A physics-constrained machine-learning sub-grid-scale modeling approach for turbulent premixed flames
Abstract
A physics-embedded training framework is used to close the sub-grid-scale dynamics of turbulent premixed flames. The trained model augments the resolved flow equations and is trained to match its predicted flow field to trusted data. An end-to-end optimization of the coupled resolved equations and embedded model leads to a model that is robust and effective for a freely propagating premixed flame in turbulence, modeled by a single-species, single-step, and irreversible chemical reaction. Important constraints are built into the training formulation for conservation, scalar boundedness, and equivariance. The model is scaled based on the residual of the resolved flow equations to focus its influence where the closure is needed. It outperforms other cases considered --- no-model, dynamic closure, and the same machine learning model trained directly to fit the residual data --- for a long-time simulation, correcting the turbulence dissipation and flame kinematics. Finally, it is shown how the prediction-based training better informs the model than the precise residual data.
Related
- Physics-Constrained Symbolic Regression for Mean-Velocity and Mixing-Length Scaling in Zero-Pressure-Gradient Turbulent Boundary Layers
- Physics-constrained neural networks for surrogate modeling of lossless periodic structures
- Role of flame localization in wavemaker regions on the suppression of combustion instability in turbulent partially-premixed methane flames
- Direct numerical simulation of NOx formation in turbulent lean premixed hydrogen-air flames under engine-relevant conditions
- Experimental assessment of a scalar-dissipation-rate sub-grid-scale closure for Large Eddy Simulation of turbulent premixed flames
BibTeX
@misc{suh2026physicsconstrained,
title = {{A physics-constrained machine-learning sub-grid-scale modeling approach for turbulent premixed flames}},
author = {Seung Won Suh and Jonathan F. MacArt and Luke N. Olson and Jonathan B. Freund},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28525},
eprint = {2608.28525},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28525},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - A physics-constrained machine-learning sub-grid-scale modeling approach for turbulent premixed flames
AU - Seung Won Suh
AU - Jonathan F. MacArt
AU - Luke N. Olson
AU - Jonathan B. Freund
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.28525
UR - https://arxiv.org/abs/2608.28525
AB - A physics-embedded training framework is used to close the sub-grid-scale dynamics of turbulent premixed flames. The trained model augments the resolved flow equations and is trained to match its predicted flow field to trusted data. An end-to-end optimization of the coupled resolved equations and embedded model leads to a model that is robust and effective for a freely propagating premixed flame in turbulence, modeled by a single-species, single-step, and irreversible chemical reaction. Important constraints are built into the training formulation for conservation, scalar boundedness, and equivariance. The model is scaled based on the residual of the resolved flow equations to focus its influence where the closure is needed. It outperforms other cases considered --- no-model, dynamic closure, and the same machine learning model trained directly to fit the residual data --- for a long-time simulation, correcting the turbulence dissipation and flame kinematics. Finally, it is shown how the prediction-based training better informs the model than the precise residual data.
ER -