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.
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
.
DOI: 10.7527/S1000-6893.2022.26747
[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.
CJA