Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and Aeroelasticity

Kolmogorov–Arnold Networks (KANs) are a recent development in machine learning, offering strong functional representation capabilities, enhanced interpretability, and reduced parameter complexity. Leveraging these advantages, this paper proposes a KAN-based reduced-order model (ROM) for unsteady aer...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuchen Zhang, Han Tang, Lianyi Wei, Guannan Zheng, Guowei Yang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/5820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129856556171264
author Yuchen Zhang
Han Tang
Lianyi Wei
Guannan Zheng
Guowei Yang
author_facet Yuchen Zhang
Han Tang
Lianyi Wei
Guannan Zheng
Guowei Yang
author_sort Yuchen Zhang
collection DOAJ
description Kolmogorov–Arnold Networks (KANs) are a recent development in machine learning, offering strong functional representation capabilities, enhanced interpretability, and reduced parameter complexity. Leveraging these advantages, this paper proposes a KAN-based reduced-order model (ROM) for unsteady aerodynamics and aeroelasticity. To effectively capture temporal dependencies inherent in nonlinear unsteady flow phenomena, an architecture termed Kolmogorov–Arnold Gated Recurrent Network (KAGRN) is introduced. By incorporating a recurrent structure and a gating mechanism, the proposed model effectively captures time-delay effects and enables the selective control and preservation of long-term temporal dependencies. This architecture provides high predictive accuracy, good generalization capability, and fast prediction speed. The performance of the model is evaluated using simulations of the NACA (National Advisory Committee for Aeronautics) 64A010 airfoil undergoing harmonic motion and limit cycle oscillations in transonic flow conditions. Results demonstrate that the proposed model can not only accurately and efficiently predict unsteady aerodynamic coefficients, but also effectively capture nonlinear aeroelastic responses.
format Article
id doaj-art-7abf0bd68188429ab7091459a67adfc8
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-7abf0bd68188429ab7091459a67adfc82025-08-20T02:32:50ZengMDPI AGApplied Sciences2076-34172025-05-011511582010.3390/app15115820Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and AeroelasticityYuchen Zhang0Han Tang1Lianyi Wei2Guannan Zheng3Guowei Yang4Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Mechanics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Mechanics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Mechanics, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Mechanics, Chinese Academy of Sciences, Beijing 100190, ChinaKolmogorov–Arnold Networks (KANs) are a recent development in machine learning, offering strong functional representation capabilities, enhanced interpretability, and reduced parameter complexity. Leveraging these advantages, this paper proposes a KAN-based reduced-order model (ROM) for unsteady aerodynamics and aeroelasticity. To effectively capture temporal dependencies inherent in nonlinear unsteady flow phenomena, an architecture termed Kolmogorov–Arnold Gated Recurrent Network (KAGRN) is introduced. By incorporating a recurrent structure and a gating mechanism, the proposed model effectively captures time-delay effects and enables the selective control and preservation of long-term temporal dependencies. This architecture provides high predictive accuracy, good generalization capability, and fast prediction speed. The performance of the model is evaluated using simulations of the NACA (National Advisory Committee for Aeronautics) 64A010 airfoil undergoing harmonic motion and limit cycle oscillations in transonic flow conditions. Results demonstrate that the proposed model can not only accurately and efficiently predict unsteady aerodynamic coefficients, but also effectively capture nonlinear aeroelastic responses.https://www.mdpi.com/2076-3417/15/11/5820Kolmogorov–Arnold Networksreduced-order modelunsteady aerodynamicsnonlinear aeroelasticity
spellingShingle Yuchen Zhang
Han Tang
Lianyi Wei
Guannan Zheng
Guowei Yang
Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and Aeroelasticity
Applied Sciences
Kolmogorov–Arnold Networks
reduced-order model
unsteady aerodynamics
nonlinear aeroelasticity
title Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and Aeroelasticity
title_full Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and Aeroelasticity
title_fullStr Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and Aeroelasticity
title_full_unstemmed Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and Aeroelasticity
title_short Kolmogorov–Arnold Networks for Reduced-Order Modeling in Unsteady Aerodynamics and Aeroelasticity
title_sort kolmogorov arnold networks for reduced order modeling in unsteady aerodynamics and aeroelasticity
topic Kolmogorov–Arnold Networks
reduced-order model
unsteady aerodynamics
nonlinear aeroelasticity
url https://www.mdpi.com/2076-3417/15/11/5820
work_keys_str_mv AT yuchenzhang kolmogorovarnoldnetworksforreducedordermodelinginunsteadyaerodynamicsandaeroelasticity
AT hantang kolmogorovarnoldnetworksforreducedordermodelinginunsteadyaerodynamicsandaeroelasticity
AT lianyiwei kolmogorovarnoldnetworksforreducedordermodelinginunsteadyaerodynamicsandaeroelasticity
AT guannanzheng kolmogorovarnoldnetworksforreducedordermodelinginunsteadyaerodynamicsandaeroelasticity
AT guoweiyang kolmogorovarnoldnetworksforreducedordermodelinginunsteadyaerodynamicsandaeroelasticity