Large eddy simulation with flamelet progress variable approach combined with artificial neural network acceleration

Angelilli, Lorenzo; Ciottoli, Pietro Paolo; Galassi, Riccardo Malpica; Pérez, Francisco E. Hernández; Soldan, Mattia; Lu, Zhen; Valorani, Mauro; Im, Hong G.

doi:10.2514/6.2021-0412

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, as also mathematically proved in Aggarwal et al (2001) and Verleysen et al (2003), as the number of dimensions increases, the concepts of distance and nearest neighbors both lose meaningfulness. Thus, Artificial Neural Networks (ANNs) represent a valid alternative to improve the classification efficiency when dealing with high-dimensional spaces, and they have also already been successfully exploited for combustion and chemical kinetics applications (Christo et al, 1995(Christo et al, , 1996Blasco et al, 1998;Hao et al, 2001;Galindo et al, 2005;Chen et al, 2020;Dalakoti et al, 2020;Debiagi et al, 2020;Angelilli et al, 2021). ANNs have also been introduced in the context of Large Eddy Simulations of reactive flows in Ihme et al (2009), and the comparison with conventional tabulation techniques for chemistry representation led to excellent results in terms of accuracy.…”

Section: Introductionmentioning

confidence: 99%

Feature extraction and artificial neural networks for the on-the-fly classification of high-dimensional thermochemical spaces in adaptive-chemistry simulations

D’Alessio

Cuoci

Parente

2021

DCE

View full text Add to dashboard Cite

The integration of Artificial Neural Networks (ANNs) and Feature Extraction (FE) in the context of the Sample- Partitioning Adaptive Reduced Chemistry approach was investigated in this work, to increase the on-the-fly classification accuracy for very large thermochemical states. The proposed methodology was firstly compared with an on-the-fly classifier based on the Principal Component Analysis reconstruction error, as well as with a standard ANN (s-ANN) classifier, operating on the full thermochemical space, for the adaptive simulation of a steady laminar flame fed with a nitrogen-diluted stream of n-heptane in air. The numerical simulations were carried out with a kinetic mechanism accounting for 172 species and 6,067 reactions, which includes the chemistry of Polycyclic Aromatic Hydrocarbons (PAHs) up to C $ {}_{20} $ . Among all the aforementioned classifiers, the one exploiting the combination of an FE step with ANN proved to be more efficient for the classification of high-dimensional spaces, leading to a higher speed-up factor and a higher accuracy of the adaptive simulation in the description of the PAH and soot-precursor chemistry. Finally, the investigation of the classifier’s performances was also extended to flames with different boundary conditions with respect to the training one, obtained imposing a higher Reynolds number or time-dependent sinusoidal perturbations. Satisfying results were observed on all the test flames.

show abstract