End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape Optimization

Aerodynamic shape design optimization faces challenges due to the computational demands and the vast design space, limiting its practicality and scalability. While progress has been made in subsonic and transonic regimes, the real-time optimization for supersonic conditions remains unexplored. To br...

Full description

Saved in:
Bibliographic Details
Main Authors: Diogo Pereira, Frederico Afonso, Fernando Lau
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Aerospace
Subjects:
Online Access:https://www.mdpi.com/2226-4310/12/5/389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850127537711087616
author Diogo Pereira
Frederico Afonso
Fernando Lau
author_facet Diogo Pereira
Frederico Afonso
Fernando Lau
author_sort Diogo Pereira
collection DOAJ
description Aerodynamic shape design optimization faces challenges due to the computational demands and the vast design space, limiting its practicality and scalability. While progress has been made in subsonic and transonic regimes, the real-time optimization for supersonic conditions remains unexplored. To bridge this gap, this work exploits knowledge learned from subsonic and transonic real-world data and introduces a rapid optimization framework tailored for the supersonic regime. A novel end-to-end multitask Convolutional Neural Network is proposed to predict the aerodynamic coefficients of an airfoil shape, extracting global and local features directly from the geometry. The surrogate model is thoroughly examined and validated, including an analysis of model explainability. The surrogate model achieves on par results with the state-of-the-art, with relative errors in aerodynamic coefficient predictions below 1.7%. Furthermore, a surrogate-based optimization strategy integrates the surrogate model with a Generative Adversarial Network to generate realistic airfoil shapes, thereby reducing the design space to a low-dimensional representation. This approach provides a robust solution that accelerates the optimization routine by over 3000 times when compared to simulation-based methods while achieving a deviation of less than 1.9% from their optimum performance. Overall, this work strikes a balance between efficiency and effectiveness without compromising reliability.
format Article
id doaj-art-3afe0622a13d47199ec64a6462e6822e
institution OA Journals
issn 2226-4310
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Aerospace
spelling doaj-art-3afe0622a13d47199ec64a6462e6822e2025-08-20T02:33:39ZengMDPI AGAerospace2226-43102025-04-0112538910.3390/aerospace12050389End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape OptimizationDiogo Pereira0Frederico Afonso1Fernando Lau2Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisboa, PortugalIDMEC, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisboa, PortugalIDMEC, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisboa, PortugalAerodynamic shape design optimization faces challenges due to the computational demands and the vast design space, limiting its practicality and scalability. While progress has been made in subsonic and transonic regimes, the real-time optimization for supersonic conditions remains unexplored. To bridge this gap, this work exploits knowledge learned from subsonic and transonic real-world data and introduces a rapid optimization framework tailored for the supersonic regime. A novel end-to-end multitask Convolutional Neural Network is proposed to predict the aerodynamic coefficients of an airfoil shape, extracting global and local features directly from the geometry. The surrogate model is thoroughly examined and validated, including an analysis of model explainability. The surrogate model achieves on par results with the state-of-the-art, with relative errors in aerodynamic coefficient predictions below 1.7%. Furthermore, a surrogate-based optimization strategy integrates the surrogate model with a Generative Adversarial Network to generate realistic airfoil shapes, thereby reducing the design space to a low-dimensional representation. This approach provides a robust solution that accelerates the optimization routine by over 3000 times when compared to simulation-based methods while achieving a deviation of less than 1.9% from their optimum performance. Overall, this work strikes a balance between efficiency and effectiveness without compromising reliability.https://www.mdpi.com/2226-4310/12/5/389aerodynamic shape optimizationsurrogate modelingdeep learningconvolutional neural networksgenerative adversarial networks
spellingShingle Diogo Pereira
Frederico Afonso
Fernando Lau
End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape Optimization
Aerospace
aerodynamic shape optimization
surrogate modeling
deep learning
convolutional neural networks
generative adversarial networks
title End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape Optimization
title_full End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape Optimization
title_fullStr End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape Optimization
title_full_unstemmed End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape Optimization
title_short End-to-End Deep-Learning-Based Surrogate Modeling for Supersonic Airfoil Shape Optimization
title_sort end to end deep learning based surrogate modeling for supersonic airfoil shape optimization
topic aerodynamic shape optimization
surrogate modeling
deep learning
convolutional neural networks
generative adversarial networks
url https://www.mdpi.com/2226-4310/12/5/389
work_keys_str_mv AT diogopereira endtoenddeeplearningbasedsurrogatemodelingforsupersonicairfoilshapeoptimization
AT fredericoafonso endtoenddeeplearningbasedsurrogatemodelingforsupersonicairfoilshapeoptimization
AT fernandolau endtoenddeeplearningbasedsurrogatemodelingforsupersonicairfoilshapeoptimization