Deep learning-based model for progress variable dissipation rate in turbulent premixed flames

Yellapantula, Shashank; Perry, Barbara; Grout, Ray

doi:10.1016/j.proci.2020.06.205

Cited by 19 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, turbulence in the flame brush is induced by homogeneous isotropic turbulence in one case and shear between the jet and the coflow in the other. Previous studies involving CNNs investigated minor parametric variations in the inlet condition [4], fuel species, and Karlovitz number [1], or turbulence intensity [5,8]. Sub-stantial generalization was observed by Wan et al [7] for a fully connected neural network trained as a surrogate model for the filtered reaction rate on a micromixing database.…”

Section: Comments On the Differences And Similarities Between The Two Configurationsmentioning

confidence: 97%

“…with ρ f the fresh gas density and s L the laminar flame speed, in order to convert Equation (1) to a nondimensional form…”

Section: Pfitzner Source Termmentioning

confidence: 99%

“…To this end, recent studies have successfully used machine learning to train artificial neural networks as SGS models. They have been applied to the modeling of scalar dissipation rates [1], filtered density functions [2,3], wrinkling functions [4,5], and have also been used to predict LES filtered reaction rates directly [6,7] or by deconvolution [8]. These studies have consistently shown that neural networks can outperform physical algebraic models on test cases identical or similar to their training configuration.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling

et al. 2021

View full text Add to dashboard Cite

Deep learning has recently emerged as a successful approach to produce accurate subgrid-scale (SGS) models for Large Eddy Simulations (LES) in combustion. However, the ability of these models to generalize to configurations far from their training distribution is still mainly unexplored, thus impeding their application to practical configurations. In this work, a convolutional neural network (CNN) model for the progress-variable SGS variance field is trained on a canonical premixed turbulent flame and evaluated a priori on a significantly more complex slot burner jet flame. Despite the extensive differences between the two configurations, the CNN generalizes well and outperforms existing algebraic models. Conditions for this successful generalization are discussed, including the effect of the filter size and flame–turbulence interaction parameters. The CNN is then integrated into an analytical reaction rate closure relying on a single-step chemical source term formulation and a presumed beta PDF (probability density function) approach. The proposed closure is able to accurately recover filtered reaction rate values on both training and generalization flames.

show abstract

Section: Comments On the Differences And Similarities Between The Two Configurationsmentioning

confidence: 97%

“…with ρ f the fresh gas density and s L the laminar flame speed, in order to convert Equation (1) to a nondimensional form…”

Section: Pfitzner Source Termmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The dataset considered here is the one used by Yellapantula et al [40] in a turbulent combustion modeling application. In particular, the data was used to learn a model for the filtered dissipation rate of a reaction progress variable C in large eddy simulations of turbulent premixed combustion systems.…”

Section: Datasetmentioning

confidence: 99%

“…With this number of data points, training time may become unreasonable, and data may need to be discarded. Data is often randomly discarded, but more elaborate methods have recently been proposed, such as clustering the data and randomly selecting data from each cluster [38][39][40]. This technique enables the efficient elimination of redundant data points from quiescent or otherwise unimportant regions when the phenomenon of interest is intermittent, effectively attempting an approximate phase-space sampling like the one proposed in the present work.…”

Section: Introductionmentioning

confidence: 99%

Uniform-in-Phase-Space Data Selection with Iterative Normalizing Flows

Hassanaly¹,

Perry²,

Müeller³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Figure 1: Graphical illustration of the data selection method. Starting from a large dataset (top left scatter plot), a reduced uniform-in-phase-space dataset is constructed (right scatter plot). The reduction method relies on the probability map which is iteratively computed (Step 1 and Step 1 correction). An acceptance probability constructed with the probability map is used to accept or reject each data point (Step 2).

show abstract

Deep Convolutional Neural Networks for Subgrid-Scale Flame Wrinkling Modeling

Xing

Lapeyre

2023

Lecture Notes in Energy

View full text Add to dashboard Cite

Subgrid-scale flame wrinkling is a key unclosed quantity for premixed turbulent combustion models in large eddy simulations. Due to the geometrical and multi-scale nature of flame wrinkling, convolutional neural networks are good candidates for data-driven modeling of flame wrinkling. This chapter presents how a deep convolutional neural network called a U-Net is trained to predict the total flame surface density from the resolved progress variable. Supervised training is performed on a database of filtered and downsampled direct numerical simulation fields. In an a priori evaluation on a slot burner configuration, the network outperforms classical dynamic models. In closing, challenges regarding the ability of deep convolutional networks to generalize to unseen configurations and their practical deployment with fluid solvers are discussed.

show abstract

Deep learning-based model for progress variable dissipation rate in turbulent premixed flames

Cited by 19 publications

References 20 publications

Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling

Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling

Uniform-in-Phase-Space Data Selection with Iterative Normalizing Flows

Deep Convolutional Neural Networks for Subgrid-Scale Flame Wrinkling Modeling

Contact Info

Product

Resources

About