This paper presents the development and application of a Transformer deep-learning model to fluid–structure problems induced by shock-turbulent boundary layer interaction. The model was trained on data from experiments conducted at a hypersonic wind tunnel under flow conditions that allowed for a Mach number of 5.3 and a Reynolds number of /m. The shock-wave turbulent boundary layer interaction occurred over an elastic panel. The Transformer was trained using panel deformation measurements taken at different probe locations and the pressure in the cavity beneath the panel. The trained Transformer was subsequently applied to unseen data corresponding to various mean cavity pressures and panel deformations. The capability of the Transformer to capture aeroelastic trends is promising, with interpolation accuracy shown to depend on the volume of data used in training and the location to which the model is applied. The practical implications of this study for aeroelastic research are significant, offering new insights and potential solutions to real-world aeroelastic challenges.
Skip Nav Destination
High-speed fluid–structure interaction predictions using a deep learning transformer architecture
,
,
,
,
,
,
,
Article navigation
May 2025
Research Article|
May 12 2025
High-speed fluid–structure interaction predictions using a deep learning transformer architecture
Available to Purchase
Dimitris Drikakis (Δημήτρης Δρικάκης)
;
Dimitris Drikakis (Δημήτρης Δρικάκης)
a)
(Conceptualization, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Resources, Supervision, Writing – original draft, Writing – review & editing)
1
Institute for Advanced Modelling and Simulation, University of Nicosia
, Nicosia CY-2417, Cyprus
a)Author to whom correspondence should be addressed: [email protected]
Search for other works by this author on:
Daryl Fung (洪日興)
;
Daryl Fung (洪日興)
(Conceptualization, Data curation, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft, Writing – review & editing)
1
Institute for Advanced Modelling and Simulation, University of Nicosia
, Nicosia CY-2417, Cyprus
Search for other works by this author on:
Ioannis William Kokkinakis (lωάѵѵης Κοκκιѵάκης)
;
Ioannis William Kokkinakis (lωάѵѵης Κοκκιѵάκης)
(Data curation, Methodology, Visualization, Writing – original draft, Writing – review & editing)
1
Institute for Advanced Modelling and Simulation, University of Nicosia
, Nicosia CY-2417, Cyprus
Search for other works by this author on:
S. Michael Spottswood
;
S. Michael Spottswood
(Conceptualization, Formal analysis, Funding acquisition, Methodology, Project administration, Supervision, Writing – review & editing)
2
Air Force Research Laboratory
, Wright Patterson AFB, Ohio 45433-7402, USA
Search for other works by this author on:
Kirk R. Brouwer
;
Kirk R. Brouwer
(Conceptualization, Formal analysis, Investigation, Writing – review & editing)
2
Air Force Research Laboratory
, Wright Patterson AFB, Ohio 45433-7402, USA
Search for other works by this author on:
Zachary B. Riley;
Zachary B. Riley
(Conceptualization, Formal analysis, Investigation, Writing – original draft, Writing – review & editing)
2
Air Force Research Laboratory
, Wright Patterson AFB, Ohio 45433-7402, USA
Search for other works by this author on:
Dennis Daub
;
Dennis Daub
(Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Resources, Visualization, Writing – original draft, Writing – review & editing)
3
Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), Institute of Aerodynamics and Flow Technology, Supersonic and Hypersonic Technologies Department
, Linder Höhe, 51147 Köln, Germany
Search for other works by this author on:
Ali Gülhan
Ali Gülhan
(Conceptualization, Investigation, Project administration, Resources, Supervision, Writing – review & editing)
3
Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), Institute of Aerodynamics and Flow Technology, Supersonic and Hypersonic Technologies Department
, Linder Höhe, 51147 Köln, Germany
Search for other works by this author on:
S. Michael Spottswood
2
Kirk R. Brouwer
2
Zachary B. Riley
2
Dennis Daub
3
Ali Gülhan
3
1
Institute for Advanced Modelling and Simulation, University of Nicosia
, Nicosia CY-2417, Cyprus
2
Air Force Research Laboratory
, Wright Patterson AFB, Ohio 45433-7402, USA
3
Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), Institute of Aerodynamics and Flow Technology, Supersonic and Hypersonic Technologies Department
, Linder Höhe, 51147 Köln, Germany
a)Author to whom correspondence should be addressed: [email protected]
Physics of Fluids 37, 056105 (2025)
Article history
Received:
February 27 2025
Accepted:
April 10 2025
Citation
Dimitris Drikakis, Daryl Fung, Ioannis William Kokkinakis, S. Michael Spottswood, Kirk R. Brouwer, Zachary B. Riley, Dennis Daub, Ali Gülhan; High-speed fluid–structure interaction predictions using a deep learning transformer architecture. Physics of Fluids 1 May 2025; 37 (5): 056105. https://doi.org/10.1063/5.0267973
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
160
Views
Citing articles via
Phase behavior of Cacio e Pepe sauce
G. Bartolucci, D. M. Busiello, et al.
Chinese Academy of Science Journal Ranking System (2015–2023)
Cruz Y. Li (李雨桐), 李雨桐, et al.
Direct numerical simulations of immiscible two-phase flow in rough fractures: Impact of wetting film resolution
R. Krishna, Y. Méheust, et al.
Related Content
Self-supervised transformers for turbulent flow time series
Physics of Fluids (June 2024)
Generalizability of transformer-based deep learning for multidimensional turbulent flow data
Physics of Fluids (February 2024)
Aeroelastic response of a thin panel excited by a separated shock–boundary layer interaction
Physics of Fluids (December 2023)
Informers for turbulent time series data forecast
Physics of Fluids (January 2025)
A deep learning super-resolution model for turbulent image upscaling and its application to shock wave–boundary layer interaction
Physics of Fluids (February 2024)