机器学习在流动控制领域的应用及发展趋势

doi:10.7527/S1000-6893.2020.24686

Abstract

Abstract: As a multidisciplinary field in fluid mechanics, flow control has played a key role in both scientific research and engineering applications. Due to complicated features of flow systems such as strong nonlinearity, flow control, especially closed-loop control, has been a challenging issue in the past decades. Recently, the rapid developing machine learning has brought new methods, new perspectives, and new views to diverse fields, and also to flow control. This article reviews three distinct ideas that involve machine learning into flow control, so as to demonstrate an overall view of machine learning in flow control, and furthermore, to outline some trends for this field.

Key words: flow control, machine learning, reduced order modeling, genetic programming, deep reinforcement learning

CLC Number:

V211.3

REN Feng, GAO Chuanqiang, TANG Hui. Machine learning for flow control: Applications and development trends[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524686-524686.

References

[1] 马付良, 曾志翔, 高义民, 等. 仿生表面减阻的研究现状与进展[J]. 中国表面工程, 2016, 29(1):7-15. MA F L, ZENG Z X, GAO Y M, et al. Research status and progress of bionic surface drag reduction[J]. China Surface Engineering, 2016, 29(1):7-15(in Chinese).
[2] 刘沛清, 马利川, 屈秋林, 等. 低雷诺数下翼型层流分离泡及吹吸气控制数值研究[J]. 空气动力学学报, 2013, 31(4):518-524. LIU P Q, MA L C, QU Q L, et al. Numerical investigation of the laminar separation bubble control by blowing/suction on an airfoil at low Re number[J]. Acta Aerodynamica Sinica, 2013, 31(4):518-524(in Chinese).
[3] 罗振兵, 夏智勋. 合成射流技术及其在流动控制中应用的进展[J]. 力学进展, 2005, 35(2):221-234. LUO Z B, XIA Z X. Advances in synthetic jet technology and applications in flow control[J]. Advances in Mechanics, 2005, 35(2):221-234(in Chinese).
[4] 吴云, 李应红. 等离子体流动控制研究进展与展望[J]. 航空学报, 2015, 36(2):381-405. WU Y, LI Y H. Progress and outlook of plasma flow control[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36(2):381-405(in Chinese).
[5] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016. ZHOU Z H. Machine learning[M]. Beijing:Tsinghua University Press, 2016(in Chinese).
[6] BRUNTON S L, NOACK B R, KOUMOUTSAKOS P. Machine learning for fluid mechanics[J]. Annual Review of Fluid Mechanics, 2020, 52(1):477-508.
[7] CAI S Z, ZHOU S C, XU C, et al. Dense motion estimation of particle images via a convolutional neural network[J]. Experiments in Fluids, 2019, 60(4):16.
[8] ZHU L, ZHANG W, KOU J, et al. Machine learning methods for turbulence modeling in subsonic flows around airfoils[J]. Phys Fluids, 2019, 31(1):015105.
[9] DURAISAMY K, IACCARINO G, XIAO H. Turbulence modeling in the age of data[J]. Annual Review of Fluid Mechanics, 2019, 51(1):357-377.
[10] VIQUERAT J, RABAULT J, KUHNLE A, et al. Direct shape optimization through deep reinforcement learning[DB/OL]. arXiv preprint:190809885,2019.
[11] REN F, HU H B, TANG H. Active flow control using machine learning:A brief review[J]. Journal of Hydrodynamics, 2020, 32(2):247-253.
[12] RABAULT J, REN F, ZHANG W, et al. Deep reinforcement learning in fluid mechanics:A promising method for both active flow control and shape optimization[J]. Journal of Hydrodynamics, 2020, 32(2):234-246.
[13] 陈刚, 李跃明, 闫桂荣, 等. 基于降阶模型的气动弹性主动控制律设计[J]. 航空学报, 2010, 31(1):12-18. CHEN G, LI Y M, YAN G R, et al. Design of active control law for aeroelastic systems via reduced order models[J]. Acta Aeronautica et Aeronautica Sinica, 2010, 31(1):12-18(in Chinese).
[14] AHUJA S, ROWLEY C W. Feedback control of unstable steady states of flow past a flat plate using reduced-order estimators[J]. Journal of Fluid Mechanics, 2010, 645:447-478.
[15] FLINOIS T L B, MORGANS A S. Feedback control of unstable flows:a direct modelling approach using the eigensystem realisation algorithm[J]. Journal of Fluid Mechanics, 2016, 793:41-78.
[16] GAO C Q, ZHANG W W. Transonic aeroelasticity:A new perspective from the fluid mode[J]. Progress in Aerospace Sciences, 2020, 113:100596.
[17] GAO C, ZHANG W W, KOU J, et al. Active control of transonic buffet flow[J]. Journal of Fluid Mechanics, 2017, 824:312-351.
[18] GLAZ B, LIU L, FRIEDMANN P P. Reduced-order nonlinear unsteady aerodynamic modeling using a surrogate-based recurrence framework[J]. AIAA Journal, 2010, 48(10):2418-2429.
[19] LIU H J, HU H Y, ZHAO Y H, et al. Efficient reduced-order modeling of unsteady aerodynamics robust to flight parameter variations[J]. Journal of Fluids and Structures, 2014, 49:728-741.
[20] ZHANG W W, WANG B, YE Z Y, et al. Efficient method for limit cycle flutter analysis based on nonlinear aerodynamic reduced-order models[J]. AIAA Journal, 2012, 50(5):1019-1028.
[21] MANNARINO A, MANTEGAZZA P. Nonlinear aeroelastic reduced order modeling by recurrent neural networks[J]. Journal of Fluids and Structures, 2014, 48:103-121.
[22] WINTER M, BREITSAMTER C. Neurofuzzy-model-based unsteady aerodynamic computations across varying freestream conditions[J]. AIAA Journal, 2016,54(9):2705-2720.
[23] HUANG R, HU H Y, ZHAO Y. Nonlinear reduced-order modeling for multiple-input/multiple-output aerodynamic systems[J]. AIAA Journal, 2014, 52(6):1219-1231.
[24] KOU J, ZHANG W W, YIN M. Novel Wiener models with a time-delayed nonlinear block and their identification[J]. Nonlinear Dynamics, 2016, 85(4):2389-2404.
[25] MANNARINO A, DOWELL E H. Reduced-order models for computational-fluid-dynamics-based nonlinear aeroelastic problems[J]. AIAA Journal, 2015, 53(9):2671-2685.
[26] KOU J, ZHANG W W. Layered reduced-order models for nonlinear aerodynamics and aeroelasticity[J]. Journal of Fluids and Structures, 2017, 68:174-193.
[27] KOU J, ZHANG W. A hybrid reduced-order framework for complex aeroelastic simulations[J]. Aerospace science and technology, 2019, 84:880-894.
[28] LI K, KOU J, ZHANG W W. Deep neural network for unsteady aerodynamic and aeroelastic modeling across multiple Mach numbers[J]. Nonlinear Dynamics, 2019, 96(3):2157-77.
[29] HAN R, WANG Y, ZHANG Y, et al. A novel spatial-temporal prediction method for unsteady wake flows based on hybrid deep neural network[J]. Phys Fluids, 2019, 31(12):127101.
[30] WU H, 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.
[31] KOZA J R. Genetic programming:On the programming of computers by means of natural selection[M]. Cambridge:MIT Press, 1992.
[32] NOACK B, PONS-PRATS J, PERIAUX J, et al. Turbulent separated shear flow control by surface plasma actuator:Experimental optimization by genetic algorithm approach[J]. Experiments in Fluids, 2016, 57:22.
[33] MINELLI G, DONG T, NOACK B, et al. Upstream actuation for bluff-body wake control driven by a genetically inspired optimization[J]. Journal of Fluid Mechanics, 2020, 893:A1.
[34] NAGARAJ B, MURUGANANTH N. A comparative study of PID controller tuning using GA, EP, PSO and ACO[C]//Proceedings of the 2010 International Conference On Communication Control And Computing Technologies, 2010.
[35] GAUTIER N, AIDER J L, DURIEZ T, et al. Closed-loop separation control using machine learning[J]. Journal of Fluid Mechanics, 2015, 770:442-457.
[36] PAREZANOVIĆ V, LAURENTIE J C, FOURMENT C, et al. Mixing layer manipulation experiment from open-loop forcing to closed-loop machine learning control[J]. Flow Turbulence and Combustion, 2015, 94(1):155-173.
[37] PAREZANOVIĆ V, CORDIER L, SPOHN A, et al. Frequency selection by feedback control in a turbulent shear flow[J]. Journal of Fluid Mechanics, 2016, 797:247-283.
[38] LI R Y, NOACK B R, CORDIER L, et al. Drag reduction of a car model by linear genetic programming control[J]. Experiments in Fluids, 2017, 58:103.
[39] ZHOU Y, FAN D, ZHANG B, et al. Artificial intelligence control of a turbulent jet[DB/OL]. arXiv preprint:200504650,2020.
[40] WU Z, FAN D W, ZHOU Y, et al. Jet mixing optimization using machine learning control[J]. Experiments in Fluids, 2018, 59:131.
[41] REN F, WANG C L, TANG H. Active control of vortex-induced vibration of a circular cylinder using machine learning[J]. Phys Fluids, 2019, 31(9):093601.
[42] ABIODUN O I, JANTAN A, OMOLARA A E, et al. State-of-the-art in artificial neural network applications:A survey[J]. Heliyon, 2018, 4(11):e00938.
[43] SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587):484-489.
[44] SILVER D, SCHRITTWIESER J, SIMONYAN K, et al. Mastering the game of go without human knowledge[J]. Nature, 2017, 550(7676):354-359.
[45] FRANÇOIS-LAVET V, HENDERSON P, ISLAM R, et al. An introduction to deep reinforcement learning[DB/OL]. arXiv preprint:181112560, 2018.
[46] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540):529-533.
[47] GU S, HOLLY E, LILLICRAP T, et al. Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates[C]//Proceedings of the 2017 IEEE International Conference on Robotics and Automation, 2017.
[48] WANG P, CHAN C Y. Formulation of deep reinforcement learning architecture toward autonomous driving for on-ramp merge[C]//Proceedings of the 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017.
[49] LUSCH B, KUTZ J N, BRUNTON S L. Deep learning for universal linear embeddings of nonlinear dynamics[J]. Nature Communications, 2018, 9:4950.
[50] BRUNTON S L, NOACK B R. Closed-loop turbulence control:progress and challenges[J]. Applied Mechanics Reviews, 2015, 67(5):050801.
[51] LEE C, KIM J, BABCOCK D, et al. Application of neural networks to turbulence control for drag reduction[J]. Phys Fluids, 1997, 9(6):1740.
[52] CHOI H, MOIN P, KIM J. Active turbulence control for drag reduction in wall-bounded flows[J]. Journal of Fluid Mechanics, 1994, 262:75-110.
[53] 许春晓. 壁湍流相干结构和减阻控制机理研究[J]. 力学进展, 2015, 45:201504. XU C X. Coherent structures and drag reduction mechanism in wall turbulence[J]. Advances in Mechanics, 2015, 45:201504(in Chinese).
[54] 杨歌. 主动凹坑变形湍流减阻控制方案研究[D]. 北京:清华大学, 2009. YANG G. Study on control schemes for turbulence drag reduction by active dimple deformation[D]. Beijing:Tsinghua University, 2009(in Chinese).
[55] 侯宏, 杨建华. RBF网络用于边界层转捩中抽吸流优化控制[J]. 航空学报, 2002, 23(6):556-559. HOU H, YANG J H. Plant edentification in active control of laminar boundary layer transition by suction using RBF neural network[J]. Acta Aeronautica et Astronautica Sinica, 2002, 23(6):556-559(in Chinese).
[56] RABAULT J, KUCHTA M, JENSEN A, et al. Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control[J]. Journal of Fluid Mechanics, 2019, 865:281-302.
[57] RABAULT J, KUHNLE A. Accelerating deep reinforcement learning strategies of flow control through a multi-environment approach[J]. Phys Fluids, 2019, 31(9):094105.
[58] TANG H, RABAULT J, KUHNLE A, et al. Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning[J]. Phys Fluids, 2020, 32(5):053605.
[59] REN F, RABAULT J, TANG H. Applying deep reinforcement learning to active flow control in turbulent conditions[DB/OL]. arXiv preprint:2006.10683, 2020.
[60] REN F, TANG H. Bluff body uses deep-reinforcement-learning trained active flow control to achieve hydrodynamic stealth[DB/OL]. arXiv preprint:2010.10429, 2020.
[61] BODENSCHATZ E, PESCH W, AHLERS G. Recent developments in Rayleigh-Bénard convection[J]. Annual Review of Fluid Mechanics, 2000, 32(1):709-778.
[62] LOHSE D, XIA K Q. Small-scale properties of turbulent Rayleigh-Bénard convection[J]. Annual Review of Fluid Mechanics, 2010, 42:335-364.
[63] BEINTEMA G, CORBETTA A, BIFERALE L, et al. Controlling rayleigh-bénard convection via reinforcement learning[DB/OL]. arXiv preprint:200314358, 2020.
[64] CICHOS F, GUSTAVSSON K, MEHLIG B, et al. Machine learning for active matter[J]. Nature Machine Intelligence, 2020, 2(2):94-103.
[65] REDDY G, CELANI A, SEJNOWSKI T J, et al. Learning to soar in turbulent environments[J]. Proceedings of the National Academy of Sciences of the United States of America, 2016, 113(33):E4877-E4884.
[66] VERMA S, NOVATI G, KOUMOUTSAKOS P. Efficient collective swimming by harnessing vortices through deep reinforcement learning[J]. Proceedings of the National Academy of Sciences of the United States of America, 2018, 115(23):5849-5854.
[67] COLABRESE S, GUSTAVSSON K, CELANI A, et al. Flow navigation by smart microswimmers via reinforcement learning[J]. Physical Review Letters, 2017, 118(15):158004.
[68] POGGIO T, MHASKAR H, ROSASCO L, et al. Why and when can deep-but not shallow-networks avoid the curse of dimensionality:A review[J]. International Journal of Automation and Computing, 2017, 14(5):503-519.

Machine learning for flow control: Applications and development trends

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Chang WANG, Long HE, Dongxia XU, Min TANG, Shuai MA, Ximing WU. Flow control drag reduction of hub on coaxial rigid rotor aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(9): 529084-529084.
[2]	Honglin ZHANG, Jianjun LUO, Weihua MA. Spacecraft game decision making for threat avoidance of space targets based on machine learning [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(8): 329136-329136.
[3]	Wei XIE, Zhenbing LUO, Yan ZHOU, Qiang LIU, Jianjun WU, Hao DONG. Double wedge shock interaction control using steady jet in hypersonic flow: Experimental study [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(7): 128813-128813.
[4]	Guangjia LI, Hongbo WANG, Kai ZHANG, Zhisheng YI. Lift enhancement and drag reduction technologies of solar powered unmanned aerial vehicles in near space: Review [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(5): 529644-529644.
[5]	Yunpeng CAI, Dapeng ZHOU, Jiangchuan DING. Intelligent collaborative control of UAV swarms with collision avoidance safety constraints [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(5): 529683-529683.
[6]	Shengzhe SHAN, Weiwei ZHANG. Air combat intelligent decision-making method based on self-play and deep reinforcement learning [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(4): 328723-328723.
[7]	Shiqi GAO, Bo DING, Xuzhen XIE, Zheng LI, Lin CHEN, Shouyuan QIAN, Zihan JIAO, Guanghui BAI. Drag reduction mechanism using plasma synthetic jet in high⁃speed flow [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 729373-729373.
[8]	Wang WANG, Caiyan RAO, Cong XU, Siyi LI, Yi DUAN, Jian ZHANG. Control effect of laser energy deposition on supersonic inlet flow [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 729424-729424.
[9]	Xuejian WANG, Yongming WEN, Xiaorong SHI, Ningning ZHANG, Jiexi LIU. Design of hybrid intelligent decision framework for multi⁃agent and multi⁃coupling tasks [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 729770-729770.
[10]	Jinyi MA, Can WANG, Tao XUE, Jianliang AI, Yiqun DONG. Development and illustrative applications of an air combat engagement database [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727538-727538.
[11]	Xizhen GAO, Liang TANG, Huang HUANG. Deep reinforcement learning in autonomous manipulation for celestial bodies exploration: Applications and challenges [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(6): 26762-026762.
[12]	Lei HE, Weiqi QIAN, Kangsheng DONG, Xian YI, Congcong CHAI. Aerodynamic characteristics modeling of iced airfoil based on convolution neural networks [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 126434-126434.
[13]	Weishi CHEN, Jia LIU, Qingbin WANG, Xianfeng LU, Jie ZHANG, Xiaolong CHEN, Yifeng HUANG. Review on technology of bird detection with weather radar [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 26781-026781.
[14]	Pan ZHOU, Jiangtao HUANG, Sheng ZHANG, Gang LIU, Bowen SHU, Jigang TANG. Intelligent air combat decision making and simulation based on deep reinforcement learning [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(4): 126731-126731.
[15]	Jian ZHANG, Min ZHANG, Juan DU, Weiliang HUANG, Chaoqun NIE. Experimental investigation into adaptive Coanda jet control in highly loaded compressor [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(22): 128883-128883.