Abstract
In this chapter we demonstrate how supervised deep learning techniques can be used to construct models for the filtered progress variable source term necessary for large eddy simulation (LES). The source data for the model is a direct numerical simulation (DNS) of a reacting flow in a low swirl burner configuration. Filtered quantities taken from the DNS data are used to train a deep neural network (DNN)-based model. An efficient data sampling strategy was devised to ensure that a uniform representation of all the states observed in the filtered DNS data are equally present in the training dataset.A-priori testing of the DNN-based model highlights the representative power of DNN to accurately reproduce the filtered reaction progress variable source term over a range of scales and various flame regimes as seen in an industrial burner.
Original language | American English |
---|---|
Title of host publication | Data Analysis for Direct Numerical Simulations of Turbulent Combustion |
Subtitle of host publication | From Equation-Based Analysis to Machine Learning |
Editors | H. Pitsch, A. Attili |
Publisher | Springer International Publishing |
Pages | 273-292 |
Number of pages | 20 |
ISBN (Electronic) | 9783030447182 |
ISBN (Print) | 9783030447175 |
DOIs | |
State | Published - 2020 |
Bibliographical note
Publisher Copyright:© Springer Nature Switzerland AG 2020.
NREL Publication Number
- NREL/CH-2C00-74457
Keywords
- combustion LES models
- machine learning
- reacting direct numerical simulation