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

김민기; 윤현식; 서장훈; 김민일

doi:10.5407/jksv.2024.22.1.049

DNN과 Decoder 모델 구축을 통한 생체모방 3차원 파형 익형의 유체역학적 특성 예측
Establishment of DNN and Decoder models to predict fluid dynamic characteristics of biomimetic three-dimensional wavy wings 원문보기

한국가시화정보학회지= Journal of the Korean society of visualization, v.22 no.1, 2024년, pp.49 - 60

김민기 (Department of Naval Architecture and Ocean Engineering, Pusan National University) , 윤현식 (Department of Naval Architecture and Ocean Engineering, Pusan National University) , 서장훈 (Department of Naval Architecture and Ocean Engineering, Pusan National University) , 김민일 (Department of Naval Architecture and Ocean Engineering, Pusan National University)

Abstract ▼ AI-Helper

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.

주제어

표/그림 (15)

그림 Fig. 1. Schematic of computational domain and boundary conditions
그림 Fig. 2. Grid system of wavy wing
그림 Fig. 3. Drag and lift coefficients of the (a) smooth wing and (b) wavy wing at Re=106
그림 Fig. 4. Typical layer architectures of (a) DNN and (b) Decoder models
그림 Fig. 5. Convergence histories of MSE with different (a) DNN and (b) Decoder model.
표 Table 1. Parameters for DNN model
표 Table 2. Parameters for Decoder model
그림 Fig. 6. Comparison of true and predicted values, (a) C_D / C_L and (b) Nu
그림 Fig. 7. Contours of pressure coefficient on the upper surface of different wavy wings for true (left column) and Decoder prediction (right column): (a) Case 1, (b) Case 2, (c) Case 3 and (d) Case 4.
그림 Fig. 8. Limiting streamlines on the upper surface of different wavy wings for true (left column) and Decoder prediction (right column) : (a) Case 1, (b) Case 2, (c) Case 3 and (d) Case 4.
표 Table 3. Geometry parameters of wavy wings (1)
그림 Fig. 9. Contours of Nusselt number on the upper surface of different wavy wings for true (left column) and Decoder prediction (right column) : (a) Case 1, (b) Case 2, (c) Case 3, and (d) Case 4.
그림 Fig. 10. Pressure coefficient and limiting streamlines of true(left column) and Decoder prediction(right column) (a) Case 5, (b) Case 6 and (c) Case 7.
표 Table 4. Geometry parameters of wavy wings (2)
그림 Fig. 11. Nusselt number of true(left column) and Decoder prediction(right column) : : (a) Case 5, (b) Case 6 and (c) Case 7.

참고문헌 (26)

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
Miklosovic, D. S., et al., 2004, "Leading-edge？tubercles delay stall on humpback whale？(Megaptera novaeangliae) flippers." Physics of？fluids 16.5: L39-L42.
Fish, FEandlauder, and George V. Lauder.,？2006, "Passive and active flow control by？swimming fishes and mammals." AnNu. Rev.？Fluid Mech. 38: 193-224.

상세보기
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.

상세보기
Kim, Mi Jeong, and Hyun Sik Yoon., 2012,？"Hydrodynamic characteristics for flow around？wavy wings." APS Division of Fluid Dynamics？Meeting Abstracts.
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.

상세보기
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.
Wu, Liming, and Xiaomin Liu., 2021, "Dynamic？stall characteristics of the bionic airfoil with？different waviness ratios." Applied Sciences？11.21: 9943.
Fan, Menghao, et al., 2022, "Numerical and？experimental study on flow separation control of？airfoils with various leading-edge tubercles."？Ocean Engineering 252: 111046.

상세보기
Liu, Jiaqi, et al., 2023, "Deep-learning-based aerodynamic shape optimization of rotor airfoils？to suppress dynamic stall." Aerospace Science？and Technology 133: 108089.

상세보기
Lou, Jinhua, et al., 2023, "Aerodynamic？optimization of airfoil based on deep？reinforcement learning." Physics of Fluids 35.3.

상세보기
Wu, Ming-Yu, et al., 2023, "Airfoil shape？optimization using genetic algorithm coupled？deep neural networks." Physics of Fluids 35.8.

상세보기
Dussauge, Thomas P., et al., 2023, "A？reinforcement learning approach to airfoil shape？optimization." Scientific Reports 13.1: 9753.
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.

상세보기
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.
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.
Chen, H., Weiqi, Q. and Song, W., 2020,？"Multiple Aerodynamic Coefficient Prediction？of Airfoils Using a Convolutional Neural？Network," Symmetry 12 (4), 544.
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.
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.

상세보기
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.

상세보기
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.
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."
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
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.
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.

상세보기
Siemens. STAR-CCM+ User Guide Version？16.04; Siemens: New York, NY, USA, 2016.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증