Three-dimensional residual convolutional neural networks for turbulence modeling in large-eddy simulations of partially premixed swirl flames
Authors:
- Zhentao PangZPZhentao Pang
- Anxiong LiuALAnxiong Liu
- Kai LiuKLKai Liu
- Yuzhou ChengYCYuzhou Cheng
- Kun LuoKun Luo
- Jianren FanJFJianren Fan
- 1 July 2025
- journal article
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (7)
Abstract
The partially premixed swirl flames with pressure expansion, abrupt density reduction, and stiff viscosity increases are inadequately captured by traditional eddy-viscosity models or conventional data-driven approaches such as fully connected neural networks. In this work, an advanced three-dimensional residual convolutional neural network (3D-ResCNN) is developed to accurately model subgrid-scale (SGS) stresses and scalar fluxes in such reacting flows. The 3D-ResCNN utilizes spatial inputs comprising first-order velocity and scalar gradients across local and adjacent grid points to effectively capture the SGS dynamics of turbulent combustion, eliminating the reliance on eddy-viscosity assumptions. In the a priori test, the 3D-ResCNN outperformed traditional models, including the Dynamic Smagorinsky Model and Velocity Gradient Model, achieve higher correlation coefficients for SGS variable predictions. Posteriori tests further validated its applicability and robustness within LES codes, demonstrating its effectiveness through time-averaged statistical results, velocity fluctuation analysis, and scalar probability density functions. This research highlights the advantages of integrating spatial inputs with the 3D-ResCNN architecture to enhance the accuracy, generalizability, and predictive capability of SGS turbulence models in LES for turbulent combustion.Keywords
Funding Information
- National Natural Science Foundation of China (NO. 52236002)
This publication has 31 references indexed in Scilit:
- Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LESPhysica D: Nonlinear Phenomena, 2022
- The effects of swirling partially premixed flame on scaled kinetic energy transport in a gas turbine-like combustorProceedings of the Combustion Institute, 2022
- Spatial artificial neural network model for subgrid-scale stress and heat flux of compressible turbulenceTheoretical and Applied Mechanics Letters, 2020
- Deep neural networks for data-driven LES closure modelsJournal of Computational Physics, 2019
- Structural subgrid-scale modeling for large-eddy simulation: A reviewActa Mechanica Sinica, 2016
- A-priori direct numerical simulation assessment of sub-grid scale stress tensor closures for turbulent premixed combustionComputers & Fluids, 2015
- Large-eddy simulation: Past, present and the futureChinese Journal of Aeronautics, 2015
- A two-step chemical scheme for kerosene–air premixed flamesCombustion and Flame, 2010
- High order conservative finite difference scheme for variable density low Mach number turbulent flowsJournal of Computational Physics, 2008
- Subgrid-Scale Models for Compressible Large-Eddy SimulationsTheoretical and Computational Fluid Dynamics, 2000