Journal ArticleDOI
Progress Variable Variance and Filtered Rate Modelling Using Convolutional Neural Networks and Flamelet Methods
Reads0
Chats0
TLDR
A purely data-driven modelling approach using deep convolutional neural networks is discussed in the context of Large Eddy Simulation (LES) of turbulent premixed flames, demonstrating with success for both the sub-grid scale progress variable variance and the filtered reaction rate.Abstract:
A purely data-driven modelling approach using deep convolutional neural networks is discussed in the context of Large Eddy Simulation (LES) of turbulent premixed flames. The assessment of the method is conducted a priori using direct numerical simulation data. The network has been trained to perform deconvolution on the filtered density and the filtered density-progress variable product, and by doing so obtain estimates of the un-filtered progress variable field. A filtered function of the progress variable can then be approximated on the LES mesh using the deconvoluted field. This new strategy for tackling turbulent combustion modelling is demonstrated with success for both the sub-grid scale progress variable variance and the filtered reaction rate, using flamelet methods, two fundamental ingredients of premixed turbulent combustion modelling.read more
Citations
More filters
Journal ArticleDOI
Chemistry reduction using machine learning trained from non-premixed micro-mixing modeling: Application to DNS of a syngas turbulent oxy-flame with side-wall effects
TL;DR: In this article, a chemistry reduction approach based on machine learning is proposed and applied to direct numerical simulation (DNS) of a turbulent non-premixed syngas oxy-flame interacting with a cooled wall.
Journal ArticleDOI
Combustion machine learning: Principles, progress and prospects
TL;DR: A review of data sources, data-driven techniques, and concepts for combustion machine learning can be found in this article , focusing on interpretability, uncertainty quantification, robustness, consistency, creation and curation of benchmark data, and the augmentation of ML methods with prior combustion domain knowledge.
Journal ArticleDOI
A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
TL;DR: Different data-driven parameterizations for large eddy simulation of two-dimensional turbulence in the a priori settings are investigated and computational gain can be achieved using the intelligent eddy viscosity model that learns eddy Viscosity computed by the DSM instead of subgrid-scale stresses.
Journal ArticleDOI
Sensing the turbulent large-scale motions with their wall signature
TL;DR: In this paper, the authors assess the capability of extended proper orthogonal decomposition (EPOD) and convolutional neural networks (CNNs) to reconstruct large-scale and very-large-scale motions (LSMs and VLSMs respectively) employing wall-shear-stress measurements in wall-bounded turbulent flows.
Machine learning for combustion
TL;DR: In this article, the authors present an overview of studies on the applications of machine learning in combustion science fields over the past several decades, including chemical reactions, combustion modeling, combustion measurement, engine performance prediction and optimization, and fuel design.
References
More filters
Journal ArticleDOI
Large Eddy Simulation of premixed turbulent combustion using approximate deconvolution and explicit flame filtering
Pascale Domingo,Luc Vervisch +1 more
TL;DR: In this paper, an approximate deconvolution and explicit filtering of scalar fields are used to construct a new approach to sub-grid scale modeling in Large Eddy Simulation (LES) of premixed turbulent flames.
Journal ArticleDOI
Regularized deconvolution method for turbulent combustion modeling
Qing Wang,Matthias Ihme +1 more
TL;DR: A priori and a posteriori analyses are conducted to examine RDM as a closure in LES to conclude that the new deconvolution method shows promise in application to combustion LES.
Journal ArticleDOI
DNS and approximate deconvolution as a tool to analyse one-dimensional filtered flame sub-grid scale modelling
Pascale Domingo,Luc Vervisch +1 more
TL;DR: In this paper, a procedure using approximate deconvolution and explicit filtering is discussed to evaluate topology-based sub-grid scale (SGS) combustion models, where a direct numerical simulation (DNS) database is first filtered, then a decon-volution operator constructed from the topologybased SGS model is applied, to compare the approximate three-dimensional fields against the exact ones.
Journal ArticleDOI
A posteriori analysis of numerical errors in subfilter scalar variance modeling for large eddy simulation
TL;DR: In this paper, a coupled direct numerical simulation (DNS)-LES a posteriori method is used to study the role of discretization errors in variance prediction for the two most widely used types of models: algebraic dynamic models and transport equation-based models.
Journal ArticleDOI
Large eddy simulation of a premixed flame with approximate deconvolution modeling
TL;DR: In this paper, a premixed flame which forms in the wake of a flameholder has been selected to examine the subgrid-scale modeling of reaction rate by this new method because a previous plane two-dimensional simulation of this wake flame, using a wrinkling function and artificial flame thickening, had revealed discrepancies when compared with experiment.