Results 11 to 20 of about 21,778,692 (350)
Journal of Marine Science and Engineering, 2023 Engineering and scientific applications are frequently affected by turbulent phenomena, which are associated with a great deal of uncertainty and complexity. Therefore, proper modeling and simulation studies are required.
Yi Zhang, Dapeng Zhang, Haoyu Jiang
doaj +2 more sources
Explaining the physics of transfer learning in data-driven turbulence modeling. [PDF]
PNAS Nexus, 2023 Transfer learning (TL), which enables neural networks (NNs) to generalize out-of-distribution via targeted re-training, is becoming a powerful tool in scientific machine learning (ML) applications such as weather/climate prediction and turbulence ...
Subel A +3 more
europepmc +3 more sources
A unified method of data assimilation and turbulence modeling for separated flows at high Reynolds numbers [PDF]
The Physics of Fluids, 2022 In recent years, machine learning methods represented by deep neural networks (DNN) have been a new paradigm of turbulence modeling. However, in the scenario of high Reynolds numbers, there are still some bottlenecks, including the lack of high-fidelity ...
Zhiyuan Wang, Weiwei Zhang
semanticscholar +1 more source
An interpretable framework of data-driven turbulence modeling using deep neural networks
The Physics of Fluids, 2021 Reynolds-averaged Navier–Stokes simulations represent a cost-effective option for practical engineering applications, but are facing ever-growing demands for more accurate turbulence models.
Chao Jiang +5 more
semanticscholar +1 more source
Feature selection and processing of turbulence modeling based on an artificial neural network [PDF]
The Physics of Fluids, 2020 Data-driven turbulence modeling has been considered an effective method for improving the prediction accuracy of Reynolds-averaged Navier-Stokes equations.
Yuhui Yin +4 more
semanticscholar +1 more source
Turbulence Modeling in the Age of Data [PDF]
Annual Review of Fluid Mechanics, 2018 Data from experiments and direct simulations of turbulence have historically been used to calibrate simple engineering models such as those based on the Reynolds-averaged Navier–Stokes (RANS) equations.
K. Duraisamy, G. Iaccarino, Heng Xiao
semanticscholar +1 more source
From bypass transition to flow control and data-driven turbulence modeling: An input-output viewpoint [PDF]
Annual Review of Fluid Mechanics, 2020 Transient growth and resolvent analyses are routinely used to assess nonasymptotic properties of fluid flows. In particular, resolvent analysis can be interpreted as a special case of viewing flow dynamics as an open system in which free-stream ...
M. Jovanovi'c
semanticscholar +1 more source
A perspective on machine learning methods in turbulence modeling [PDF]
GAMM-Mitteilungen, 2020 This work presents a review of the current state of research in data‐driven turbulence closure modeling. It offers a perspective on the challenges and open issues but also on the advantages and promises of machine learning (ML) methods applied to ...
A. Beck, Marius Kurz
semanticscholar +1 more source
Turbulence Modeling of Iced Wind Turbine Airfoils
Energies, 2022 Icing is a severe problem faced by wind turbines operating in cold climates. It is affected by various fluctuating parameters. Due to ice accretion, a significant drop in the aerodynamic performance of the blades’ airfoils leads to productivity loss in ...
F. Martini +4 more
semanticscholar +1 more source
Machine learning-augmented turbulence modeling for RANS simulations of massively separated flows
, 2021 We combine data assimilation and machine learning to correct the RANS Spalart-Allmaras turbulence model. The final neural-network contribution is a Boussinesq-correction, rather than a turbulent eddy-viscosity adjustment.
P. S. Volpiani +7 more
semanticscholar +1 more source