Data-driven modeling of large-eddy simulations for fuel injector design

P. J. Milan, S. Mondal, R. Torelli, B. Lusch, R. Maulik, G. M. Magnotti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

The objective of this work is to develop an efficient emulator framework using modern machine learning techniques to predict spatiotemporally evolving flow dynamics for design exploration. This emulation framework encompasses autoencoders for nonlinear dimensionality reduction, deep neural networks for regression and predictive modeling, and a reconstruction algorithm for recovery of the flowfields. As a demonstration case, the turbulent multiphase flow development in a side-oriented single-hole diesel injector is considered for a wide range of design parameters, fuel properties, and operating conditions. The prediction accuracy of the flow features for new design settings is assessed, and the efficiency of the proposed emulator is evaluated.

Original languageEnglish (US)
Title of host publicationAIAA Scitech 2021 Forum
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
Pages1-15
Number of pages15
ISBN (Print)9781624106095
StatePublished - 2021
EventAIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2021 - Virtual, Online
Duration: Jan 11 2021Jan 15 2021

Publication series

NameAIAA Scitech 2021 Forum

Conference

ConferenceAIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2021
CityVirtual, Online
Period1/11/211/15/21

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering

Cite this