DOI QR코드

DOI QR Code

Establishment of DNN and Decoder models to predict fluid dynamic characteristics of biomimetic three-dimensional wavy wings

DNN과 Decoder 모델 구축을 통한 생체모방 3차원 파형 익형의 유체역학적 특성 예측

  • Minki Kim (Department of Naval Architecture and Ocean Engineering, Pusan National University) ;
  • Hyun Sik Yoon (Department of Naval Architecture and Ocean Engineering, Pusan National University) ;
  • Janghoon Seo (Department of Naval Architecture and Ocean Engineering, Pusan National University) ;
  • Min Il Kim (Department of Naval Architecture and Ocean Engineering, Pusan National University)
  • Received : 2024.03.08
  • Accepted : 2024.03.15
  • Published : 2024.03.31

Abstract

The purpose of this study establishes the deep neural network (DNN) and Decoder models to predict the flow and thermal fields of three-dimensional wavy wings as a passive flow control. The wide ranges of the wavy geometric parameters of wave amplitude and wave number are considered for the various the angles of attack and the aspect ratios of a wing. The huge dataset for training and test of the deep learning models are generated using computational fluid dynamics (CFD). The DNN and Decoder models exhibit quantitatively accurate predictions for aerodynamic coefficients and Nusselt numbers, also qualitative pressure, limiting streamlines, and Nusselt number distributions on the surface. Particularly, Decoder model regenerates the important flow features of tiny vortices in the valleys, which makes a delay of the stall. Also, the spiral vortical formation is realized by the Decoder model, which enhances the lift.

Keywords

Acknowledgement

이 과제는 부산대학교 기본연구지원사업(2년)에 의하여 연구되었음.

References

  1. Watts, Phil, and Frank E. Fish., 2001, "The influence of passive, leading edge tubercles on wing performance." Proc. Twelfth Intl. Symp. Unmanned Untethered Submers. Technol. Durham
  2. Miklosovic, D. S., et al., 2004, "Leading-edge tubercles delay stall on humpback whale (Megaptera novaeangliae) flippers." Physics of fluids 16.5: L39-L42. https://doi.org/10.1063/1.1688341
  3. Fish, FEandlauder, and George V. Lauder., 2006, "Passive and active flow control by swimming fishes and mammals." AnNu. Rev. Fluid Mech. 38: 193-224. https://doi.org/10.1146/annurev.fluid.38.050304.092201
  4. Van Nierop, Ernst A., Silas Alben, and Michael P. Brenner., 2008, "How bumps on whale flippers delay stall: an aerodynamic model." Physical review letters 100.5: 054502.
  5. Kim, Mi Jeong, and Hyun Sik Yoon., 2012, "Hydrodynamic characteristics for flow around wavy wings." APS Division of Fluid Dynamics Meeting Abstracts.
  6. Perez-Torro, Rafael, and Jae Wook Kim., 2017, "A large-eddy simulation on a deep-stalled aerofoil with a wavy leading edge." Journal of Fluid Mechanics 813: 23-52. https://doi.org/10.1017/jfm.2016.841
  7. Chen, Weijie, Weiyang Qiao, and Zuojun Wei., 2020, "Aerodynamic performance and wake development of airfoils with wavy leading edges." Aerospace Science and Technology 106: 106216.
  8. Wu, Liming, and Xiaomin Liu., 2021, "Dynamic stall characteristics of the bionic airfoil with different waviness ratios." Applied Sciences 11.21: 9943.
  9. Fan, Menghao, et al., 2022, "Numerical and experimental study on flow separation control of airfoils with various leading-edge tubercles." Ocean Engineering 252: 111046.
  10. Liu, Jiaqi, et al., 2023, "Deep-learning-based aerodynamic shape optimization of rotor airfoils to suppress dynamic stall." Aerospace Science and Technology 133: 108089.
  11. Lou, Jinhua, et al., 2023, "Aerodynamic optimization of airfoil based on deep reinforcement learning." Physics of Fluids 35.3.
  12. Wu, Ming-Yu, et al., 2023, "Airfoil shape optimization using genetic algorithm coupled deep neural networks." Physics of Fluids 35.8.
  13. Dussauge, Thomas P., et al., 2023, "A reinforcement learning approach to airfoil shape optimization." Scientific Reports 13.1: 9753.
  14. Yoon, H. S., Hung, P. A., Jung, J. H., Kim, M. C., 2011, "Effect of the wavy leading edge on hydrodynamic characteristics for flow around low aspect ratio wing" Comput. Fluids, 49, 276-289. https://doi.org/10.1016/j.compfluid.2011.06.010
  15. Seo, J., Yoon, H. S., Kim, M. I., 2022, "Prediction of aerodynamic force coefficients and flow fields of airfoils using CNN and Encoder-Decoder models" The Korean Society of Visualization: 94-101.
  16. Xu, H. J., et al., 2022, "Bent Pipe Flow Prediction Based on Ultrasound Doppler Velocimetry and Machine Learning." The Korean Society of Visualization: 31-32.
  17. Chen, H., Weiqi, Q. and Song, W., 2020, "Multiple Aerodynamic Coefficient Prediction of Airfoils Using a Convolutional Neural Network," Symmetry 12 (4), 544.
  18. Kim, M. J.; Yoon, H. S.; Jung, J. H.; Chun, H. H.; Park, D. W., 2012, "Hydrodynamic characteristics for flow around wavy wings with different wave lengths", Int. J. Nav. Archit. Ocean Eng., 4, 447-459. https://doi.org/10.2478/IJNAOE-2013-0110
  19. Duru, C., Alemdar, H. ands Baran, O. U. 2021, "CNNFOIL: Convolutional encoder decoder modeling for pressure fields around airfoils," Neural Computing and Applications, 33(12), 6835-6849. https://doi.org/10.1007/s00521-020-05461-x
  20. Seo, J., Yoon, H. S., Kim, M. I., 2022, "Establishment of CNN and encoder-decoder models for the prediction of characteristics of flow and heat transfer around NACA sections." Energies 15.23: 9204.
  21. Kim, M. I., Hyun-Sik Yoon, and Jang-Hoon Seo., 2023, "Deep Learning Models for the Evaluation of the Aerodynamic and Thermal Performance of Three-Dimensional Symmetric Wavy Wings." Symmetry 16.1: 21.
  22. Molland, A. F., and S. R. Turnock. 1993, "Wind tunnel tests on the influence of propeller loading on ship rudder performance: Four quadrant operation, low and zero speed operation."
  23. Kingma, D.P.; Ba, J. Adam, 2015, "A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations (ICLR)", San Diego, CA, USA, 24-28
  24. LeCun, Y.; Boser, B.; Denker, J. S.; Henderson, D.; Howard, R. E.; Hubbard, W. 1989, "Jackel, L. D. Backpropagation applied to handwritten zip code recognition.", Neural Comput., 1, 541-551.
  25. Zanin, B. Y.' Zverkov, I. D.; Kozlov, V. V.; Pavlenko, A. M., 2008, "Vortex structure of separated flows on model wings at low freestream velocities.", Fluid Dynamics, 43, 938-944. https://doi.org/10.1134/S0015462808060148
  26. Siemens. STAR-CCM+ User Guide Version 16.04; Siemens: New York, NY, USA, 2016.