Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime

Tarek Ayman; Mayar A. Elrefaie; Eman Sayed; Mohammed Elrefaie; Mahmoud Ayyad; Ahmed A. Hamada; Mohamed M. Abdelrahman

doi:10.1109/NILES59815.2023.10296587

Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime

Tarek Ayman, Mayar A. Elrefaie, Eman Sayed, Mohammed Elrefaie, Mahmoud Ayyad, Ahmed A. Hamada, Mohamed M. Abdelrahman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

This paper presents an approach to estimate the aerodynamic coefficients of airfoils in the transonic regime using Artificial Neural Networks. The transonic regime is a critical and challenging aerodynamic domain, and our approach utilizes data generated by the OpenFOAM® to train our model. Our dataset encompasses a wide range of transonic flow conditions and different airfoil shapes, enabling our Artificial Neural Networks to capture the complex behavior of aerodynamic phenomena in this regime. Our proposed framework achieves high accuracy, with the lift and moment coefficient predictions demonstrating an unprecedented accuracy level of 99.7% with respect to the test dataset obtained by OpenFOAM®. Our results demonstrate the potential of Artificial Neural Networks to accurately predict aerodynamic coefficients in the transonic regime, which could have significant implications for the design and optimization of high-performance aircraft.

Original language	English
Title of host publication	5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings
Pages	157-160
Number of pages	4
ISBN (Electronic)	9798350381030
DOIs	https://doi.org/10.1109/NILES59815.2023.10296587
State	Published - 2023
Event	5th International IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Hybrid, Giza, Egypt Duration: 21 Oct 2023 → 23 Oct 2023

Publication series

Name	5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings

Conference

Conference	5th International IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023
Country/Territory	Egypt
City	Hybrid, Giza
Period	21/10/23 → 23/10/23

Keywords

Aerodynamic performance
Artificial Neural Network
Compressible flow
Computational Fluid Dynamics
OpenFOAM
Transonic airfoils

Access to Document

10.1109/NILES59815.2023.10296587

Cite this

Ayman, T., Elrefaie, M. A., Sayed, E., Elrefaie, M., Ayyad, M., Hamada, A. A., & Abdelrahman, M. M. (2023). Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime. In 5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings (pp. 157-160). (5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings). https://doi.org/10.1109/NILES59815.2023.10296587

@inproceedings{5b5f8b160b6943958ca506a136530d10,

title = "Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime",

abstract = "This paper presents an approach to estimate the aerodynamic coefficients of airfoils in the transonic regime using Artificial Neural Networks. The transonic regime is a critical and challenging aerodynamic domain, and our approach utilizes data generated by the OpenFOAM{\textregistered} to train our model. Our dataset encompasses a wide range of transonic flow conditions and different airfoil shapes, enabling our Artificial Neural Networks to capture the complex behavior of aerodynamic phenomena in this regime. Our proposed framework achieves high accuracy, with the lift and moment coefficient predictions demonstrating an unprecedented accuracy level of 99.7% with respect to the test dataset obtained by OpenFOAM{\textregistered}. Our results demonstrate the potential of Artificial Neural Networks to accurately predict aerodynamic coefficients in the transonic regime, which could have significant implications for the design and optimization of high-performance aircraft.",

keywords = "Aerodynamic performance, Artificial Neural Network, Compressible flow, Computational Fluid Dynamics, OpenFOAM, Transonic airfoils",

author = "Tarek Ayman and Elrefaie, {Mayar A.} and Eman Sayed and Mohammed Elrefaie and Mahmoud Ayyad and Hamada, {Ahmed A.} and Abdelrahman, {Mohamed M.}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 5th International IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 ; Conference date: 21-10-2023 Through 23-10-2023",

year = "2023",

doi = "10.1109/NILES59815.2023.10296587",

language = "English",

series = "5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings",

pages = "157--160",

booktitle = "5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings",

}

Ayman, T, Elrefaie, MA, Sayed, E, Elrefaie, M, Ayyad, M, Hamada, AA & Abdelrahman, MM 2023, Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime. in 5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings. 5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings, pp. 157-160, 5th International IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023, Hybrid, Giza, Egypt, 21/10/23. https://doi.org/10.1109/NILES59815.2023.10296587

Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime. / Ayman, Tarek; Elrefaie, Mayar A.; Sayed, Eman et al.
5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings. 2023. p. 157-160 (5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime

AU - Ayman, Tarek

AU - Elrefaie, Mayar A.

AU - Sayed, Eman

AU - Elrefaie, Mohammed

AU - Ayyad, Mahmoud

AU - Hamada, Ahmed A.

AU - Abdelrahman, Mohamed M.

PY - 2023

Y1 - 2023

N2 - This paper presents an approach to estimate the aerodynamic coefficients of airfoils in the transonic regime using Artificial Neural Networks. The transonic regime is a critical and challenging aerodynamic domain, and our approach utilizes data generated by the OpenFOAM® to train our model. Our dataset encompasses a wide range of transonic flow conditions and different airfoil shapes, enabling our Artificial Neural Networks to capture the complex behavior of aerodynamic phenomena in this regime. Our proposed framework achieves high accuracy, with the lift and moment coefficient predictions demonstrating an unprecedented accuracy level of 99.7% with respect to the test dataset obtained by OpenFOAM®. Our results demonstrate the potential of Artificial Neural Networks to accurately predict aerodynamic coefficients in the transonic regime, which could have significant implications for the design and optimization of high-performance aircraft.

AB - This paper presents an approach to estimate the aerodynamic coefficients of airfoils in the transonic regime using Artificial Neural Networks. The transonic regime is a critical and challenging aerodynamic domain, and our approach utilizes data generated by the OpenFOAM® to train our model. Our dataset encompasses a wide range of transonic flow conditions and different airfoil shapes, enabling our Artificial Neural Networks to capture the complex behavior of aerodynamic phenomena in this regime. Our proposed framework achieves high accuracy, with the lift and moment coefficient predictions demonstrating an unprecedented accuracy level of 99.7% with respect to the test dataset obtained by OpenFOAM®. Our results demonstrate the potential of Artificial Neural Networks to accurately predict aerodynamic coefficients in the transonic regime, which could have significant implications for the design and optimization of high-performance aircraft.

KW - Aerodynamic performance

KW - Artificial Neural Network

KW - Compressible flow

KW - Computational Fluid Dynamics

KW - OpenFOAM

KW - Transonic airfoils

UR - http://www.scopus.com/inward/record.url?scp=85178506146&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85178506146&partnerID=8YFLogxK

U2 - 10.1109/NILES59815.2023.10296587

DO - 10.1109/NILES59815.2023.10296587

M3 - Conference contribution

AN - SCOPUS:85178506146

T3 - 5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings

SP - 157

EP - 160

BT - 5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings

T2 - 5th International IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023

Y2 - 21 October 2023 through 23 October 2023

ER -

Ayman T, Elrefaie MA, Sayed E, Elrefaie M, Ayyad M, Hamada AA et al. Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime. In 5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings. 2023. p. 157-160. (5th Novel Intelligent and Leading Emerging Sciences Conference, NILES 2023 - Proceedings). doi: 10.1109/NILES59815.2023.10296587

Deep Learning-Based Prediction of Aerodynamic Performance for Airfoils in Transonic Regime

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this