流体力学深度学习建模技术研究进展

doi:10.7527/S1000-6893.2020.24779

Abstract

Abstract: Deep learning technology has brought subversive changes in many fields, such as image processing, language translation, disease diagnosis, and game competition. Due to the characteristics of high dimensionality, strong nonlinearity and large amount of data, fluid mechanics is an important area where deep learning is good at and could bring out innovation in research paradigm. At present, the deep learning technology has been initially applied in the field of fluid mechanics, and its application potential has been gradually confirmed. Based on the deep learning technology for fluid mechanics and the recent research results of our group, this paper discusses the deep learning modeling technology for fluid mechanics and its latest progress. First, the basic theory of the deep learning technology is introduced, and the mathematics behind the deep learning methods commonly used in fluid mechanics modeling are explained. Then, the progress of the deep learning technology involved in several typical application scenarios of artificial intelligence of fluid mechanics, such as basic control equation, flow field reconstruction, and feature modeling and application, are introduced. Finally, the challenges and future development trend of the deep learning modeling technology of fluid mechanics are discussed.

Key words: deep learning, fluid mechanics, reduced order method, flow field reconstruction, extraction of geometry information, modeling of nonlinear system

CLC Number:

V211.3

WANG Yixing, HAN Renkun, LIU Ziyang, ZHANG Yang, CHEN Gang. Progress of deep learning modeling technology for fluid mechanics[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524779-524779.

References

[1] SLOTNICK J, KHODADOUST A, ALONSO J, et al. CFD vision 2030 study:a path to revolutionary computational aerosciences:NASA/CR-2014-218178[R]. Washington,D.C.:NASA, 2014.
[2] 周铸, 黄江涛, 黄勇, 等. CFD技术在航空工程领域的应用、挑战与发展[J]. 航空学报, 2017, 38(3):020891. ZHOU Z, HUANG J T, HUANG Y, et al. CFD technology in aeronautic engineering field:Applications, challenges and development[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(3):020891(in Chinese).
[3] JAMESON A, VASSBERG J. Computational fluid dynamics for aerodynamic design-Its current and future impact[C]//39th Aerospace Sciences Meeting and Exhibit, 2001.
[4] 张淼, 刘铁军, 马涂亮, 等. 基于CFD方法的大型客机高速气动设计[J]. 航空学报, 2016, 37(1):244-254. ZHANG M, LIU T J, MA T L, et al. High speed aerodynamic design of large civil transporter based on CFD method[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(1):244-254(in Chinese).
[5] RAISSI M, WANG Z, TRIANTAFYLLOU M S, et al. Deep learning of vortex-induced vibrations[J]. Journal of Fluid Mechanics, 2019, 861:119-137.
[6] HUANG J, LIU H, CAI W. Online in situ prediction of 3-D flame evolution from its history 2-D projections via deep learning[J]. Journal of Fluid Mechanics, 2019, 875, R2.
[7] DOWELL E H. Eigenmode analysis in unsteady aerodynamics-reduced-order models[J]. AIAA Journal, 1996, 34(8):1578-1583.
[8] SCHMID P J. Dynamic mode decomposition of numerical and experimental data[J]. Journal of Fluid Mechanics, 2010, 656:5-28.
[9] KUTZ J N. Deep learning in fluid dynamics[J]. Journal of Fluid Mechanics, 2017, 814:1-4.
[10] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436.
[11] XIONG H Y, ALIPANAHI B, LEE L J, et al. The human splicing code reveals new insights into the genetic determinants of disease[J]. Science, 2015, 347(6218):1254806.
[12] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5):359-366.
[13] CYBENKO G. Approximations by superpositions of a sigmoidal function[J]. Mathematics of Control, Signals and Systems, 1989, 2:183-192.
[14] GOODFELLOW I, BENGIO Y, COURVILLE A. Deep learning[M]. Massachusetts:The MIT Press, 2016.
[15] PARISH E J, DURAISAMY K. A paradigm for data-driven predictive modeling using field inversion and machine learning[J]. Journal of Computational Physics, 2016, 305:758-774.
[16] SINGH A P, MEDIDA S, DURAISAMY K. Machine-learning-augmented predictive modeling of turbulent separated flows over airfoils[J]. AIAA Journal, 2017, 55(7):2215-2227.
[17] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems, 2012.
[18] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7):1527-1554.
[19] SAINATH T N, MOHAMED A, KINGSBURY B, et al. Deep convolutional neural networks for LVCSR[C]//2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013.
[20] 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.
[21] DURAISAMY K, IACCARINO G, XIAO H. Turbulence modeling in the age of data[J]. Annual Review of Fluid Mechanics, 2019, 51:357-377.
[22] WANG M, LI H X, CHEN X, et al. Deep learning-based model reduction for distributed parameter systems[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2016, 46(12):1664-1674.
[23] OMATA N, SHIRAYAMA S. A novel method of low-dimensional representation for temporal behavior of flow fields using deep autoencoder[J]. AIP Advances, 2019, 9(1):015006.
[24] MOHAN A T, GAITONDE D V. A deep learning based approach to reduced order modeling for turbulent flow control using LSTM neural networks[DB/OL]. arXiv preprint:1804.09269,2018.
[25] PAWAR S, RAHMAN S, VADDIREDDY H, et al. A deep learning enabler for nonintrusive reduced order modeling of fluid flows[J]. Physics of Fluids, 2019, 31(8):085101.
[26] DENG Z, CHEN Y, LIU Y, et al. Time-resolved turbulent velocity field reconstruction using a long short-term memory (LSTM)-based artificial intelligence framework[J]. Physics of Fluids, 2019, 31(7):075108.
[27] FUKAMI K, FUKAGATA K, TAIRA K. Super-resolution reconstruction of turbulent flows with machine learning[J]. Journal of Fluid Mechanics, 2019, 870:106-120.
[28] GUO 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, 2016.
[29] JIN X, CHENG P, CHEN W L, 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[J]. Physics of Fluids, 2018, 30(4):047105.
[30] SEKAR V, JIANG Q, SHU C, et al. Fast flow field prediction over airfoils using deep learning approach[J]. Physics of Fluids, 2019, 31(5):057103.
[31] MOHAN A, DANIEL D, CHERTKOV M, et al. Compressed convolutional LSTM:An efficient deep learning framework to model high fidelity 3D turbulence[DB/OL]. arXiv preprint:1903.00033,2019.
[32] LEE S, YOU D. Data-driven prediction of unsteady flow over a circular cylinder using deep learning[J]. Journal of Fluid Mechanics, 2019, 879:217-254.
[33] HAN R K, WANG Y, ZHANG Y, et al. A novel spatial-temporal prediction method for unsteady wake flows based on hybrid deep neural network[J]. Physics of Fluids, 2019, 31(12):127101.
[34] RüTTGERS M, LEE S, YOU D. Prediction of typhoon tracks using a generative adversarial network with observational and meteorological data[DB/OL]. arXiv preprint:1812.01943,2018.
[35] MIYANAWALA T, JAIMAN R K. A novel deep learning method for the predictions of current forces on bluff bodies[C]//ASME 37th International Conference on Ocean, Offshore and Arctic Engineering, 2018.
[36] MAO X, JOSHI V, MIYANAWALA T, et al. Data-driven computing with convolutional neural networks for two-phase flows:Application to wave-structure interaction[C]//ASME 37th International Conference on Ocean, Offshore and Arctic Engineering, 2018.
[37] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[38] HINTON G, SALAKHUTDINOV R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[39] VERSTEEG H K, MALALASEKERA W. An introduction to computational fluid dynamics:the finite volume method[M]. Pearson Education, 2007.
[40] 陶文铨. 数值传热学[M]. 西安:西安交通大学出版社, 2001. TAO W Q. Numerical heat transfer[M]. Xi'an:Xi'an Jiaotong University Press, 2001(in Chinese).
[41] GOODFELLOW I J, SHLENS J, SZEGEDY C. Explaining and harnessing adversarial examples[C]//ICML, 2015.
[42] SZEGEDY C, ZAREMBA W, SUTSKEVER I, et al. Intriguing properties of neural networks[DB/OL]. arXiv preprint:1312.6199,2013.
[43] RAISSI M, YAZDANI A, KARNIADAKIS G E. Hidden fluid mechanics:Learning velocity and pressure fields from flow visualizations[J]. Science, 2020, 367(6481):1026-1030.
[44] RUDY S H, BRUNTON S L, PROCTOR J L, et al. Data-driven discovery of partial differential equations[J]. Science Advances, 2017, 3(4):e1602614.
[45] RAISSI M. Deep hidden physics models:Deep learning of nonlinear partial differential equations[J]. The Journal of Machine Learning Research, 2018, 19(1):932-955.
[46] BASDEVANT C, DEVILLE M, HALDENWANG P, et al. Spectral and finite difference solutions of Burgers equation[J]. Computers & Fluids, 1986, 14(1):23-41.
[47] DURAISAMY K, IACCARINO G, XIAO H. Turbulence modeling in the age of data[J]. Annual Review of Fluid Mechanics, 2019, 51:357-377.
[48] LUO S, CUI J, VELLAKAL M, et al. Review and examination of input feature preparation methods and machine learning models for turbulence modeling[DB/OL]. arXiv preprint:2001.05485,2020.
[49] YANG M, XIAO Z. Improving the k-ω-γ-Ar transition model by the field inversion and machine learning framework[J]. Physics of Fluids, 2020, 32(6):064101.
[50] MAULIK R, SAN O, JACOB J D, et al. Sub-grid scale model classification and blending through deep learning[J]. Journal of Fluid Mechanics, 2019, 870:784-812.
[51] ZHU L, ZHANG W W, KOU J, et al. Machine learning methods for turbulence modeling in subsonic flows around airfoils[J]. Physics of Fluids, 2019, 31(1):015105.
[52] MAULIK R, SAN O, RASHEED A, et al. Subgrid modelling for two-dimensional turbulence using neural networks[J]. Journal of Fluid Mechanics, 2019, 858:122-144.
[53] WU J L, XIAO H, PATERSON E. Physics-informed machine learning approach for augmenting turbulence models:A comprehensive framework[J]. Physical Review Fluids, 2018, 3(7):074602.
[54] XIE C, WANG J, LI H, et al. Artificial neural network mixed model for large eddy simulation of compressible isotropic turbulence[J]. Physics of Fluids, 2019, 31(8):085112.
[55] KOU J Q, ZHANG W W. Multi-kernel neural networks for nonlinear unsteady aerodynamic reduced-order modeling[J]. Aerospace Science and Technology, 2017, 67:309-326.
[56] 张伟伟, 朱林阳, 刘溢浪, 等. 机器学习在湍流模型构建中的应用进展[J]. 空气动力学学报, 2019, 37(3):444-454. ZHANG W W, ZHU L Y, LIU Y L, et al. Progresses in the application of machine learning in turbulence modeling[J]. Acta Aerodynamica Sinica, 2019, 37(3):444-454(in Chinese).
[57] WANG J X, WU J L, XIAO H. Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data[J]. Physical Review Fluids, 2017, 2(3):034603.
[58] XIAO H, WU J L, WANG J X, et al. Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations:A data-driven, physics-informed Bayesian approach[J]. Journal of Computational Physics, 2016, 324:115-136.
[59] TI Z, DENG X W, YANG H. Wake modeling of wind turbines using machine learning[J]. Applied Energy, 2020, 257:114025.
[60] WANG J X, HUANG J, DUAN L, et al. Prediction of Reynolds stresses in high-Mach-number turbulent boundary layers using physics-informed machine learning[J]. Theoretical and Computational Fluid Dynamics, 2019, 33(1):1-19.
[61] WU J, XIAO H, SUN R, et al. Reynolds-averaged Navier-Stokes equations with explicit data-driven Reynolds stress closure can be ill-conditioned[J]. Journal of Fluid Mechanics, 2019, 869:553-586.
[62] WU J L, WANG J X, XIAO H, et al. A priori assessment of prediction confidence for data-driven turbulence modeling[J]. Flow, Turbulence and Combustion, 2017, 99(1):25-46.
[63] ZHANG X, WU J, COUTIER-DELGOSHA O, et al. Recent progress in augmenting turbulence models with physics-informed machine learning[J]. Journal of Hydrodynamics, 2019, 31(6):1153-1158.
[64] LING J, KURZAWSKI A, TEMPLETON J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance[J]. Journal of Fluid Mechanics, 2016, 807:155-166.
[65] CRUZ M A, THOMPSON R L, SAMPAIO L E, et al. The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling[J]. Computers & Fluids, 2019, 192:104258.
[66] KAANDORP M L, DWIGHT R P. Data-driven modelling of the Reynolds stress tensor using random forests with invariance[J]. Computers & Fluids, 2020, 202:104497.
[67] WEATHERITT J, SANDBERG R. The development of algebraic stress models using a novel evolutionary algorithm[J]. International Journal of Heat and Fluid Flow, 2017, 68:298-318.
[68] ZHANG Z, SONG X D, YE S R, et al. Application of deep learning method to Reynolds stress models of channel flow based on reduced-order modeling of DNS data[J]. Journal of Hydrodynamics, 2019, 31(1):58-65.
[69] LING J, TEMPLETON J. Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier-Stokes uncertainty[J]. Physics of Fluids, 2015, 27(8):085103.
[70] MAULIK R, SHARMA H, PATEL S, et al. Accelerating RANS turbulence modeling using potential flow and machine learning[DB/OL]. arXiv preprint:1910.10878,2019.
[71] ZHANG Y, SUNG W J, MAVRIS D N. Application of convolutional neural network to predict airfoil lift coefficient[C]//2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 2018.
[72] 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.
[73] WANG Z, XIAO D, FANG F, et al. Model identification of reduced order fluid dynamics systems using deep learning[J]. International Journal for Numerical Methods in Fluids, 2018, 86(4):255-268.
[74] LEE S, YOU D. Prediction of laminar vortex shedding over a cylinder using deep learning[DB/OL]. arXiv preprint:1712.07854,2017.
[75] 王怡星, 李东风, 陈刚. 一种基于流场特征的气动力深度学习降阶模型[C]//第四届全国非定常空气动力学学术会议论文集, 2018. WANG Y X, LI D F, CHEN G. A deep learning reduced order model of aerodynamics based on flow field characteristics[C]//Proceedings of the 4th National Conference on Unsteady Aerodynamics, 2018(in Chinese).
[76] GUO 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, 2016:481-490.
[77] 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:2004.08826,2020.
[78] SHYY W, AONO R, CHIMAKURTHI R K, et al. Recent progress in flapping wing aerodynamics and aeroelasticity[J]. Progress in Aerospace, 2010, 46(7):284-327.
[79] HAN R K, ZHANG Z, WANG Y, et al. Hybrid deep neural network based prediction method for unsteady flows with moving boundaries[DB/OL]. arXiv preprint:2006.00690, 2020.
[80] MATHIEU M, COUPRIE C, LECUN Y. Deep multi-scale video prediction beyond mean square error[DB/OL]. arXiv preprint:1511.05440, 2015.
[81] YAO Z, SUNG W J, MAVRIS D N. Application of convolutional neural network to predict airfoil lift coefficient[C]//2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 2018.
[82] SALEHIPOUR H, PELTIER W R. Deep learning of mixing by two ‘atoms’ of stratified turbulence[DB/OL]. arXiv preprint:1809.06499, 2018.
[83] 李凯, 寇家庆, 张伟伟. 基于深度神经网络的非定常气动力建模[C]//第四届全国非定常空气动力学学术会议论文集, 2018. LI K, KOU J Q, ZHANG W W. Unsteady aerodynamic modeling based on deep neural network[C]//Proceedings of the 4th National Conference on Unsteady Aerodynamics, 2018(in Chinese).
[84] ZHENG J, SHEN S, JIANG T, et al. Deep neural networks design and analysis for automatic phase pickers from three-component microseismic recordings[J]. Geophysical Journal International, 2020, 220(1):323-334.
[85] 罗金梅, 罗建, 李艳梅, 等. 基于多特征融合CNN的人脸识别算法研究[J]. 航空计算技术, 2019(3):40-45. LUO J M, LUO J, LI Y M, et al. Face recognition algorithm based on multi-feature fusion convolution neural network[J]. Aviation Computing Technology, 2019(3):40-45(in Chinese).
[86] XIAO Z L, YI N W, YING H Y. Fault diagnosis based on sparse semi-supervised gan model[C]//2020 Chinese Control And Decision Conference (CCDC), 2020:5620-5624.

Progress of deep learning modeling technology for fluid mechanics

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[12]	ZHAN Qingliang, BAI Chunjin, ZHANG Ning, GE Yaojun. Feature extraction method of flow around airfoil based on time-history convolutional autoencoder [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(11): 526531-526531.
[13]	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.
[14]	CAI Guobiao, ZHANG Baiyi, HE Bijiao, WENG Huiyan, LIU Lihui. Intelligent computation of vacuum plume [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(10): 527352-527352.
[15]	LI Hongguang, WANG Fei, DING Wenrui. Survey on multi-task learning for object classification and recognition [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(1): 24889-024889.