Machine learning tabulation of thermochemistry for turbulent dimethyl ether (DME) flames

The present work applies a machine learning tabulation methodology for the thermochemistry of ether (DME), a typical biodiesel fuel, to accelerate the real-time computation of a large-size DME mechanism turbulent non-premixed combustion. This approach is known as the hybrid flamelet/random data and multilayer perceptrons (HFRD-MMLP) method (Ding et al., 2021). The essence of the HFRD-MMLP method in the generation of training data using the HFRD approach, which enhances the capacity of generalisation for the reactive composition space encountered in practical turbulent combustion by using the random to expand the training dataset from laminar flamelets. The MMLP artificial neural networks (ANNs) trained to predict different composition states, aiming to improve the accuracy of ANN predictions. To the effectiveness of the ANNs, they are initially tested on 1-D laminar flame simulations with varying rates. Subsequently, a test is conducted on Sandia non-premixed turbulent DME series flames D and an increasing jet Reynolds Number. The results regarding species mole fractions and temperature show excellent agreement with the direct integration method. The HFRD-MMLP method achieves speed-up of over 16 and 10 for the reaction step, and total computational costs, respectively, in the LES-PDF with the DME mechanism in this work, surpassing the speed-up factors of approximately 12-14, 5 for the reaction step, and total time costs, respectively, in previous works on GRI-1.2 mechanism (Ding et al., 2021) and CH4/H2 (Ding et al., 2022) combustion. This indicates that the HRFD-MMLP is highly effective for mechanisms of large size in reducing the computational cost by avoiding a number of highly stiff ordinary differential equations (ODEs) integration. This approach can be real-time calculations of reaction source terms in methods including Direct Numerical Simulation Probability Density Function (PDF) methods, unsteady flamelet, Conditional Moment Closure (CMC), Mapping Closure (MMC), Linear Eddy Model (LEM), Thickened Flame Model, the Partially Stirred (PaSR) method (as in OpenFOAM) and laminar flame computation.