☆ 4.7 Article

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

JOURNAL OF FLUID MECHANICS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Interdisciplinary Applications

PDE-constrained models with neural network terms: Optimization and global convergence

Justin Sirignano et al.

Summary: Recent research has developed partial differential equation (PDE) models in science and engineering using deep learning. The PDE's functional form is determined by a neural network and calibrated to available data. Gradient descent is used to optimize the neural network parameters in the PDE, with the gradient evaluated using an adjoint PDE. As the number of parameters increases, the PDE and adjoint PDE converge to a non-local PDE system. The adjoint method is then used to train a neural network model for fluid mechanics, acting as a closure model for the Reynolds-averaged Navier-Stokes equations.

JOURNAL OF COMPUTATIONAL PHYSICS (2023)

添加到收藏夹

Article Mechanics

Comparative analysis of machine learning methods for active flow control

Fabio Pino et al.

Summary: This work presents a comparative analysis of machine learning frameworks such as genetic programming and reinforcement learning in flow control. The algorithms are benchmarked against global optimization techniques and tested on three test cases. The results show differences in exploration versus exploitation and the balance between model capacity and required complexity. The comparison paves the way for hybridization of methods and offers perspectives on future development in flow control problems.

JOURNAL OF FLUID MECHANICS (2023)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning

Yifei Guan et al.

Summary: Developing machine learning-based data-driven subgrid-scale models for large eddy simulation is of growing interest. Prior tests show that deep convolutional neural networks accurately predict the inter-scale transfers, and transfer learning enhances the stability and accuracy of the model for different flow conditions.

JOURNAL OF COMPUTATIONAL PHYSICS (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Scientific multi-agent reinforcement learning for wall-models of turbulent flows

H. Jane Bae et al.

Summary: Researchers propose a multi-agent reinforcement learning approach to discover wall models for large-eddy simulations, solving the challenge of capturing near-wall dynamics in turbulent flow simulations.

NATURE COMMUNICATIONS (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Efficient assimilation of sparse data into RANS-based turbulent flow simulations using a discrete adjoint method

Oliver Brenner et al.

Summary: Turbulent flow simulations based on the Reynolds-averaged Navier-Stokes equations are widely used in industrial flow problems, but their accuracy is limited due to inherent averaging and closure models. Data assimilation can combine experimental data with closure models to improve simulation results. The objective of this study is to recover a spatially varying eddy viscosity correction factor from sparse reference data.

JOURNAL OF COMPUTATIONAL PHYSICS (2022)

添加到收藏夹

Article Physics, Fluids & Plasmas

Embedded training of neural-network subgrid-scale turbulence models

Jonathan F. MacArt et al.

Summary: In this study, a deep neural-network model is optimized in conjunction with the governing flow equations to provide a model for subgrid-scale stresses in a temporally developing plane turbulent jet at Reynolds number Re-0 = 6000. Training based on this model shows that a lower mesh density is needed for accurate prediction of mean flow, Reynolds stresses, and spectra. However, directly training the neural-network model to match filtered subgrid-scale stresses without incorporating the flow equations during training leads to incorrect predictions.

PHYSICAL REVIEW FLUIDS (2021)

添加到收藏夹

Article Mechanics

Large eddy simulation of aircraft at affordable cost: a milestone in computational fluid dynamics

Konrad A. Goc et al.

Summary: This paper systematically studies the predictive capability of LES for a range of angles of attack, grid resolution, and wind tunnel effects. The results show reduced grid point requirements while maintaining accuracy, demonstrating potential for industrial use in aeronautical design.

FLOW (2021)

添加到收藏夹

Review Mechanics

Machine Learning for Fluid Mechanics

Steven L. Brunton et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 52 (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

DPM: A deep learning PDE augmentation method with application to large-eddy simulation

Justin Sirignano et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2020)

添加到收藏夹

Review Mechanics

Turbulence Modeling in the Age of Data

Karthik Duraisamy et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 51 (2019)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Anisotropic minimum-dissipation (AMD) subgrid-scale model implemented in OpenFOAM: Verification and assessment in single-phase and multi-phase flows

Amir-Pouyan Zahiri et al.

COMPUTERS & FLUIDS (2019)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Deep neural networks for data-driven LES closure models

Andrea Beck et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2019)

添加到收藏夹

Review Mechanics

Wall-Modeled Large-Eddy Simulation for Complex Turbulent Flows

Sanjeeb T. Bose et al.

ANNUAL REVIEW OF FLUID MECHANICS, VOL 50 (2018)

添加到收藏夹

Article Mechanics

A data assimilation model for turbulent flows using continuous adjoint formulation

Chuangxin He et al.

PHYSICS OF FLUIDS (2018)

添加到收藏夹

Article Engineering, Aerospace

On the role and challenges of CFD in the aerospace industry

P. R. Spalart et al.

AERONAUTICAL JOURNAL (2016)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Machine learning strategies for systems with invariance properties

Julia Ling et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2016)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A paradigm for data-driven predictive modeling using field inversion and machine learning

Eric J. Parish et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2016)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Semi-implicit iterative methods for low Mach number turbulent reacting flows: Operator splitting versus approximate factorization

Jonathan F. MacArt et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2016)

添加到收藏夹

Article Mechanics

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance

Julia Ling et al.

JOURNAL OF FLUID MECHANICS (2016)

添加到收藏夹

Article Mechanics

Minimum-dissipation models for large-eddy simulation

Wybe Rozema et al.

PHYSICS OF FLUIDS (2015)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

High order conservative finite difference scheme for variable density low Mach number turbulent flows

Olivier Desjardins et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2008)

添加到收藏夹

Article Meteorology & Atmospheric Sciences

Overview of global data assimilation developments in numerical weather-prediction centres

Florence Rabier

QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.