Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network

doi:10.1088/1674-1056/ac5e98

中国物理B ›› 2022, Vol. 31 ›› Issue (6): 64305-064305.doi: 10.1088/1674-1056/ac5e98

Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network

Hai-Yang Meng(孟海洋)¹, Zi-Xiang Xu(徐自翔)^1,2, Jing Yang(杨京)^1,†, Bin Liang(梁彬)^1,2, and Jian-Chun Cheng(程建春)^1,2

1 Key Laboratory of Modern Acoustics, MOE, Institute of Acoustics, Department of Physics, Nanjing University, Nanjing 210093, China;
2 Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210093, China

收稿日期:2022-01-14 修回日期:2022-03-02 接受日期:2022-03-17 出版日期:2022-05-17 发布日期:2022-06-06
通讯作者: Jing Yang E-mail:yangj@nju.edu.cn
基金资助:
Project supported by the National Key Research and Development Program of China (Grant No. 2017YFA0303700), the National Natural Science Foundation of China (Grants Nos. 12174190, 11634006, 12074286, and 81127901), the Innovation Special Zone of the National Defense Science and Technology, High-Performance Computing Center of Collaborative Innovation Center of Advanced Microstructures, and the Priority Academic Program Development of Jiangsu Higher Education Institutions.

Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network

Hai-Yang Meng(孟海洋)¹, Zi-Xiang Xu(徐自翔)^1,2, Jing Yang(杨京)^1,†, Bin Liang(梁彬)^1,2, and Jian-Chun Cheng(程建春)^1,2

1 Key Laboratory of Modern Acoustics, MOE, Institute of Acoustics, Department of Physics, Nanjing University, Nanjing 210093, China;
2 Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210093, China

Received:2022-01-14 Revised:2022-03-02 Accepted:2022-03-17 Online:2022-05-17 Published:2022-06-06
Contact: Jing Yang E-mail:yangj@nju.edu.cn
Supported by:
Project supported by the National Key Research and Development Program of China (Grant No. 2017YFA0303700), the National Natural Science Foundation of China (Grants Nos. 12174190, 11634006, 12074286, and 81127901), the Innovation Special Zone of the National Defense Science and Technology, High-Performance Computing Center of Collaborative Innovation Center of Advanced Microstructures, and the Priority Academic Program Development of Jiangsu Higher Education Institutions.

摘要/Abstract

摘要： Accurate and fast prediction of aerodynamic noise has always been a research hotspot in fluid mechanics and aeroacoustics. The conventional prediction methods based on numerical simulation often demand huge computational resources, which are difficult to balance between accuracy and efficiency. Here, we present a data-driven deep neural network (DNN) method to realize fast aerodynamic noise prediction while maintaining accuracy. The proposed deep learning method can predict the spatial distributions of aerodynamic noise information under different working conditions. Based on the large eddy simulation turbulence model and the Ffowcs Williams-Hawkings acoustic analogy theory, a dataset composed of 1216 samples is established. With reference to the deep learning method, a DNN framework is proposed to map the relationship between spatial coordinates, inlet velocity and overall sound pressure level. The root-mean-square-errors of prediction are below 0.82 dB in the test dataset, and the directivity of aerodynamic noise predicted by the DNN framework are basically consistent with the numerical simulation. This work paves a novel way for fast prediction of aerodynamic noise with high accuracy and has application potential in acoustic field prediction.

关键词: aerodynamic noise prediction, deep neural network, aeroacoustics

Abstract: Accurate and fast prediction of aerodynamic noise has always been a research hotspot in fluid mechanics and aeroacoustics. The conventional prediction methods based on numerical simulation often demand huge computational resources, which are difficult to balance between accuracy and efficiency. Here, we present a data-driven deep neural network (DNN) method to realize fast aerodynamic noise prediction while maintaining accuracy. The proposed deep learning method can predict the spatial distributions of aerodynamic noise information under different working conditions. Based on the large eddy simulation turbulence model and the Ffowcs Williams-Hawkings acoustic analogy theory, a dataset composed of 1216 samples is established. With reference to the deep learning method, a DNN framework is proposed to map the relationship between spatial coordinates, inlet velocity and overall sound pressure level. The root-mean-square-errors of prediction are below 0.82 dB in the test dataset, and the directivity of aerodynamic noise predicted by the DNN framework are basically consistent with the numerical simulation. This work paves a novel way for fast prediction of aerodynamic noise with high accuracy and has application potential in acoustic field prediction.

Key words: aerodynamic noise prediction, deep neural network, aeroacoustics

中图分类号: (Aeroacoustics and atmospheric sound)

43.28.+h

07.64.+z (Acoustic instruments and equipment)

Hai-Yang Meng(孟海洋), Zi-Xiang Xu(徐自翔), Jing Yang(杨京), Bin Liang(梁彬), and Jian-Chun Cheng(程建春). Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network[J]. 中国物理B, 2022, 31(6): 64305-064305.

参考文献

[1] Astoul T, Wissocq G, Boussuge J F, Sengissen A and Sagaut P 2021 J. Comput. Phys. 447 110667
[2] Ritos K, Drikakis D, Kokkinakis I W and Spottswood S M 2020 Comput. Fluids 203 104520
[3] Gu X and Yao J 2021 J. Acoust. Soc. Am. 150 1912
[4] Wang Z H, Rienstra S W, Bi C X and Koren B 2020 J. Comput. Phys. 412 109442
[5] Feuchter C 2021 Comput. Fluids 224 104970
[6] Tam C K 2004 Int. J. Comput. Fluid Dyn. 18 547
[7] Kutz J N 2017 J. Fluid Mech. 814 1
[8] Ling J, Kurzawski A and Templeton J 2016 J. Fluid Mech. 807 155
[9] Wu J L, Xiao H and Paterson E 2018 Phys. Rev. Fluids 3 074602
[10] Sekar V, Jiang Q, Shu C and Khoo B C 2019 Phys. Fluids 31 057103
[11] Han R, Wang Y, Zhang Y and Chen G 2019 Phys. Fluids 31 127101
[12] Pandey S and Schumacher J 2020 Phys. Rev. Fluids 5 113506
[13] Park J and Choi H 2021 J. Fluid Mech. 914 16
[14] Rüttgers M, Lee S, Jeon S and You D 2019 Sci. Rep. 9 6057
[15] Pathak J, Hunt B, Girvan M, Lu Z and Ott E 2018 Phys. Rev. Lett. 120 024102
[16] Raissi M 2018 J. Mach. Learn. Res. 19 1
[17] Severson K A, Attia P M, Jin N, Perkins N, Jiang B, Yang Z, Chen M H, Aykol M, Herring P K, Fraggedakis D, Bazant M Z, Harris S J, Chueh W C and Braatz R D 2019 Nat. Energy 4 383
[18] Braatz R D 2019 Nat. Energy 4 383
[19] Ziletti A, Kumar D, Scheffler M and Ghiringhelli L M 2018 Nat. Commun. 9 2775
[20] Ye W, Chen C, Wang Z, Chu I H and Ong S P 2018 Nat. Commun. 9 3800
[21] Ye S, Li B, Li Q, Zhao H P and Feng X Q 2019 Appl. Phys. Lett. 115 161901
[22] Xu Z X, Gao H, Ding Y J, Yang J, Liang B and Cheng J C 2021 Phys. Rev. Appl. 16 044020
[23] Tao J and Sun G 2016 Chin. J. Aeronaut. 29 1213
[24] Sanaye S and Hassanzadeh A 2014 J. Renewable Sustainable Energy. 6 053105
[25] Li S and Lee S 2020 AIAA Aviation 2020 Forum, June 15-19, 2020, p. 2588
[26] Ffowcs Williams J E and Hawkings D L 1969 Proc. R. Soc. 264 321
[27] Lighthill M J 1952 Proc. R. Soc. 211 564
[28] Lighthill M J 1954 Proc. R. Soc. 222 1
[29] Blevins R D 1984 J. Sound Vib. 92 455
[30] Cox J S, Brentner K S and Rumsey C L 1998 Theor. Comput. Fluid Dyn. 12 233
[31] Revell J D, Prydz R A and Hays A P 1977 Lockheed Report 28074, Feburay, 1977, Final Report for NASA Contract NAS1-14403
[32] Li L, Liu P, Xing Y, Guo H and Tian Y 2016 Journal of Beijing University of Aeronautics and Astronsutics 42 977
[33] Srivastava N, Hinton G, Krizhevsky A, Sutskever I and Salakhutdinov R 2014 J. Mach. Learn. Res. 15 1929
[34] Nair V and Hinton G E 2010 Proceedings of the 27th International Conference on Machine Learning, June 21, 2010, Haifa, pp. 807-814
[35] Rumelhart D E, Hinton G E and Williams R J 1986 Nature 323 533
[36] Kingma D P and Ba J arXiv: 1412.6980

Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network

Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	Hai-Chao Zhan(詹海潮), Bing Chen(陈兵), Yi-Xiang Peng(彭怡翔), Le Wang(王乐), Wen-Nai Wang(王文鼐), and Sheng-Mei Zhao(赵生妹). Diffraction deep neural network based orbital angular momentum mode recognition scheme in oceanic turbulence[J]. 中国物理B, 2023, 32(4): 44208-044208.
[2]	陈勇, 黄奕勇, 陈小前, 白玉铸, 谭晓栋. Flow aeroacoustic damping using coupled mechanical–electrical impedance in lined pipeline[J]. 中国物理B, 2015, 24(5): 54302-054302.