[HTML][HTML] The potential of machine learning methods for separated turbulent flow simulations: Classical versus dynamic methods

S Heinz - Fluids, 2024 - mdpi.com
Feasible and reliable predictions of separated turbulent flows are a requirement to
successfully address the majority of aerospace and wind energy problems. Existing …

A survey on the application of machine learning in turbulent flow simulations

M Majchrzak, K Marciniak-Lukasiak, P Lukasiak - Energies, 2023 - mdpi.com
As early as at the end of the 19th century, shortly after mathematical rules describing fluid
flow—such as the Navier–Stokes equations—were developed, the idea of using them for …

Field inversion and machine learning for turbulence modelling applied to three-dimensional separated flows

J Ho, A West - AIAA aviation 2021 forum, 2021 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2021-2903. vid The Field Inversion and
Machine Learning (FIML) method was applied to augment the k-ω SST turbulence model to …

A high-performance vortex adjustment design for an air-cooling battery thermal management system in electric vehicles

G Zhao, X Wang, M Negnevitsky, C Li, H Zhang… - Batteries, 2023 - mdpi.com
To boost the performance of the air-cooling battery thermal management system, this study
designed a novel vortex adjustment structure for the conventional air-cooling battery pack …

Application of convolutional neural network for efficient turbulence modeling in urban wind field simulation

R Zhao, S Zhong, R You - Physics of Fluids, 2024 - pubs.aip.org
Accurate flow field estimation is crucial for the improvement of outdoor environmental
quality, but computational fluid dynamics (CFD) based on the widely used Reynolds …

Investigation and optimization of thermal management system for lithium-ion battery packs used in EVs and HEVs

G Zhao - 2024 - figshare.utas.edu.au
Transportation electrification has been universally regarded as a critical method to tackle the
more and more severe global warming and climate change issues nowadays. The …

Physically Consistent Resolving Simulations of Turbulent Flows

S Heinz - Entropy, 2024 - mdpi.com
Usually applied simulation methods for turbulent flows as large eddy simulation (LES), wall-
modeled LES (WMLES), and detached eddy simulation (DES) face significant challenges …

[PDF][PDF] Estimating performance bounds of machine-learning Reynolds-stress models via optimal tensor basis expansions

AJ Banko, JK Eaton - Center for Turbulence Research Annual …, 2020 - stanford.edu
Engineering design relies on numerical simulations of turbulent flows to perform analysis
and optimize components. Realistic turn-around times for the ensembles of simulations …

[PDF][PDF] IDENTIFYING INFORMATIVE FEATURES FOR DATA-DRIVEN TURBULENCE MODELLING

J Ho, N Pepper, T Dodwell - researchgate.net
To date most work on applying data-driven techniques to augment the Reynolds Averaged
Navier-Stokes turbulence models have concentrated on the form of correction to the …