真空羽流智能化计算

doi:10.7527/S1000-6893.2022.27352

流体力学与飞行力学

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

真空羽流智能化计算

蔡国飙^1,2, 张百一^1,2, 贺碧蛟^1,2, 翁惠焱^1,2, 刘立辉^1,2

1. 北京航空航天大学宇航学院, 北京 100191;
2. 航天器设计优化与动态模拟教育部重点实验室, 北京 100191

收稿日期:2022-04-30 修回日期:2022-05-31 发布日期:2022-06-17
通讯作者: 蔡国飙,E-mail:cgb@buaa.edu.cn E-mail:cgb@buaa.edu.cn
基金资助:
国家自然科学基金（51676010）

Intelligent computation of vacuum plume

CAI Guobiao^1,2, ZHANG Baiyi^1,2, HE Bijiao^1,2, WENG Huiyan^1,2, LIU Lihui^1,2

1. School of Astronautics, Beihang University, Beijing 100191, China;
2. Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies, Ministry of Education, Beijing 100191, China

Received:2022-04-30 Revised:2022-05-31 Published:2022-06-17
Supported by:
National Natural Science Foundation of China (51676010)

摘要/Abstract

摘要： 真空环境中，姿轨控发动机工作产生的高温高速真空羽流会对航天器产生气动力、气动热、污染、电磁干扰和视场干扰等效应，影响航天器正常工作甚至任务成败。因此，真空羽流及其效应评估和防护是航天领域的关键科学和工程问题。直接模拟蒙特卡洛（DSMC）方法是真空羽流数值模拟的主流方法，但DSMC是一种粒子模拟方法，非常耗时，严重制约了真空羽流及其效应的评估效率。提出了一种基于卷积神经网络的直接模拟蒙特卡洛（CNN-DSMC）方法。CNN-DSMC的训练集包括两个部分：将DSMC羽流数值模型的几何拓扑与边界条件信息作为训练集的输入，将DSMC数值模拟得到的羽流流场数据作为训练集的输出。将该训练集输入卷积神经网络进行训练，可得到高精度、高效率的真空羽流智能化计算模型，以此预测不同条件下的真空羽流流场。以月球探测器月面着陆过程中的真空羽流场为例，分别使用CNN-DSMC和DSMC数值模拟了在不同着陆高度条件下的真空羽流流场流速和密度。结果显示，两种方法结果基本一致，流场流速和密度的平均相对误差分别小于6.0%和8.8%。但与传统的DSMC方法相比，CNN-DSMC方法的计算速度提升至少4个量级，最大可达6个量级。因此，本文提出的CNN-DSMC方法在真空羽流数值模拟方面具有较强的应用潜力。

关键词: 真空羽流, 人工智能, 深度学习, 神经网络, 直接模拟蒙特卡洛

Abstract: The high-temperature and high-speed vacuum plume generated by the attitude orbit control engine in the vacuum causes aerodynamic forces, heat fluxes, contamination, electromagnetic interference, and visual interference to the spacecraft, affecting the spacecraft operation and even the success of missions. Therefore, the assessment of vacuum plumes and their effect is a critical scientific and engineering issue in aerospace. The Direct Simulation Monte Carlo (DSMC) method is generally utilized in the numerical simulation of vacuum plumes. However, being a particle simulation method, DSMC is time-consuming, and severely limits the efficiency of vacuum plume evaluation. In this study, we propose a Convolutional Neural Networks-based Direct Simulation Monte Carlo (CNN-DSMC) method. The geometric topology information, the boundary condition information, and the flow field data obtained from DSMC simulations are employed as the training set of the CNN-DSMC. Then, a highly accurate and efficient intelligent computational model of vacuum plumes is trained based on the convolutional neural network, which can be used to predict the vacuum plume flow field under different input conditions. In addition, the velocity and density of the vacuum plume during the lunar landing are computed by CNN-DSMC and DSMC simulation at different landing altitudes. The results obtained by the two methods are consistent, and the average relative errors of the flow velocity and density are smaller than 6.0% and 8.8%, respectively. Furthermore, the computational speed of the CNN-DSMC is improved by at least four orders of magnitude and up to six orders of magnitude compared with the conventional DSMC method. Overall, the CNN-DSMC proposed in this study offers promising applications for the numerical simulation of vacuum plumes.

Key words: vacuum plume, artificial intelligence, deep learning, neural networks, direct simulation Monte Carlo

中图分类号:

V211.25

蔡国飙, 张百一, 贺碧蛟, 翁惠焱, 刘立辉. 真空羽流智能化计算[J]. 航空学报, 2022, 43(10): 527352-527352.

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.

参考文献

[1] HE B J, ZHANG J H, CAI G B. Research on vacuum plume and its effects[J]. Chinese Journal of Aeronautics, 2013, 26(1):27-36.
[2] GENOVESE J. Rapid estimation of hydrazine exhaust plume interaction:AIAA-1978-1091[R]. Reston:AIAA, 1978.
[3] GRABE M, SOARES C. Status and future of research on plume induced contamination[C]//70th International Astronautical Congress, 2019.
[4] ZHANG M X, CAI G B, TANG Z Y, et al. Experimental and numerical research on the diversion effect of a conic flame deflector for a lunar module ascent stage[J]. Journal of Aerospace Engineering, 2016, 29(5):04016021.
[5] ZHANG M X, CAI G B, HE B J, et al. Experimental and numerical analysis of the heat flux characteristic of the plume of a 120-N thruster[J]. Science China Technological Sciences, 2019, 62(10):1854-1860.
[6] HE X Y, HE B J, CAI G B. Simulation of rocket plume and lunar dust using DSMC method[J]. Acta Astronautica, 2012, 70:100-111.
[7] HE B J, HE X Y, ZHANG M X, et al. Plume aerodynamic effects of cushion engine in lunar landing[J]. Chinese Journal of Aeronautics, 2013, 26(2):269-278.
[8] CAI G B, LING G L, HE B J. An introduction to the novel vacuum plume effects experimental system[J]. Science China Technological Sciences, 2016, 59(6):953-960.
[9] CAI G, REN X, HE B, et al. The dependence of transport coefficient on spatial dimensions and grid shape in the direct simulation Monte Carlo based on Green-Kubo relation[J]. Physics of Fluids, 2020, 32(4):042006.
[10] 叶青, 饶炜, 刘锋, 等. 火星着陆发动机羽流与火壤的相互作用[J]. 航空学报, 2022, 43(3):626557. YE Q, RAO W, LIU F, et al. Interaction between engine plume and Martian soil during Mars landing[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(3):626557 (in Chinese).
[11] 李锦, 耿湘人, 陈坚强, 等. DSMC量子动理学模型在火星再入流动中的应用[J]. 航空学报, 2020, 41(7):123240. LI J, GENG X R, CHEN J Q, et al. Application of DSMC quantum kinetic model in re-entry flow of Mars[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(7):123240 (in Chinese).
[12] CHINNAPPAN A K, KUMAR R, ARGHODE V K. Modeling of dusty gas flows due to plume impingement on a lunar surface[J]. Physics of Fluids, 2021, 33(5):053307.
[13] GAIER JR. The effects of lunar dust on EVA systems during the Apollo missions:NASA/TM-2005-213610/REV1[R]. Washington, D.C.:NASA, 2007.
[14] CALLE C I, BUHLER C R, MCFALL J L, et al. Particle removal by electrostatic and dielectrophoretic forces for dust control during lunar exploration missions[J]. Journal of Electrostatics, 2009, 67(2-3):89-92.
[15] FLASIŃSKI M. Introduction to artificial intelligence[M]. Berlin:Springer, 2016.
[16] GOODFELLOW I, BENGIO Y, COURVILLE A. Deep learning[M]. Cambridge:The MIT Press, 2016.
[17] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016:770-778.
[18] YOUNG T, HAZARIKA D, PORIA S, et al. Recent trends in deep learning based natural language processing[J]. IEEE Computational Intelligence Magazine, 2018, 13(3):55-75.
[19] DENG L, HINTON G, KINGSBURY B. New types of deep neural network learning for speech recognition and related applications:an overview[C]//2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway:IEEE Press, 2013:8599-8603.
[20] WANG H J, YANG Z, ZHOU W G, et al. Online scheduling of image satellites based on neural networks and deep reinforcement learning[J]. Chinese Journal of Aeronautics, 2019, 32(4):1011-1019.
[21] LI M H, HU T J. Deep learning enabled localization for UAV autolanding[J]. Chinese Journal of Aeronautics, 2021, 34(5):585-600.
[22] HU Z J, GAO X G, WAN K F, et al. Relevant experience learning:a deep reinforcement learning method for UAV autonomous motion planning in complex unknown environments[J]. Chinese Journal of Aeronautics, 2021, 34(12):187-204.
[23] ZHANG H, JIAO Z X, SHANG Y X, et al. Ground maneuver for front-wheel drive aircraft via deep reinforcement learning[J]. Chinese Journal of Aeronautics, 2021, 34(10):166-176.
[24] 何磊, 钱炜祺, 董康生, 等. 基于卷积神经网络的结冰翼型气动特性建模研究[J]. 航空学报, (2021-11-12)[2022-04-30]. https://kns.cnki.net/kcms/detail/11.1929.V.20211110.1515.002.html. HE L, QIAN W Q, DONG K S, et al. Aerodynamic characteristics modeling of iced airfoil based on convolution neural networks[J]. Acta Aeronautica et Astronautica Sinica, (2021-11-12)[2022-04-30]. https://kns.cnki.net/kcms/detail/11.1929.V.20211110.1515.002.html (in Chinese).
[25] 李左飙, 温风波, 唐晓雷, 等. 基于深度学习的单排孔气膜冷却性能预测[J]. 航空学报, 2021, 42(4):524331. LI Z B, WEN F B, TANG X L, et al. Prediction of single-row hole film cooling performance based on deep learning[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524331 (in Chinese).
[26] 黄旭星, 李爽, 杨彬, 等. 人工智能在航天器制导与控制中的应用综述[J]. 航空学报, 2021, 42(4):524201. HUANG X X, LI S, YANG B, et al. Spacecraft guidance and control based on artificial intelligence:Review[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524201 (in Chinese).
[27] 任峰, 高传强, 唐辉. 机器学习在流动控制领域的应用及发展趋势[J]. 航空学报, 2021, 42(4):524686. REN F, GAO C Q, TANG H. Machine learning for flow control:Applications and development trends[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524686 (in Chinese).
[28] 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.
[29] 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.
[30] WU H Z, LIU X J, AN W, et al. A generative deep learning framework for airfoil flow field prediction with sparse data[J]. Chinese Journal of Aeronautics, 2022, 35(1):470-484.
[31] 王怡星, 韩仁坤, 刘子扬, 等. 流体力学深度学习建模技术研究进展[J]. 航空学报, 2021, 42(4):524779. WANG Y X, HAN R K, LIU Z Y, et al. Progress of deep learning modeling technology for fluid mechanics[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524779 (in Chinese).
[32] 叶舒然, 张珍, 王一伟, 等. 基于卷积神经网络的深度学习流场特征识别及应用进展[J]. 航空学报, 2021, 42(4):524736. YE S R, ZHANG Z, WANG Y W, et al. Progress in deep convolutional neural network based flow field recognition and its applications[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524736 (in Chinese).
[33] 奕建苗, 邓枫, 覃宁, 等. 快速预测跨音速流场的深度学习方法[J]. 航空学报, (2022-03-01)[2022-04-30]. https://kns.cnki.net/kcms/detail/11.1929.V.20220228.1120.018.html. YI J M, DENG F, QIN N, et al. Fast prediction of transonic flow field using deep learning method[J]. Acta Aeronautica et Astronautica Sinica, (2022-03-01)[2022-04-30].https://kns.cnki.net/kcms/detail/11.1929.V.20220228.1120.018.html (in Chinese).
[34] 战庆亮, 白春锦, 张宁, 等. 基于时程卷积自编码的机翼绕流特征识别方法[J]. 航空学报, (2021-12-13)[2022-04-30]. https://kns.cnki.net/kcms/detail/11.1929.V.20211209.1732.004.html. ZHAN Q L, BAI C J, ZHANG N, et al. Feature extraction method of flow around wing based on time history convolutional autoencoder[J]. Acta Aeronautica et Astronautica Sinica, (2021-12-13)[2022-04-30]. https://kns.cnki.net/kcms/detail/11.1929.V.20211209.1732.004.html (in Chinese).
[35] 张伟伟, 寇家庆, 刘溢浪. 智能赋能流体力学展望[J]. 航空学报, 2021, 42(4):524689. ZHANG W W, KOU J Q, LIU Y L. Prospect of artificial intelligence empowered fluid mechanics[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524689 (in Chinese).
[36] YANG Z, TANG Z Y, CAI G B, et al. Development of a coupled NS-DSMC method for the simulation of plume impingement effects of space thrusters[J]. Thermophysics and Aeromechanics, 2017, 24(6):835-847.
[37] CAI G B, ZHENG H R, LIU L H, et al. Three-dimensional particle simulation of ion thruster plume impingement[J]. Acta Astronautica, 2018, 151:645-654.
[38] ZHENG H R, CAI G B, LIU L H, et al. Three-dimensional particle simulation of back-sputtered carbon in electric propulsion test facility[J]. Acta Astronautica, 2017, 132:161-169.
[39] ZHANG B Y, CAI G B, ZHENG H R, et al. Analysis of influencing parameters in ion thruster plume simulation[J]. Proceedings of the Institution of Mechanical Engineers, Part G:Journal of Aerospace Engineering, 2021, 235(10):1158-1169.
[40] LIU L H, CAI G B, ZHENG H R, et al. Measurement of the momentum accommodation coefficient for the interactions between electric thruster plume and a solid surface[J]. Physics of Plasmas, 2020, 27(5):053511.
[41] BIRD G. Molecular gas dynamics[R]. Washington, D.C.:NASA, 1976.
[42] LUDWIG J. Image convolution[R]. Portland:Portland State University, 2013.
[43] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011:315-323.
[44] IOFFE S, SZEGEDY C. Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning. New York:Association for Computing Machinery, 2015:448-456.
[45] LOSHCHILOV I, HUTTER F. Fixing weight decay regularization in Adam[DB/OL]. arXiv preprint:1711.05101,2018.
[46] 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:Association for Computing Machinery, 2016:481-490.
[47] 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.
[48] OSHER S, FEDKIW R, PIECHOR K. Level set methods and dynamic implicit surfaces[J]. Applied Mechanics Reviews, 2004, 57(3):B15.
[49] SETHIAN J A. A fast marching level set method for monotonically advancing fronts[J]. Proceedings of the National Academy of Sciences of the United States of America, 1996, 93(4):1591-1595.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

真空羽流智能化计算

Intelligent computation of vacuum plume

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	胡伟, 万文章, 陈谋. 基于神经网络和干扰观测器的UAV自动着舰控制[J]. 航空学报, 2022, 43(S1): 726963-726963.
[2]	苏翎菲, 化永朝, 董希旺, 任章. 人与无人机集群多模态智能交互方法[J]. 航空学报, 2022, 43(S1): 727001-727001.
[3]	陈博, 岳凯, 王如生, 胡明南. 基于学习策略的多速率多传感器融合定位方法[J]. 航空学报, 2022, 43(S1): 726904-726904.
[4]	王宇斐, 刘骁佳, 刘欢, 曹立俊, 罗志强. 孪生神经网络在航天产品电性能测试方面的应用[J]. 航空学报, 2022, 43(S1): 727048-727048.
[5]	王子玲, 熊振宇, 顾祥岐. 可见光与SAR多源遥感图像关联学习算法[J]. 航空学报, 2022, 43(S1): 727239-727239.
[6]	惠俊鹏, 汪韧, 俞启东. 基于强化学习的再入飞行器“新质”走廊在线生成技术[J]. 航空学报, 2022, 43(9): 325960-325960.
[7]	曹明, 王鹏, 左洪福, 曾海军, 孙见忠, 杨卫东, 魏芳, 陈雪峰. 民用航空发动机故障诊断与健康管理现状、挑战与机遇Ⅱ: 地面综合诊断、寿命管理和智能维护维修决策[J]. 航空学报, 2022, 43(9): 625574-625574.
[8]	杨特, 杨智春, 梁舒雅, 康在飞, 贾有. 平稳随机载荷的信号特征提取与深度神经网络识别[J]. 航空学报, 2022, 43(9): 225952-225952.
[9]	韩淞宇, 邵海东, 姜洪开, 张笑阳. 基于提升卷积神经网络的航空发动机高速轴承智能故障诊断[J]. 航空学报, 2022, 43(9): 625479-625479.
[10]	赵良玉, 李丹, 赵辰悦, 蒋飞. 无人机自主降落标识检测方法若干研究进展[J]. 航空学报, 2022, 43(9): 25882-025882.
[11]	刘佳奇, 冯蕴雯, 路成, 薛小锋, 潘维煌. 基于智能神经网络的航空发动机运行安全分析[J]. 航空学报, 2022, 43(9): 625375-625375.
[12]	邵怡韦, 陈嘉宇, 林翠颖, 万程, 葛红娟, 石智龙. 小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法[J]. 航空学报, 2022, 43(8): 625429-625429.
[13]	康玉祥, 陈果, 尉询楷, 周磊. 深度残差对冲网络及其在滚动轴承故障诊断中的应用[J]. 航空学报, 2022, 43(8): 625201-625201.
[14]	刘子超, 王江, 何绍溟, 李宇飞. 基于预测校正的落角约束计算制导方法[J]. 航空学报, 2022, 43(8): 325433-325433.
[15]	孙灿飞, 黄林然, 沈勇. 复杂工况下的直升机行星传动轮系故障诊断[J]. 航空学报, 2022, 43(8): 625480-625480.