eddy Simulation for Complex Turbulent Flows
• Optimal LES formulations for isotropic turbulence
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Turbulence Modeling in the Age of Data
• Comparative analysis of machine learning methods for active flow control

This page was built for publication: Deep learning closure models for large-eddy simulation of flows around bluff bodies