Data-driven multifidelity surrogate models for rocket engines injector design

Surrogate models of turbulent diffusive flames could play a strategic role in the design of liquid rocket engine combustion chambers. The present article introduces a method to obtain data-driven surrogate models for coaxial injectors, by leveraging an inductive transfer learning strategy over a U-N...

Full description

Saved in:
Bibliographic Details
Main Authors: Jose Felix Zapata Usandivaras, Michael Bauerheim, Bénédicte Cuenot, Annafederica Urbano
Format: Article
Language:English
Published: Cambridge University Press 2025-01-01
Series:Data-Centric Engineering
Subjects:
Online Access:https://www.cambridge.org/core/product/identifier/S263267362400056X/type/journal_article
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850190408688074752
author Jose Felix Zapata Usandivaras
Michael Bauerheim
Bénédicte Cuenot
Annafederica Urbano
author_facet Jose Felix Zapata Usandivaras
Michael Bauerheim
Bénédicte Cuenot
Annafederica Urbano
author_sort Jose Felix Zapata Usandivaras
collection DOAJ
description Surrogate models of turbulent diffusive flames could play a strategic role in the design of liquid rocket engine combustion chambers. The present article introduces a method to obtain data-driven surrogate models for coaxial injectors, by leveraging an inductive transfer learning strategy over a U-Net with available multifidelity Large Eddy Simulations (LES) data. The resulting models preserve reasonable accuracy while reducing the offline computational cost of data-generation. First, a database of about 100 low-fidelity LES simulations of shear-coaxial injectors, operating with gaseous oxygen and gaseous methane as propellants, has been created. The design of experiments explores three variables: the chamber radius, the recess-length of the oxidizer post, and the mixture ratio. Subsequently, U-Nets were trained upon this dataset to provide reasonable approximations of the temporal-averaged two-dimensional flow field. Despite the fact that neural networks are efficient non-linear data emulators, in purely data-driven approaches their quality is directly impacted by the precision of the data they are trained upon. Thus, a high-fidelity (HF) dataset has been created, made of about 10 simulations, to a much greater cost per sample. The amalgamation of low and HF data during the the transfer-learning process enables the improvement of the surrogate model’s fidelity without excessive additional cost.
format Article
id doaj-art-55afbc5828b94d6eaec60c1007d41a12
institution OA Journals
issn 2632-6736
language English
publishDate 2025-01-01
publisher Cambridge University Press
record_format Article
series Data-Centric Engineering
spelling doaj-art-55afbc5828b94d6eaec60c1007d41a122025-08-20T02:15:17ZengCambridge University PressData-Centric Engineering2632-67362025-01-01610.1017/dce.2024.56Data-driven multifidelity surrogate models for rocket engines injector designJose Felix Zapata Usandivaras0https://orcid.org/0000-0003-4111-8577Michael Bauerheim1https://orcid.org/0000-0001-9550-9077Bénédicte Cuenot2https://orcid.org/0000-0002-7061-3668Annafederica Urbano3https://orcid.org/0000-0002-7576-8685Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, Toulouse, FranceCentre Europén de Recherche et de Formation Avancé en Calcul Scientifique (CERFACS), Toulouse, FranceCentre Europén de Recherche et de Formation Avancé en Calcul Scientifique (CERFACS), Toulouse, FranceFédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, Toulouse, FranceSurrogate models of turbulent diffusive flames could play a strategic role in the design of liquid rocket engine combustion chambers. The present article introduces a method to obtain data-driven surrogate models for coaxial injectors, by leveraging an inductive transfer learning strategy over a U-Net with available multifidelity Large Eddy Simulations (LES) data. The resulting models preserve reasonable accuracy while reducing the offline computational cost of data-generation. First, a database of about 100 low-fidelity LES simulations of shear-coaxial injectors, operating with gaseous oxygen and gaseous methane as propellants, has been created. The design of experiments explores three variables: the chamber radius, the recess-length of the oxidizer post, and the mixture ratio. Subsequently, U-Nets were trained upon this dataset to provide reasonable approximations of the temporal-averaged two-dimensional flow field. Despite the fact that neural networks are efficient non-linear data emulators, in purely data-driven approaches their quality is directly impacted by the precision of the data they are trained upon. Thus, a high-fidelity (HF) dataset has been created, made of about 10 simulations, to a much greater cost per sample. The amalgamation of low and HF data during the the transfer-learning process enables the improvement of the surrogate model’s fidelity without excessive additional cost.https://www.cambridge.org/core/product/identifier/S263267362400056X/type/journal_articleRocket engineshear-coaxial injectorsurrogate modelingtransfer learning
spellingShingle Jose Felix Zapata Usandivaras
Michael Bauerheim
Bénédicte Cuenot
Annafederica Urbano
Data-driven multifidelity surrogate models for rocket engines injector design
Data-Centric Engineering
Rocket engine
shear-coaxial injector
surrogate modeling
transfer learning
title Data-driven multifidelity surrogate models for rocket engines injector design
title_full Data-driven multifidelity surrogate models for rocket engines injector design
title_fullStr Data-driven multifidelity surrogate models for rocket engines injector design
title_full_unstemmed Data-driven multifidelity surrogate models for rocket engines injector design
title_short Data-driven multifidelity surrogate models for rocket engines injector design
title_sort data driven multifidelity surrogate models for rocket engines injector design
topic Rocket engine
shear-coaxial injector
surrogate modeling
transfer learning
url https://www.cambridge.org/core/product/identifier/S263267362400056X/type/journal_article
work_keys_str_mv AT josefelixzapatausandivaras datadrivenmultifidelitysurrogatemodelsforrocketenginesinjectordesign
AT michaelbauerheim datadrivenmultifidelitysurrogatemodelsforrocketenginesinjectordesign
AT benedictecuenot datadrivenmultifidelitysurrogatemodelsforrocketenginesinjectordesign
AT annafedericaurbano datadrivenmultifidelitysurrogatemodelsforrocketenginesinjectordesign