快速预测跨声速流场的深度学习方法

doi:10.7527/S1000-6893.2022.26747

Abstract

Abstract: The computational cost and memory requirements for Computational Fluid Dynamics (CFD) codes can be demanding for engineering design. Reconstruction of subsonic aerodynamic flow fields based on deep learning has been highly successful. Compared with the subsonic flow field, the transonic flow field has a larger gradient and higher geometric sensitivity, resulting in limited accuracy of the model based on the traditional encoder-decoder architecture. A deep Convolutional Neural Network (CNN) based on the U-Net architecture is therefore established to quickly predict the transonic flow field. High-fidelity CFD solutions to different geometric airfoils are used as the training dataset, while the neural network takes the Signed Distance Function (SDF) representing the airfoil geometry as input, outputting the airfoil peripheral pressure field and velocity field. The CNN model based on the U-Net architecture automatically detects multi-scale low-dimensional features and reflects them in the output results. Compared with the benchmark encoder-decoder architecture, the error of the new U-Net architecture is reduced by about 24%. Gradient sharpening enhances the visualization of the flow field while further reducing the error by approximately 10%. The effectiveness of the neural network in predicting unseen airfoil flow fields is explored, and the error of our model on the velocity field and pressure field is maintained at 1.013% and 4.625%, respectively.

Key words: computational fluid dynamics, deep learning, U-Net, convolutional neural network, gradient sharpening

CLC Number:

V211

YI Jianmiao, DENG Feng, QIN Ning, LIU Xueqiang. Fast prediction of transonic flow field using deep learning method[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(11): 526747-526747.

References

[1] DURAISAMY K, IACCARINO G, XIAO H. Turbulence modeling in the age of data[J]. Annual Review of Fluid Mechanics, 2019, 51:357-377.
[2] BRUNTON S L, NOACK B R, KOUMOUTSAKOS P. Machine learning for fluid mechanics[J]. Annual Review of Fluid Mechanics, 2020, 52:477-508.
[3] DOWELL E H. Eigenmode analysis in unsteady aerodynamics:Reduced order models[J]. AIAA Journal, 1996, 34(8):1578-1583.
[4] SCHMID P J. Dynamic mode decomposition of numerical and experimental data[J]. Journal of Fluid Mechanics, 2010, 656:5-28.
[5] HU L W, ZHANG J, XIANG Y, et al. Neural networks-based aerodynamic data modeling:A comprehensive review[J]. IEEE Access, 2020, 8:90805-90823.
[6] SCHMIDHUBER J. Deep learning in neural networks:An overview[J]. Neural Networks, 2015, 61:85-117.
[7] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5):359-366.
[8] TAYLOR G W, FERGUS R, LECUN Y, et al. Convolutional learning of spatio-temporal features[C]//Proceedings of the 11th European Conference on Computer Vision:Part VI. New York:ACM, 2010:140-153.
[9] YANG C, YANG X B, XIAO X Y. Data-driven projection method in fluid simulation[J]. Computer Animation and Virtual Worlds, 2016, 27(3-4):415-424.
[10] TOMPSON J, SCHLACHTER K, SPRECHMANN P, et al. Accelerating eulerian fluid simulation with convolutional networks[C]//Proceedings of the 34th International Conference on Machine Learning-Volume 70. New York:ACM, 2017:3424-3433.
[11] MILANO M, KOUMOUTSAKOS P. Neural network modeling for near wall turbulent flow[J]. Journal of Computational Physics, 2002, 182(1):1-26.
[12] LING J L, KURZAWSKI A, TEMPLETON J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance[J]. Journal of Fluid Mechanics, 2016, 807:155-166.
[13] ZHU L Y, ZHANG W W, KOU J Q, et al. Machine learning methods for turbulence modeling in subsonic flows around airfoils[J]. Physics of Fluids, 2019, 31(1):015105.
[14] MIYANAWALA T P, JAIMAN R K. An efficient deep learning technique for the navier-stokes equations:Application to unsteady wake flow dynamics[DB/OL]. arXiv preprint:1710.09099, 2017.
[15] ZHANG Y, SUNG W J, MAVRIS D. Application of convolutional neural network to predict airfoil lift coefficient[C]//2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, 2018.
[16] GUO X X, LI W, IORIO F. Convolutional neural networks for steady flow approximation[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2016:481-490.
[17] BHATNAGAR S, AFSHAR Y, PAN S W, et al. Prediction of aerodynamic flow fields using convolutional neural networks[J]. Computational Mechanics, 2019, 64(2):525-545.
[18] RIBEIRO M D, REHMAN A, AHMED S, et al. DeepCFD:Efficient steady-state laminar flow approximation with deep convolutional neural networks[DB/OL]. arXiv preprint:2004.08826v2, 2020.
[19] SEKAR V, JIANG Q H, SHU C, et al. Fast flow field prediction over airfoils using deep learning approach[J]. Physics of Fluids, 2019, 31(5):057103.
[20] SEKAR V, ZHANG M Q, SHU C, et al. Inverse design of airfoil using a deep convolutional neural network[J]. AIAA Journal, 2019, 57(3):993-1003.
[21] THUEREY N, WEIßENOW K, PRANTL L, et al. Deep learning methods for Reynolds-averaged navier-stokes simulations of airfoil flows[J]. AIAA Journal, 2020, 58(1):25-36.
[22] TANGSALI K, KRISHNAMURTHY V R, HASNAIN Z. Generalizability of convolutional encoder-decoder networks for aerodynamic flow-field prediction across geometric and physical-fluidic variations[J]. Journal of Mechanical Design, 2021, 143(5):051704.
[23] HUI X Y, BAI J Q, WANG H, et al. Fast pressure distribution prediction of airfoils using deep learning[J]. Aerospace Science and Technology, 2020, 105:105949.
[24] WU H Z, LIU X J, AN W, et al. A deep learning approach for efficiently and accurately evaluating the flow field of supercritical airfoils[J]. Computers & Fluids, 2020, 198:104393.
[25] DURU C, ALEMDAR H, BARAN Ö U. CNNFOIL:Convolutional encoder decoder modeling for pressure fields around airfoils[J]. Neural Computing and Applications, 2021, 33(12):6835-6849.
[26] RONNEBERGER O, FISCHER P, BROX T. U-net:Convolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science. Cham:Springer International Publishing, 2015:234-241.
[27] COOK P, FIRMIN M, MCDONALD M. Aerofoil RAE 2822:Pressure distributions,and boundary layer and wake measurements:AGARD-AR-138[R]. Research and Technology Organisation, 1979.

Fast prediction of transonic flow field using deep learning method

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Jianling QIAO, Zhonghua HAN, Yulin DING, Wenping SONG, Bifeng SONG. Effects of stratified atmospheric turbulence on farfield sonic boom propagation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(2): 626350-626350.
[2]	SU Lingfei, HUA Yongzhao, DONG Xiwang, REN Zhang. Human-UAV swarm multi-modal intelligent interaction methods [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(S1): 727001-727001.
[3]	CAO Ming, WANG Peng, ZUO Hongfu, ZENG Haijun, SUN Jianzhong, YANG Weidong, WEI Fang, CHEN Xuefeng. Current status, challenges and opportunities of civil aero-engine diagnostics & health management Ⅱ: Comprehensive off-board diagnosis, life management and intelligent condition based MRO [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(9): 625574-625574.
[4]	LIU Jiaqi, FENG Yunwen, LU Cheng, XUE Xiaofeng, PAN Weihuang. Safety analysis of aero-engine operation based on intelligent neural network [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(9): 625375-625375.
[5]	HAN Songyu, SHAO Haidong, JIANG Hongkai, ZHANG Xiaoyang. Intelligent fault diagnosis of aero-engine high-speed bearings using enhanced CNN [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(9): 625479-625479.
[6]	ZHAO Liangyu, LI Dan, ZHAO Chenyue, JIANG Fei. Some achievements on detection methods of UAV autonomous landing markers [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(9): 25882-025882.
[7]	KANG Yuxiang, CHEN Guo, WEI Xunkai, ZHOU Lei. Deep residual hedging network and its application in fault diagnosis of rolling bearings [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 625201-625201.
[8]	XIAHOU Tangfan, CHEN Jiangtao, SHAO Zhidong, WU Xiaojun, LIU Yu. Model validation metrics for CFD numerical simulation under aleatory and epistemic uncertainty [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 25716-025716.
[9]	SUN Canfei, HUANG Linran, SHEN Yong. Fault diagnosis of helicopter planetary gear transmission system under complex operating conditions [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 625480-625480.
[10]	LIU Zichao, WANG Jiang, HE Shaoming, LI Yufei. A computational guidance algorithm for impact angle control based on predictor-corrector concept [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 325433-325433.
[11]	SHAO Yiwei, CHEN Jiayu, LIN Cuiying, WAN Cheng, GE Hongjuan, SHI Zhilong. Gearbox fault diagnosis with small training samples: An improved deep forest based method [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 625429-625429.
[12]	LYU Shuaishuai, YANG Yu, WANG Binwen, YIN Chenfei. A crack identification method of aircraft structure based on improved FaceNet [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 525463-525463.
[13]	LIU Tianyuan, ZHENG Hangbin, YANG Changqi, BAO Jinsong, WANG Junliang, GU Jun. Explainable deep learning method for laser welding defect detection [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(4): 524961-524961.
[14]	KANG Shuo, KE Zhenzheng, WANG Xuan, ZHU Weidong. Detection method of defects in automatic fiber placement based on fusion of infrared and visible images [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(3): 425187-425187.
[15]	CHEN Guangqiang, DOU Guohui, WEI Haogong, ZOU Xin, LI Qi, LIU Zhou, ZHOU Weijiang. Air data sensing technology of Mars probe [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(3): 626619-626619.