EI、Scopus 收录
中文核心期刊
Zhao Shule, Zhang Weiwei. Machine learning of skin friction distribution based on surface inviscid flow feature. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(8): 2243-2258. DOI: 10.6052/0459-1879-23-615
Citation: Zhao Shule, Zhang Weiwei. Machine learning of skin friction distribution based on surface inviscid flow feature. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(8): 2243-2258. DOI: 10.6052/0459-1879-23-615

MACHINE LEARNING OF SKIN FRICTION DISTRIBUTION BASED ON SURFACE INVISCID FLOW FEATURE

  • Received Date: December 19, 2023
  • Accepted Date: March 11, 2024
  • Available Online: March 06, 2024
  • Published Date: March 12, 2024
  • Accurate and efficient prediction of skin friction drag is crucial for aircraft design. However, the computation of the skin friction drag distribution is not only costly but also highly dependent on mesh density, turbulence patterns and numerical algorithms, while experimental measurements are more challenging. To this end, this paper proposes a data-driven machine-learning modeling method for skin friction drag distribution with high generalizability. Based on the numerical solution of Euler's equation, the method combines a small number of skin friction distribution samples computed by RANS to construct a model of the correlation relationship between the surface inviscid flow feature and the friction distribution, so as to realize the prediction of friction. Since the physical model of Euler's equation is embedded in this modeling method, the high generalizability and accuracy of the model can be ensured with few samples; on the other hand, compared with the numerical computation of RANS, the amount of computation is reduced by about one order of magnitude because only the Euler's equation is solved. The study demonstrates the effectiveness of the method for predicting variable geometric shapes skin friction in aerodynamic design by means of test cases for typical airfoils and wings. Compared to end-to-end distributed force deep learning modeling, the method achieves high modeling accuracy (drag error of about 2% ~ 3%) despite a fivefold reduction in sample size, and has strong generalization ability for working conditions and shape changes with low dispersion of results. This study provides a new and efficient research tool for the prediction of the friction distribution of attached-flow airfoils and the optimal design of airfoils.
  • [1]
    Guo M, Manzoni A, Amendt M, et al. Multi-fidelity regression using artificial neural networks: Efficient approximation of parameter-dependent output quantities. Computer Methods in Applied Mechanics and Engineering, 2022, 389: 114378 doi: 10.1016/j.cma.2021.114378
    [2]
    刘朋欣, 孙东, 李辰等. 高焓湍流边界层壁面摩阻产生机制分析. 力学学报, 2022, 54(1): 39-47 (Liu Pengxin, Sun Dong, Li Chen, et al. Analyses on generation mechanism of skin friction in high enthalpy turbulent boundary layer. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(1): 39-47 (in Chinese)

    Liu Pengxin, Sun Dong, Li Chen, et al. Analyses on generation mechanism of skin friction in high enthalpy turbulent boundary layer. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(1): 39-47 (in Chinese)
    [3]
    范月华, 段毅, 周乃桢等. 高马赫数层流摩阻数值计算精度. 航空学报, 2021, 42(9): 625737 (Fan Yuehua, Duan Yi, Zhou Naizhen, et al. Friction numerical calculation precision in high Mach number laminar flow. Acta Aeronauticaet Astronautica Sinica, 2021, 42(9): 625737 (in Chinese)

    Fan Yuehua, Duan Yi, Zhou Naizhen, et al. Friction numerical calculation precision in high Mach number laminar flow. Acta Aeronauticaet Astronautica Sinica, 2021, 42(9): 625737 (in Chinese)
    [4]
    张益荣, 张毅锋, 解静等. 典型高超声速翼身组合体黏性干扰效应模型研究 空气动力学学报, 2017, 35(2): 186-191 (Zhang Yirong, Zhang Yifeng, Xie Jing, et al. Study of viscous interaction effect model for typical hypersonic wing-body figuration. Acta Aerodynamica Sinica, 2017, 35(2): 186-191 (in Chinese)

    Zhang Yirong, Zhang Yifeng, Xie Jing, et al. Study of viscous interaction effect model for typical hypersonic wing-body figuration. Acta Aerodynamica Sinica, 2017, 35(2): 186-191 (in Chinese)
    [5]
    Götten F, Havermann M, Braun C, et al. Airfoil drag at low-to-medium Reynolds numbers: A novel estimation method. AIAA Journal, 2020, 58(7): 2791-805 doi: 10.2514/1.J058983
    [6]
    Raymer D. Aircraft Design: A Conceptual Approach, 6th ed. Reston, VA: AIAA Education Series, 2019
    [7]
    Roskam J. Airplane Design. Ottawa, Kansas: DAR corporation, 1987
    [8]
    Torenbeek E. An introduction to the preliminary design of subsonic general aviation and transport aircraft, with emphasis on layout, aerodynamic design, propulsion and performance//Synthesis of Subsonic Airplane Design. Dordrecht: Springer Netherlands, 2010
    [9]
    卞荫贵, 赵国英. 可压缩流边界层参数的工程计算方法. 力学学报, 1980, 16(2): 120-128 (Bian Yingui, Zhao Guoying. Engineering calculation method for boundary layer parameters of compressible flows, Chinese Journal of Theoretical and Applied Mechanics, 1980, 16(2): 120-128 (in Chinese)

    Bian Yingui, Zhao Guoying. Engineering calculation method for boundary layer parameters of compressible flows, Chinese Journal of Theoretical and Applied Mechanics, 1980, 16(2): 120-128 (in Chinese)
    [10]
    Xia Z, Zhang P, Yang X. On skin friction in wall-bounded turbulence. Acta Mechanica Sinica, 2021, 37(4): 589-598 doi: 10.1007/s10409-020-01024-4
    [11]
    Xiao M, She Z. Precise drag prediction of airfoil flows by a new algebraic model. Acta Mechanica Sinica, 2019, 36(1): 35-43
    [12]
    Lombardi G, Salvetti MV, Pinelli D. Numerical evaluation of airfoil friction drag. Journal of Aircraft, 2015, 37(2): 354-6
    [13]
    Zhou BY, Gauger NR, Hauth J, et al. Towards real-time in-flight ice detection systems via computational aeroacoustics and machine learning//AIAA Aviation 2019 Forum, 2019
    [14]
    Durbin PA. Some recent developments in turbulence closure modeling. Annual Review of Fluid Mechanics, 2018, 50(1): 77-103 doi: 10.1146/annurev-fluid-122316-045020
    [15]
    Shi L, Han Z, Shahbaz M, et al. Surrogate-based robust airfoil optimization under aleatory flight condition and geometric uncertainties//54th AIAA Aerospace Sciences Meeting, 2016
    [16]
    蔡罕龙, 李锋. Euler方程与边界层积分方程耦合求解跨音速翼型绕流. 航空学报, 1991, 12(5): 221-227 (Cai Hanlong, Li Feng. Transonic airfoil analysis based on the interaction of Euler and integral boundary-layer equation. Acta Aeronauticaet Astronautica Sinica, 1991, 12(5): 221-227 (in Chinese)

    Cai Hanlong, Li Feng. Transonic airfoil analysis based on the interaction of Euler and integral boundary-layer equation. Acta Aeronauticaet Astronautica Sinica, 1991, 12(5): 221-227 (in Chinese)
    [17]
    Gaible F, Cariou R, Houdeville R. Numerical simulation of three-dimensional supersonic flows using Euler and boundary layer solvers//31st Aerospace Sciences Meeting. 1993, AIAA 1993-531
    [18]
    Oksuz O, Akmandor IS, Kavsaoglu MS. Aerodynamic optimization of turbomachinery cascades using euler/boundary-layer coupled genetic algorithms. Journal of Propulsion and Power, 2001, 18: 652-657, 3
    [19]
    Mark D, Michael BG. Viscous-inviscid analysis of transonic and low Reynolds number airfoils. AIAA Journal, 1987, 25(10): 1347-1355
    [20]
    Krzysztof JF. A coupled inviscid-viscous airfoil analysis solver, revisited. AIAA Journal, 2022, 60(5): 2961-2971
    [21]
    张伟伟, 寇家庆, 刘溢浪. 智能赋能流体力学展望. 航空学报, 2021, 42(4): 524689 (Zhang Weiwei, Kou Jiaqing, Liu Yilang. Prospect of artificial intelligence empowered fluid mechanics. Acta Aeronauticaet Astronautica Sinica, 2021, 42(4): 524689 (in Chinese)

    Zhang Weiwei, Kou Jiaqing, Liu Yilang. Prospect of artificial intelligence empowered fluid mechanics. Acta Aeronauticaet Astronautica Sinica, 2021, 42(4): 524689 (in Chinese)
    [22]
    唐志共, 朱林阳, 向星皓等. 智能空气动力学若干研究进展及展望. 空气动力学学报, 2023, 41(7): 1-35 (Tang Zhigong, Zhu Linyang, Xiang Xinghao, et al. Some research progress and prospect of intelligent aerodynamics. Acta Aerodynamica Sinica, 2023, 41(7): 1-35 (in Chinese)

    Tang Zhigong, Zhu Linyang, Xiang Xinghao, et al. Some research progress and prospect of intelligent aerodynamics. Acta Aerodynamica Sinica, 2023, 41(7): 1-35 (in Chinese)
    [23]
    Sekar V, Jiang Q, Shu C, et al. Fast flow field prediction over airfoils using deep learning approach. Physics of Fluids, 2019, 31(5): 057103 doi: 10.1063/1.5094943
    [24]
    Jin X, Cheng P, Chen W, et al. Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder. Physics of Fluids, 2018, 30(4): 047105 doi: 10.1063/1.5024595
    [25]
    Balla K, Sevilla R, Hassan O, et al. An application of neural networks to the prediction of aerodynamic coefficients of aerofoils and wings. Applied Mathematical Modelling, 2021, 96(10): 456-479
    [26]
    Xiong F, Zhang L, Hu X, et al. A point cloud deep neural network metamodel method for aerodynamic prediction. Chinese Journal of Aeronautics, 2023, 36(4): 92-103 doi: 10.1016/j.cja.2022.11.025
    [27]
    Silva AD, Cavalcanti J, Catalano F. Prediction of pressure distribution on wings using neural networks//AIAA/ISSMO Multidisciplinary Analysis & Optimization Conference, 2013
    [28]
    Hui X, Bai J, Wang H, et al. Fast pressure distribution prediction of airfoils using deep learning. Aerospace Science and Technology, 2020, 105: 105949 doi: 10.1016/j.ast.2020.105949
    [29]
    张伟伟, 王旭, 寇家庆. 面向流体力学的多范式融合研究展望. 力学进展, 2023, 53(2): 433-467 (Zhang Weiwei, Wang Xu, Kou Jiaqing. Prospects of multi-paradigm fusion methods for fluid mechanics research. Advances in Mechanics, 2023, 53(2): 433-467 (in Chinese)

    Zhang Weiwei, Wang Xu, Kou Jiaqing. Prospects of multi-paradigm fusion methods for fluid mechanics research. Advances in Mechanics, 2023, 53(2): 433-467 (in Chinese)
    [30]
    Suraj P, Omer S, Aditya N, et al. Model fusion with physics-guided machine learning: Projection-based reduced-order modeling. Physics of Fluids, 2021, 33(6): 067123 doi: 10.1063/5.0053349
    [31]
    Sansana J, Joswiak MN, Castillo I, et al. Recent trends on hybrid modeling for industry 4.0. Computers & Chemical Engineering, 2021, 151: 107365
    [32]
    Bradley W, Kim J, Kilwein Z, et al. Perspectives on the integration between first-principles and data-driven modeling. Computers & Chemical Engineering, 2022, 166: 107898
    [33]
    Suraj P, Omer S, Burak A, et al. Physics guided machine learning using simplified theories. Physics of Fluids, 2021, 33(1): 011701 doi: 10.1063/5.0038929
    [34]
    Du X, Martins JR. Super resolution generative adversarial networks for multi-fidelity pressure distribution prediction//AIAA Scitech 2023 Forum, 2023
    [35]
    赵旋, 张伟伟, 邓子辰. 融入压力分布信息的气动力建模方法. 力学学报, 2022, 54(9): 2616-2626 (Zhao Xuan, Zhang Weiwei, Deng Zichen. Aerodynamic modeling method incorporating pressure distribution information. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(9): 2616-2626 (in Chinese) doi: 10.6052/0459-1879-22-170

    Zhao Xuan, Zhang Weiwei, Deng Zichen. Aerodynamic modeling method incorporating pressure distribution information. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(9): 2616-2626 (in Chinese) doi: 10.6052/0459-1879-22-170
    [36]
    Ribeiro MD, Stradtner M, Bekemeyer P. Unsteady reduced order model with neural networks and flight-physics-based regularization for aerodynamic applications. Computers & Fluids, 2023, 264: 105949
    [37]
    Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks, 1989, 2(5): 359-366 doi: 10.1016/0893-6080(89)90020-8
    [38]
    He K, Zhang X, Ren S, et al. Deep residual learning for image recognition//IEEE Conference on Computer Vision and Pattern Recognition, 2016
    [39]
    Verónica BC, Amparo AB. Ensembles for feature selection: A review and future trends. Information Fusion, 2019, 52: 1-12 doi: 10.1016/j.inffus.2018.11.008
    [40]
    Kanter JM, Veeramachaneni K. Deep feature synthesis: Towards automating data science endeavors//IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2015
    [41]
    Sun X, Cao W, Liu Y, et al. High Reynolds number airfoil turbulence modeling method based on machine learning technique. Computers & Fluids, 2022, 236: 105298
    [42]
    何磊, 郭勇颜, 曾志春等. 国家数值风洞(NNW)软件自动化集成与测试平台设计与研发. 空气动力学学报, 2020, 38(6): 1158-1164 (He Lei, Guo Yongyan, Zeng Zhichun, et al. Design and development of software automated continuous integration and testing platform for national numerical wind tunnel project. Acta Aerodynamica Sinica, 2020, 38(6): 1158-1164 (in Chinese)

    He Lei, Guo Yongyan, Zeng Zhichun, et al. Design and development of software automated continuous integration and testing platform for national numerical wind tunnel project. Acta Aerodynamica Sinica, 2020, 38(6): 1158-1164 (in Chinese)
    [43]
    Kulfan B, Bussoletti J. Fundamental parameteric geometry representations for aircraft component shapes//11th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, 2006
    [44]
    李凯, 杨静媛, 高传强等. 基于POD和代理模型的静气动弹性分析方法. 力学学报, 2023, 55(2): 299-308 (Li Kai, Yang Jingyuan, Gao Chuanqiang, et al. Static aeroelastic analysis based on proper orthogonal decomposition and surrogate model. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(2): 299-308 (in Chinese)

    Li Kai, Yang Jingyuan, Gao Chuanqiang, et al. Static aeroelastic analysis based on proper orthogonal decomposition and surrogate model. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(2): 299-308 (in Chinese)
    [45]
    Zhang W, Peng X, Kou J, et al. Heterogeneous data-driven aerodynamic modeling based on physical feature embedding. Chinese Journal of Aeronautics, 2023, in press
    [46]
    Immordino G, Ronch AD, Righi M. Deep–learning framework for aircraft aerodynamics prediction//AIAA Aviation 2023 Forum, 2023
  • Related Articles

    [1]Jiang Shouyan, Deng Wangtao, Sun Liguo, Du Chengbin. DATA-DRIVEN CRACK IDENTIFICATION MODELS IN SEMI-INFINITE MEDIA[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(6): 1727-1739. DOI: 10.6052/0459-1879-23-550
    [2]Zhou Rui, Xiong Yukai, Chu Jielei, Kan Qianhua, Kang Guozheng, Zhang Xu. PARAMETER IDENTIFICATION OF NONLOCAL CRYSTAL PLASTIC MODEL BASED ON MACHINE LEARNING AND GENETIC ALGORITHM[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(3): 751-762. DOI: 10.6052/0459-1879-23-479
    [3]Wang Xucheng, Li Wenkai, Ai Fei, Liu Zhibing, Zhang Yuantao. DATA-DRIVEN PLASMA SIMULATION ON ATMOSPHERIC RADIO FREQUENCY DISCHARGE PLASMAS[J]. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(12): 2900-2912. DOI: 10.6052/0459-1879-23-347
    [4]Shi Guanghui, Jia Yibo, Hao Wenyu, Wu Wenhua, Li Qiang, Lin Ye, Du Zongliang. OPTIMAL DESIGN OF RUDDER STRUCTURES BASED ON DATA-DRIVEN METHOD[J]. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(11): 2577-2587. DOI: 10.6052/0459-1879-23-187
    [5]Qiu Hongyun, Wang Zhixia, Ding Bei, Wang Wei. DATA-DRIVEN MODELING AND APPLICATION OF VIBRATION ENERGY HARVESTER WITH DOUBLE FILM[J]. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(10): 2189-2198. DOI: 10.6052/0459-1879-23-358
    [6]Liu Yifan, Zhang Jie, Zhang Xinyu, Wang Zhiyong, Wang Zhihua. PREDICTION OF CONCRETE MESO-MODEL COMPRESSION STRESS-STRAIN CURVE BASED ON “AM-GOOGLENET + BP” COMBINED DATA-DRIVEN METHODS[J]. Chinese Journal of Theoretical and Applied Mechanics, 2023, 55(4): 925-938. DOI: 10.6052/0459-1879-22-506
    [7]He Jiaqi, Jia Xiaoxuan, Wu Weida, Zhong Jiehua, Luo Yangjun. P-CS UNCERTAINTY QUANTIFICATION MODEL AND ITS PERFORMANCE DATA-DRIVEN UPDATING METHOD[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(10): 2808-2824. DOI: 10.6052/0459-1879-22-173
    [8]Yao Qi, Li Quantong, Du Qiuyue, Chen Song, Wang Xiangyu, Zhan Weiliang, Yin Siwei. RESEARCH ON TRAILING ARM SUSPENSION SYSTEM OF FULL X-BY-WIRE CONTROL CHASSIS BASED ON DATA DRIVE[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(7): 1880-1895. DOI: 10.6052/0459-1879-21-624
    [9]Zhao Yaomin, Xu Xiaowei. DATA-DRIVEN TURBULENCE MODELLING BASED ON GENE-EXPRESSION PROGRAMMING[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(10): 2640-2655. DOI: 10.6052/0459-1879-21-391
    [10]Jiang Hao, Wang Bofu, Lu Zhiming. DATA-DRIVEN SPARSE IDENTIFICATION OF GOVERNING EQUATIONS FOR FLUID DYNAMICS[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(6): 1543-1551. DOI: 10.6052/0459-1879-21-052

Catalog

    Article Metrics

    Article views (161) PDF downloads (69) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return