Large eddy simulation of flow over a circular cylinder with a neural-network-based subgrid-scale model

Kim, Myunghwa; Park, Jonghwan; Choi, Haecheon

doi:10.1017/jfm.2024.154

Cited by 7 publications

(1 citation statement)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only the 'universal' and better-understood small scales are subject to closure modeling. There is significant literature on ML-LES approaches that aim to develop subgrid stress models from high-fidelity data [78][79][80][81][82][83][84][85][86][87][88][89][90][91][92][93][94]. This body of work can be broadly classified into parametric and non-parametric approaches.…”

Section: Machine-learning and Lesmentioning

confidence: 99%

Turbulence closure modeling with machine learning: a foundational physics perspective

Girimaji

2024

New J. Phys.

View full text Add to dashboard Cite

Turbulence closure modeling using machine learning is at an early crossroads. The extraordinary success of machine learning (ML) in a variety of challenging fields had given rise to an expectation of similar transformative advances in the area of turbulence closure modeling. However, by most accounts, the current rate of progress toward accurate and predictive ML-RANS (Reynolds Averaged Navier-Stokes) closure models has been very slow. Upon retrospection, the absence of rapid transformative progress can be attributed to two factors: theunderestimation of the intricacies of turbulence modeling and the overestimation of ML’s ability to capture all features without employing targeted strategies. To pave the way for moremeaningful ML closures tailored to address the nuances of turbulence, this article seeks toreview the foundational flow physics to assess the challenges in the context of data-drivenapproaches. Revisiting analogies with statistical mechanics and stochastic systems, the keyphysical complexities and mathematical limitations are explicated. It is noted that the currentML approaches do not systematically address the inherent limitations of a statistical approachor the inadequacies of the mathematical forms of closure expressions. The study underscoresthe drawbacks of supervised learning-based closures and stresses the importance of a morediscerning ML modeling framework. As ML methods evolve (which is happening at a rapidpace) and our understanding of the turbulence phenomenon improves, the inferences expressedhere should be suitably modified.

show abstract

Section: Machine-learning and Lesmentioning

confidence: 99%

Turbulence closure modeling with machine learning: a foundational physics perspective

Girimaji

2024

New J. Phys.

View full text Add to dashboard Cite

show abstract

Pedestrian-level low-occurrence wind speeds in an urban area predicted by artificial neural networks from fundamental statistics

Li,

Seta,

Ikegaya

2024

Sustainable Cities and Society

View full text Add to dashboard Cite

A recursive neural-network-based subgrid-scale model for large eddy simulation: application to homogeneous isotropic turbulence

Cho,

Park,

Choi

2024

J. Fluid Mech.

View full text Add to dashboard Cite

We introduce a novel recursive procedure to a neural-network-based subgrid-scale (NN-based SGS) model for large eddy simulation (LES) of high-Reynolds-number turbulent flow. This process is designed to allow an SGS model to be applicable to a hierarchy of different grid sizes without requiring expensive filtered direct numerical simulation (DNS) data: (1) train an NN-based SGS model with filtered DNS data at a low Reynolds number; (2) apply the trained SGS model to LES at a higher Reynolds number; (3) update this SGS model with training data augmented with filtered LES (fLES) data, accommodating coarser filter size; (4) apply the updated NN to LES at a further higher Reynolds number; (5) go back to Step (3) until a target (very coarse) filter size divided by the Kolmogorov length scale is reached. We also construct an NN-based SGS model using a dual NN architecture whose outputs are the SGS normal stresses for one NN and the SGS shear stresses for the other NN. The input is composed of the velocity gradient tensor and grid size. Furthermore, for the application of an NN-based SGS model trained with one flow to another flow, we modify the NN by eliminating bias and introducing a leaky rectified linear unit function as an activation function. The present recursive SGS model is applied to forced homogeneous isotropic turbulence (FHIT) and successfully predicts FHIT at high Reynolds numbers. The present model trained from FHIT is also applied to decaying homogeneous isotropic turbulence and shows an excellent prediction performance.

show abstract

Large eddy simulation of flow over a circular cylinder with a neural-network-based subgrid-scale model

Cited by 7 publications

References 80 publications

Turbulence closure modeling with machine learning: a foundational physics perspective

Turbulence closure modeling with machine learning: a foundational physics perspective

Pedestrian-level low-occurrence wind speeds in an urban area predicted by artificial neural networks from fundamental statistics

A recursive neural-network-based subgrid-scale model for large eddy simulation: application to homogeneous isotropic turbulence

Contact Info

Product

Resources

About