Journal of the Korean Society of Visualization (한국가시화정보학회지)

The Korean Society of Visualization (한국가시화정보학회)
권호 표지
DOI QR코드

DOI QR Code

Study of an AI Model for Airfoil Parameterization and Aerodynamic Coefficient Prediction from Image Data

이미지 데이터를 이용한 익형 매개변수화 및 공력계수 예측을 위한 인공지능 모델 연구

  • Seung Hun Lee (Department of Mechanical Engineering, Korea Maritime and Ocean University) ;
  • Bo Ra Kim (Department of Mechanical Engineering, Korea Maritime and Ocean University) ;
  • Jeong Hun Lee (Department of Mechanical Engineering, Korea Maritime and Ocean University) ;
  • Joon Young Kim (Department of Ocean Advanced Materials Convergence Engineering, Korea Maritime and Ocean University) ;
  • Min Yoon (Department of Mechanical Engineering, Korea Maritime and Ocean University)
  • Received : 2023.06.23
  • Accepted : 2023.07.24
  • Published : 2023.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

The shape of an airfoil is a critical factor in determining aerodynamic characteristics such as lift and drag. Aerodynamic properties of an airfoil have a decisive impact on the performance of various engineering applications, including airplane wings and wind turbine blades. Therefore, it is essential to analyze the aerodynamic characteristics of airfoils. Various analytical tools such as experiments, computational fluid dynamics, and Xfoil are used to perform these analyses, but each tool has its limitation. In this study, airfoil parameterization, image recognition, and artificial intelligence are combined to overcome these limitations. Image and coordinate data are collected from the UIUC airfoil database. Airfoil parameterization is performed by recognizing images from image data to build a database for deep learning. Trained model can predict the aerodynamic characteristics not only of airfoil images but also of sketches. The mean absolute error of untrained data is 0.0091.

Keywords

Acknowledgement

이 연구는 2021학년도 한국해양대학교 신진교수 정착연구지원사업 연구비 및 정부(과학기술정보통신부)의 재원으로 한국연구재단의 무인이동체원천기술개발 사업(2020M3C1C1A02086326)의 지원을 받아 수행되었습니다.

References

  1. Drela, M., 1989, "XFOIL: An analysis and design system for low Reynolds number airfoils," In Low Reynolds Number Aerodynamics, Springer, Berlin, Heidelberg., pp.1~12. 
  2. Xflr5., 2019, http://www.xflr5.tech/xflr5.html. 
  3. Oliver, J. M., Kipouros, T., and Savill, A.M., 2013, "A Self-adaptive Genetic Algorithm Applied to Multi-Objective Optimization of an Airfoil," In EVOLVE-A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation IV. Advances in Intelligent Systems and Computing, Springer Heidelberg., pp.261~ 276. 
  4. Echavarria, C., Hoyos, J. D., Jimenez, J. H., Suarez, G., and Saldarriaga, A., 2022, "Optimal airfoil design through particle swarm optimization fed by CFD and XFOIL," J. Braz. Soc. Mech. Sci. Eng., Vol. 44(11), p.561. 
  5. Kim, B. R., Lee, S. H., Jang, S. H., Hwang, G. I., and Yoon, M., 2022, "Prediction of aerodynamics using VGG16 and U-Net," J. Korean Soc. Vis., Vol. 20(3), pp.109~116. 
  6. Seo, J. H., Yoon, H. S., Kim, and M. I., 2022, "Prediction of aerodynamic force coefficients and flow fields of airfoils using CNN and EncoderDecoder models.," J. Korean Soc. Vis., Vol. 20(3), pp.94~101. 
  7. Bradski, G., 2000, "The openCV library," Dr. Dobb's Journal: Software Tools for the Professional Programmer, Vol. 25(11), pp.120~ 123. 
  8. Ramchoun, H., Ghanou, Y., Ettaouil, M., and Janati Idrissi, M. A., 2016, "Multilayer perceptron: Architecture optimization and training,", Proc. IJIMAI, Vol. 4(1), pp.26~30.  https://doi.org/10.9781/ijimai.2016.415
  9. Pokhrel, P., 2023, "A Comparison of AutoML Hyperparameter Optimization Tools for Tabular Data," Master's thesis, Youngstown State University. 
  10. Frazier, P. I., 2018, "A tutorial on Bayesian optimization," arXiv preprint arXiv:1807.02811. 
  11. Selig, M. S., 1996, "UIUC airfoil data site," Department of Aeronautical and Astronautical Engineering University of Illinois at Urbana-Champaign. 
  12. Chicco, D., Warrens, M. J., and Jurman, G., 2021, "The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation," PeerJ Comput. Sci., Vol. 7, pp.623. 
  13. Nagelkerke, N. J., 1991," A note on a general definition of the coefficient of determination," Biometrika., Vol. 78(3), pp.691~ 692.  https://doi.org/10.1093/biomet/78.3.691