A robust autoregressive long-term spatiotemporal forecasting framework for surrogate-based turbulent combustion modeling via deep learning

This paper systematically develops a high-fidelity turbulent combustion surrogate model using deep learning.We construct a surrogate model to simulate the turbulent combustion process in real time,based on a state-ofthe-art spatiotemporal forecasting neural network.To address the issue of shifted distribution in autoregressive long-term prediction,two training techniques are proposed:unrolled training and injecting noise training.These techniques significantly improve the stability and robustness of the model.Two datasets of turbulent combustion in a combustor with cavity and a vitiated co-flow burner(Cabra burner)have been generated for model validation.The effects of model architecture,unrolled time,noise amplitude,and training dataset size on the long-term predictive performance are explored.The well-trained model can be applicable to new cases by extrapolation and give spatially and temporally consistent results in long-term predictions for turbulent reacting flows that are highly unsteady.

Thermodynamic Nonequilibrium Features in Binary Diffusion

Diffusion is a ubiquitous physical phenomenon where thermodynamic nonequilibrium effects(TNEs) are outstanding issues. In this work, we employ the discrete Boltzmann method to investigate the TNEs in the dynamic process of binary diffusion. The main features of the distribution function in velocity space are recovered and discussed.It is found that, with the decreasing gradients of macroscopic quantities(such as density, concentration, velocity, etc.),both the local and global TNEs decrease with the time but increase with the relaxation time in a power law, respectively.