Efficient modeling of the filtered density function in turbulent sprays using ensemble learning

An efficient ensemble learning approach is used for modeling the filtered density function (FDF) of mixture fraction in turbulent evaporating sprays. This is achieved by implementing the state-of-the-art eXtreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) algorithms. The results show that ensemble learning models achieve a very high accuracy that is comparable to a deep neural network. Computational requirements are, however, much reduced and of the order of those needed for the computation of a conventional beta-FDF. Ensemble learning thus provides a suitable alternative to model FDF statistics and corresponding software for training and a C++ model library are provided.(C) 2021 The Combustion Institute. Published by Elsevier Inc. All rights reserved.

Automated summary

This article discusses the use of an efficient ensemble learning approach to model the filtered density function of mixture fraction in turbulent evaporating sprays. The results show that this approach achieves high accuracy comparable to a deep neural network, while significantly reducing computational requirements. It provides an alternative solution for simulating FDF statistics.