Journal of Aerospace System Engineering (항공우주시스템공학회지)

The Society for Aerospace System Engineering (항공우주시스템공학회)
권호 표지
DOI QR코드

DOI QR Code

Deep learning-based Approach for Prediction of Airfoil Aerodynamic Performance

에어포일 공력 성능 예측을 위한 딥러닝 기반 방법론 연구

  • Cheon, Seongwoo (Department of AeroSpace Engineering, Jeonbuk National University) ;
  • Jeong, Hojin (Department of AeroSpace Engineering, Jeonbuk National University) ;
  • Park, Mingyu (ISAE-SUPAERO) ;
  • Jeong, Inho (Department of AeroSpace Engineering, Jeonbuk National University) ;
  • Cho, Haeseong (Department of AeroSpace Engineering, Jeonbuk National University) ;
  • Ki, Youngjung (Korea Aerospace Research Institute)
  • Received : 2022.01.21
  • Accepted : 2022.06.15
  • Published : 2022.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, a deep learning-based network that can predict the aerodynamic characteristics of airfoils was designed, and the feasibility of the proposed network was confirmed by applying aerodynamic data generated by Xfoil. The prediction of aerodynamic characteristics according to the variation of airfoil thickness was performed. Considering the angle of attack, the coordinate data of an airfoil is converted into image data using signed distance function. Additionally, the distribution of the pressure coefficient on airfoil is expressed as reduced data via proper orthogonal decomposition, and it was used as the output of the proposed network. The test data were constructed to evaluate the interpolation and extrapolation performance of the proposed network. As a result, the coefficients of determination of the lift coefficient and moment coefficient were confirmed, and it was found that the proposed network shows benign performance for the interpolation test data, when compared to that of the extrapolation test data.

본 논문에서는 에어포일의 좌표 데이터에 대해 공력 특성을 예측할 수 있는 합성곱 신경망 기반 네트워크 프레임 워크를 설계하였으며 Xfoil을 이용한 공력 데이터를 적용하여 네트워크의 가능성을 확인하였다. 이 때 에어포일의 두께 변화에 따른 공력 특성 예측을 수행하였다. 부호화 거리 함수를 이용하여 에어포일의 좌표 데이터를 이미지 데이터로 변환하였으며 받음각 정보를 반영하였다. 또한 에어포일의 압력 계수 분포를 축소 모델 기법 중 하나인 적합 직교 분해를 이용하여 축소된 데이터로 표현하였으며 이를 네트워크의 출력 데이터로 사용하였다. 제시하는 네트워크의 내삽과 외삽 성능을 평가하기 위하여 시험 데이터를 구성하였고, 결과적으로 내삽 데이터에 대한 예측 성능이 외삽에 비해 우수함을 확인하였다.

Keywords

Acknowledgement

본 연구는 2021년 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원(No. 2020R1C1C1006006)과 한국전력공사의 2021년 착수 기초연구 개발 과제 연구비의 지원(No. R21XO01-6)을 받아 수행된 연구입니다.

References

  1. R. Shrestha, M. Benedict, V. Hrishikeshavan and I. Chopra, "Hover performance of a small-scale helicopter rotor for flying on mars," Journal of Aircraft, vol. 53, no. 4, pp. 1160-1167, May 2016 https://doi.org/10.2514/1.C033621
  2. J.-S. Wang and J.-J. Wang, "Wake-Induced Transition in the Low-Reynolds-Number Flow over a Multi-Element Airfoil," Journal of Fluid Mechanics, vol. 915, March 2021.
  3. S. Wang, Y. Zhou, M. M. Alam and H. Yang, "Turbulent Intensity and Reynolds Number Effects on an Airfoil at Low Reynolds Numbers," Physics of Fluids, vol. 26, no. 11, p. 115107, Nov. 2014
  4. J. Winslow, H. Otsuka, B. Govindarajan and I. Chopra, "Basic Understanding of Airfoil Characteristics at Low Reynolds Numbers (104 - 105)," Journal of Aircraft, vol. 55, no. 3 pp.1050-1061, Dec. 2018 https://doi.org/10.2514/1.C034415
  5. E. Yilmaz, and B. German, "A Convolutional Neural Network Approach to Training Predctors for Airfoil Performance," 18th AIAA/ISSMO multidisciplinary analysis and optimization conference, Denver, Colorado, p. 3660, Jun. 2017
  6. C. Duru, H. Alemdar, and O. U. Baran, "A deep learning approach for the transonic flow field predictions around airfoils," Computers & Fluids, vol. 236, p.105312, Mar. 2022
  7. S. Bhatnagar, Y. Afshar, S. Pan, K. Duraisamy and S. Kaushik, "Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks," Computational Mechanics, vol. 64, no. 2, pp. 525-545, June 2019 https://doi.org/10.1007/s00466-019-01740-0
  8. Y. Zhang, W. J. Sung and D. N. Mavris, "Application of convolutional neural network to predict airfoil lift coefficient," AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference 2018, Kissimmee, Florida, p. 1903, Jan. 2018
  9. K. Balla, R. Sevilla, O. Hassan and K. Morgan, "An Application of Neural Networks to the Prediction of Aerodynamic Coefficients of Aerofoils and Wings," Applied Mathematical Modelling, vol. 96, pp. 456-479, Aug. 2021 https://doi.org/10.1016/j.apm.2021.03.019
  10. T. Murata, K. Fukami, and K. Fukagata, "Nonlinear mode decomposition with convolutional neural networks for luid dynamics," Journal of Fluid Mechanics, vol. 882, Jan. 2020
  11. M. Drela, "Xfoil: An Analysis and Design System for Low Reynolds Number Airfoils," Low Reynolds number aerodynamics, pp. 1-12, Springer, Berlin, 1989.
  12. D. Scherer, A. Mulle,and S. Behnke, "Evaluation of pooling operations in convolutional architectures for object recognition," International conference on artificial neural networks, Thessaloniki, Greece, pp. 92-101, Sep. 2010
  13. G. Berkooz, P. Holmes, and J. L. Lumley, "The proper orthogonal decomposition in the analysis of turbulent flows," Annual review of fluid mechanics, vol. 25, no. 1, pp. 539-575, 1993 https://doi.org/10.1146/annurev.fl.25.010193.002543
  14. S. Walton, O. Hassan, K. Morgan, "Reduced order modelling for unsteady fluid flow using proper orthogonal decomposition and radial basis functions," Applied Mathematical Modelling, vol. 37, no. 20-21, pp. 8930-8945, Nov. 2013 https://doi.org/10.1016/j.apm.2013.04.025
  15. A. F. Agarap, "Deep learning using rectified linear units(relu)," arXiv preprint arXiv: 1803.08375, Mar. 2018
  16. D. P. Kingma, and J. Ba, "Adam: Amethod for stochastic optimization," arXiv preprint arXiv:1412.6980, Dec. 2014
  17. S. P. Pan, and Q. Yang, "A survey on transfer learning," IEEE Transactions on knowledge and data engineering, vol. 22, no. 10, pp. 1345-1359 https://doi.org/10.1109/TKDE.2009.191