☆ 4.7 Article

Log-law recovery through reinforcement-learning wall model for large eddy simulation

PHYSICS OF FLUIDS (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 Thermodynamics

Deep reinforcement learning for turbulence modeling in large eddy simulations

Marius Kurz et al.

Summary: In recent years, supervised learning has become the state-of-the-art approach for data-driven turbulence modeling. However, this approach is not feasible for implicitly filtered large eddy simulation (LES) due to the unknown filter form. To address this issue, reinforcement learning is applied to directly interact with the LES environment and incorporate the implicit LES filter into the training process. The trained models demonstrate long-term stability, outperform analytical models, and generalize well to different resolutions and discretizations.

INTERNATIONAL JOURNAL OF HEAT AND FLUID FLOW (2023)

添加到收藏夹

Article Chemistry, Physical

Deep reinforcement learning for turbulent drag reduction in channel flows

Luca Guastoni et al.

Summary: This research introduces a reinforcement learning environment for designing and evaluating control strategies to reduce drag in turbulent fluid flows in a channel. The environment provides a computationally efficient, parallelized, high-fidelity fluid simulation framework that can interface with established RL agent programming interfaces. This allows for testing existing DRL algorithms and advancing our understanding of complex turbulent physical systems.

EUROPEAN PHYSICAL JOURNAL E (2023)

添加到收藏夹

Article Thermodynamics

Validating the design optimisation of ultrasonic flow meters using computational fluid dynamics and surrogate modelling

Mario Javier Rincon et al.

Summary: Computational fluid dynamics is used to predict turbulent flow and perform robust design optimization of domestic ultrasonic flow meters. Surrogate modeling based on Kriging, Latin hypercube sampling, and Bayesian strategies is utilized to ensure high-quality response surface. A novel function is defined to quantify flow meter measurement uncertainty and optimize the pressure drop. The applied methodology improves ultrasonic flow meters and similar internal-flow problems.

INTERNATIONAL JOURNAL OF HEAT AND FLUID FLOW (2023)

添加到收藏夹

Article Physics, Fluids & Plasmas

Survey of machine-learning wall models for large-eddy simulation

Aurelien Vadrot et al.

Summary: This survey investigated the use of data-driven machine learning techniques for wall modeling in large-eddy simulations (LES). Three machine learning wall models were implemented and compared with an equilibrium wall model in LES of half-channel flow at various Reynolds numbers. Results showed promise in data-driven ML wall models, although some models had errors at certain Reynolds numbers.

PHYSICAL REVIEW FLUIDS (2023)

添加到收藏夹

Article Computer Science, Theory & Methods

Constructing Neural Network Based Models for Simulating Dynamical Systems

Christian Legaard et al.

Summary: Dynamical systems are extensively used in natural sciences and engineering disciplines. While simple systems can be described by differential equations derived from fundamental physical laws, more complex systems require data-driven modeling approaches. This article surveys the use of neural networks to construct models of dynamical systems, reviews related literature, identifies significant challenges, and discusses promising research areas.

ACM COMPUTING SURVEYS (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep Reinforcement Learning for Cyber Security

Thanh Thi Nguyen et al.

Summary: This article presents a survey of DRL approaches developed for cyber security, including vital aspects such as DRL-based security methods for cyber-physical systems and autonomous intrusion detection techniques. It also discusses multiagent DRL-based game theory simulations for defense strategies against cyberattacks. Future research directions and extensive discussions on DRL-based cyber security are provided.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

添加到收藏夹

Article Meteorology & Atmospheric Sciences

Logarithmic-Linear Law of the Streamwise Velocity Variance in Stably Stratified Boundary Layers

Xiang I. A. Yang et al.

Summary: This study utilizes Monin-Obukhov similarity theory and Townsend's attached-eddy hypothesis to propose a logarithmic-linear law for the streamwise velocity variance in the surface layer of stably stratified boundary layers. Large-eddy simulations are conducted to test this scaling law under various stratification conditions, and the results strongly support the validity of the logarithmic-linear law in the wake layer of strongly stratified boundary layers due to the suppression of large-scale detached eddies by stable thermal stratification.

BOUNDARY-LAYER METEOROLOGY (2022)

添加到收藏夹

Article Mechanics

A Lagrangian relaxation towards equilibrium wall model for large eddy simulation

Mitchell Fowler et al.

Summary: A large eddy simulation wall model is developed based on a formal interpretation of quasi-equilibrium that governs momentum balance. The model includes a relaxation time scale that ensures self-consistency with assumed quasi-equilibrium conditions. The new approach allows for formally distinguishing between quasi-equilibrium and additional, non-equilibrium contributions to wall stress.

JOURNAL OF FLUID MECHANICS (2022)

添加到收藏夹

Article Physics, Fluids & Plasmas

LES wall modeling for heat transfer at high speeds

Peng E. S. Chen et al.

Physical Review Fluids (2022)

添加到收藏夹

Review Green & Sustainable Science & Technology

Data-driven fluid mechanics of wind farms: A review

Navid Zehtabiyan-Rezaie et al.

Summary: With the increasing number of wind farms, research in wind-farm flow modeling is shifting towards data-driven techniques. However, the complexity of fluid flows in real wind farms poses unique challenges for data-driven modeling, requiring models to be interpretable and have some degree of generalizability.

JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY (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 Mechanics

Data-driven quantification of model-form uncertainty in Reynolds-averaged simulations of wind farms

Ali Eidi et al.

Summary: This study quantifies the model-form uncertainties in RANS simulations using a data-driven machine-learning technique. By applying a two-step feature-selection method and the extreme gradient boosting algorithm, more accurate representations of the Reynolds stress anisotropy are obtained. The proposed framework provides optimal estimation of uncertainty bounds for the RANS-predicted quantities of interest.

PHYSICS OF FLUIDS (2022)

添加到收藏夹

Article Mechanics

Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence

Junhyuk Kim et al.

Summary: The development of a reliable subgrid-scale (SGS) model for large-eddy simulation (LES) is essential for scientific and engineering applications. This study proposes a physics-constrained deep reinforcement learning (DRL) framework for developing a deep neural network-based SGS model for LES of turbulent channel flow. The DRL models are trained based on the local gradient of the filtered velocities, and experiments show that they can produce SGS models consistent with the filtered DNS in various environments.

PHYSICS OF FLUIDS (2022)

添加到收藏夹

Article Physics, Fluids & Plasmas

Progressive, extrapolative machine learning for near-wall turbulence modeling

Yuanwei Bin et al.

Summary: Conventional empirical turbulence modeling progresses gradually, while data-enabled turbulence modeling trains against a group of data containing both simple and complex flows. Criticisms towards data-driven models include their inability to fully preserve empirical facts such as the law of the wall, as well as their limited generalizability to high Reynolds numbers. This paper aims to address these criticisms and demonstrate the compatibility between conventional modeling and data-enabled modeling using the extrapolation theorem and neutral neural network theorem.

PHYSICAL REVIEW FLUIDS (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Dimensionally consistent learning with Buckingham Pi

Joseph Bakarji et al.

Summary: In the absence of governing equations, dimensional analysis is a powerful technique for extracting insights and finding symmetries in physical systems. This study proposes an automated approach that utilizes the structure of available measurement data to discover the dimensionless groups that best collapse the data to a lower dimensional space.

NATURE COMPUTATIONAL SCIENCE (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Enhancing computational fluid dynamics with machine learning

Ricardo Vinuesa et al.

Summary: Machine learning is rapidly integrating into scientific computing, offering significant opportunities for advancing computational fluid dynamics. Key areas of impact include accelerating numerical simulations, enhancing turbulence modeling, and developing simplified models, while potential limitations should also be taken into consideration.

NATURE COMPUTATIONAL SCIENCE (2022)

添加到收藏夹

Article Mechanics

A Bayesian approach to the mean flow in a channel with small but arbitrarily directional system rotation

Xinyi L. D. Huang et al.

Summary: This study investigates the mean flow scaling of wall-bounded flows with small but arbitrarily directional system rotation, establishing a universal function of U+ in terms of y(+), Omega x+, Omega y+, and Omega z+. Direct numerical simulation is utilized to study a Re-tau = 180 channel at various rotation conditions, with a Bayesian approach efficiently sampling the parameter space. The framework provides a method for surrogate modeling in a high-dimensional parameter space at high Reynolds numbers when sampling in a designated parameter space is possible only at a few conditions and at a low Reynolds number.

PHYSICS OF FLUIDS (2021)

添加到收藏夹

Article Engineering, Aerospace

Assessing Wall-Modeled Large-Eddy Simulation for Low-Speed Flows with Heat Transfer

Haosen H. A. Xu et al.

Summary: This study utilizes wall-modeled large-eddy simulation (WMLES) to investigate low-speed turbulent flows in a plane channel, ribbed ducts, and around a film cooling jet. Comparisons are made with direct numerical simulations (DNS) and the performance of different implementations of the equilibrium wall model. The results show that WMLES with first-grid point implementation (FGI) accurately predicts heat transfer at a lower cost than other methods for the flows considered.

AIAA JOURNAL (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Direct shape optimization through deep reinforcement learning

Jonathan Viquerat et al.

Summary: Deep Reinforcement Learning (DRL) has achieved remarkable achievements in various domains within physics and engineering, but there is still much to be explored before the capabilities of these methods are well understood. This paper presents the first application of DRL to direct shape optimization, demonstrating that an artificial neural network trained through DRL can generate optimal shapes autonomously, paving the way to new generic shape optimization strategies in fluid mechanics and other domains where relevant reward functions can be defined.

JOURNAL OF COMPUTATIONAL PHYSICS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Learning dominant physical processes with data-driven balance models

Jared L. Callaham et al.

Summary: Traditional physics-based modeling relies on approximating observed dynamics as a balance between dominant processes within asymptotic regimes, but researchers have proposed a new approach using equation space to identify neglected terms in non-asymptotic regimes. Their data-driven balance models successfully delineate dominant physics in systems like turbulence, combustion, nonlinear optics, geophysical fluids, and neuroscience.

NATURE COMMUNICATIONS (2021)

添加到收藏夹

Article Thermodynamics

Genetic algorithm based topology optimization of heat exchanger fins used in aerospace applications

Bashir S. Mekki et al.

Summary: This study develops a new optimization method combining Genetic Algorithm and Computational Fluid Dynamics for generating optimized fin shapes for heat exchangers used in aerospace applications. The research reveals that as Reynolds number increases, the percent improvement in the optimum relative to the baseline also increases, potentially up to 89%.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2021)

添加到收藏夹

Article Physics, Fluids & Plasmas

Perspectives on machine learning-augmented Reynolds-averaged and large eddy simulation models of turbulence

Karthik Duraisamy

Summary: This paper reviews recent developments in using machine learning to enhance Reynolds-averaged Navier-Stokes (RANS) and large eddy simulation (LES) models of turbulent flows, emphasizing the importance of consistent ML augmentation in modeling. It discusses techniques for promoting model-consistent training and choosing the feature space based on physical and mathematical considerations, highlighting the potential of machine learning in turbulence modeling.

PHYSICAL REVIEW FLUIDS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Highly accurate protein structure prediction with AlphaFold

John Jumper et al.

Summary: Proteins are essential for life, and accurate prediction of their structures is a crucial research problem. Current experimental methods are time-consuming, highlighting the need for accurate computational approaches to address the gap in structural coverage. Despite recent progress, existing methods fall short of atomic accuracy in protein structure prediction.

NATURE (2021)

添加到收藏夹

Article Physics, Fluids & Plasmas

Wall model based on neural networks for LES of turbulent flows over periodic hills

Zhideng Zhou et al.

Summary: A data-driven wall model for turbulent flows over periodic hills is developed using feedforward neural network (FNN) and wall-resolved large-eddy simulation (WRLES) data. The FNN predictions show good agreement with WRLES data for the wall shear stresses, but some discrepancies are observed near the crest of the hill. Overall, the correlation coefficients between FNN predictions and WRLES predictions are larger than 0.7 at most streamwise locations.

PHYSICAL REVIEW FLUIDS (2021)

添加到收藏夹

Article Mechanics

Neuroevolution-enabled adaptation of the Jacobi method for Poisson's equation with density discontinuities

T. R. Xiang et al.

Summary: The study utilizes evolutionary neural network to adjust the Jacobi iterative method to accommodate density discontinuities in the pressure Poisson equation, without the need for labeled data, but simply evaluating the network's performance on the task.

THEORETICAL AND APPLIED MECHANICS LETTERS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Automating turbulence modelling by multi-agent reinforcement learning

Guido Novati et al.

Summary: Researchers have used multi-agent reinforcement learning to improve the discovery of turbulence models, with promising results. This approach can estimate unresolved subgrid-scale physics and generalize well across different grid sizes and flow conditions.

NATURE MACHINE INTELLIGENCE (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 Mechanics

Scaling of velocity fluctuations in statistically unstable boundary-layer flows

Xiang I. A. Yang et al.

JOURNAL OF FLUID MECHANICS (2020)

添加到收藏夹

Review Mechanics

Active flow control using machine learning: A brief review

Feng Ren et al.

JOURNAL OF HYDRODYNAMICS (2020)

添加到收藏夹

Article Mechanics

Machine-learning-based reduced-order modeling for unsteady flows around bluff bodies of various shapes

Kazuto Hasegawa et al.

THEORETICAL AND COMPUTATIONAL FLUID DYNAMICS (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 Physics, Fluids & Plasmas

Predictive large-eddy-simulation wall modeling via physics-informed neural networks

X. I. A. Yang et al.

PHYSICAL REVIEW FLUIDS (2019)

添加到收藏夹

Article Thermodynamics

Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates

Corentin J. Lapeyre et al.

COMBUSTION AND FLAME (2019)

添加到收藏夹

Article Mechanics

Sub-grid scale model classification and blending through deep learning

Romit Maulik et al.

JOURNAL OF FLUID MECHANICS (2019)

添加到收藏夹

Article Mechanics

Wall-modeled large-eddy simulations of spanwise rotating turbulent channels-Comparing a physics-based approach and a data-based approach

Xinyi L. D. Huang et al.

PHYSICS OF FLUIDS (2019)

添加到收藏夹

Article Mechanics

Dynamic slip wall model for large-eddy simulation

Hyunji Jane Bae et al.

JOURNAL OF FLUID MECHANICS (2019)

添加到收藏夹

Article Mechanics

Recent progress in augmenting turbulence models with physics-informed machine learning

Xinlei Zhang et al.

JOURNAL OF HYDRODYNAMICS (2019)

添加到收藏夹

Article Mechanics

Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework

Zhiwen Deng et al.

PHYSICS OF FLUIDS (2019)

添加到收藏夹

Review Mechanics

Some Recent Developments in Turbulence Closure Modeling

Paul A. Durbin

ANNUAL REVIEW OF FLUID MECHANICS, VOL 50 (2018)

添加到收藏夹

Article Mechanics

A hierarchical random additive model for passive scalars in wall-bounded flows at high Reynolds numbers

Xiang I. A. Yang et al.

JOURNAL OF FLUID MECHANICS (2018)

添加到收藏夹

Article Multidisciplinary Sciences

Efficient collective swimming by harnessing vortices through deep reinforcement learning

Siddhartha Verma et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2018)

添加到收藏夹

Article Mechanics

A semi-locally scaled eddy viscosity formulation for LES wall models and flows at high speeds

Xiang I. A. Yang et al.

THEORETICAL AND COMPUTATIONAL FLUID DYNAMICS (2018)

添加到收藏夹

Article Physics, Fluids & Plasmas

Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework

Jin-Long Wu et al.

PHYSICAL REVIEW FLUIDS (2018)

添加到收藏夹

Article Multidisciplinary Sciences

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

David Silver et al.

SCIENCE (2018)

添加到收藏夹

Article Mechanics

Wall shear stress fluctuations: Mixed scaling and their effects on velocity fluctuations in a turbulent boundary layer

Carlos Diaz-Daniel et al.

PHYSICS OF FLUIDS (2017)

添加到收藏夹

Article Physics, Fluids & Plasmas

Log-layer mismatch and modeling of the fluctuating wall stress in wall-modeled large-eddy simulations

Xiang I. A. Yang et al.

PHYSICAL REVIEW FLUIDS (2017)

添加到收藏夹

Article Meteorology & Atmospheric Sciences

Large-Eddy Simulation of Thermally Stratified Atmospheric Boundary-Layer Flow Using a Minimum Dissipation Model

Mahdi Abkar et al.

BOUNDARY-LAYER METEOROLOGY (2017)

添加到收藏夹

Article Mechanics

A Web services accessible database of turbulent channel flow and its use for testing a new integral wall model for LES

J. Graham et al.

JOURNAL OF TURBULENCE (2016)

添加到收藏夹

Article Physics, Fluids & Plasmas

Minimum-dissipation scalar transport model for large-eddy simulation of turbulent flows

Mahdi Abkar et al.

PHYSICAL REVIEW FLUIDS (2016)

添加到收藏夹

Article Mechanics

Direct numerical simulation of turbulent channel flow up to Reτ ≈ 5200

Myoungkyu Lee et al.

JOURNAL OF FLUID MECHANICS (2015)

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 Mechanics

Integral wall model for large eddy simulations of wall-bounded turbulent flows

X. I. A. Yang et al.

PHYSICS OF FLUIDS (2015)

添加到收藏夹

Article Mechanics

Influence of atmospheric stability on wind-turbine wakes: A large-eddy simulation study

Mahdi Abkar et al.

PHYSICS OF FLUIDS (2015)

添加到收藏夹

Article Mechanics

A dynamic slip boundary condition for wall-modeled large-eddy simulation

S. T. Bose et al.

PHYSICS OF FLUIDS (2014)

添加到收藏夹

Article Mechanics

An improved dynamic non-equilibrium wall-model for large eddy simulation

George Ilhwan Park et al.

PHYSICS OF FLUIDS (2014)

添加到收藏夹

Review Robotics

Reinforcement learning in robotics: A survey

Jens Kober et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2013)

添加到收藏夹

Article Mechanics

On the logarithmic region in wall turbulence

Ivan Marusic et al.

JOURNAL OF FLUID MECHANICS (2013)

添加到收藏夹

Article Mechanics

A new boundary condition for large-eddy simulation of boundary-layer flow over surface roughness transitions

Mahdi Abkar et al.

JOURNAL OF TURBULENCE (2012)

添加到收藏夹

Article Physics, Multidisciplinary

Turbulent Pipe Flow at Extreme Reynolds Numbers

M. Hultmark et al.

PHYSICAL REVIEW LETTERS (2012)

添加到收藏夹

Article Mechanics

Wall-modeling in large eddy simulation: Length scales, grid resolution, and accuracy

Soshi Kawai et al.

PHYSICS OF FLUIDS (2012)

添加到收藏夹

Article Mechanics

Variations of von Karman coefficient in canonical flows

Hassan M. Nagib et al.

PHYSICS OF FLUIDS (2008)

添加到收藏夹

Article Mechanics

A scale-dependent Lagrangian dynamic model for large eddy simulation of complex turbulent flows

E Bou-Zeid et al.

PHYSICS OF FLUIDS (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.