Generative artificial intelligence and hybrid models to accelerate LES in reactive flows: Application to hydrogen/methane combustion

TL;DR

This paper presents a novel hybrid generative machine learning framework combining modal decomposition and neural networks to accelerate large eddy simulations of hydrogen-methane combustion, achieving significant speed-ups while maintaining accuracy.

Contribution

It introduces the first hybrid generative model for reactive flow prediction, integrating POD and deep learning to significantly speed up LES in combustion simulations.

Findings

Achieved speed-up ratios of 121 and 845 compared to LES.

Demonstrated good agreement between predicted and LES data.

Validated the approach on a hydrogen-methane jet-in-hot-coflow burner.

Abstract

With increasing emphasis on carbon neutrality, accurate and efficient combustion prediction has become essential for the design and optimization of new generation combustion systems. This study established a computational framework by combining large eddy simulation (LES) with a generative machine learning approach which integrates modal decomposition and neural network, enabling fast prediction of hydrogen-methane combustion. A canonical jet-in-hot-coflow burner was selected as the benchmark configuration. LES was performed using eddy dissipation concept model in conjunction with a 17-species and 58-step skeletal mechanism. Reasonable agreement between LES results and experimental data was obtained for temperature and species mass fraction, confirming the accuracy of the present LES results. Flow characteristics and flame structures were analyzed, providing a reference for choosing parameters in prediction. Proper orthogonal decomposition (POD) was used to extract dominant flow features, and a hybrid autoregressive model, which combines modal decomposition with a deep learning (POD-DL) was constructed to forecast the temporal evolution of the combustion field. Comparison between the predicted results and LES data, including instantaneous contours, radial distributions, histogram and relative root mean square error, demonstrated a reasonable agreement. The main complexity lies in capturing the chaotic and fine-scale structures inherent to turbulent combustion. To the authors' knowledge, this is the first application of such a hybrid generative model to reactive flow prediction, representing an important step toward using data-driven surrogates to accelerate CFD simulations in combustion research. The proposed approach achieves speed-up ratios of 121 and 845 relative to LES for two tested cases. The implementation will be integrated into the upcoming release of the ModelFLOWs-app.