基于数据挖掘的飞行器气动布局设计知识提取

刘深深; 陈江涛; 桂业伟; 唐伟; 王安龄; 韩青华

doi:10.7527/S1000-6893.2020.24708

航空学报 >

2021 , Vol. 42 >Issue 4: 524708 - 524708

DOI: https://doi.org/10.7527/S1000-6893.2020.24708

流体力学与飞行力学

基于数据挖掘的飞行器气动布局设计知识提取

刘深深 ,
陈江涛 ,
桂业伟 ,
唐伟 ,
王安龄 ,
韩青华

展开

1. 空气动力学国家重点实验室, 绵阳 621000;
2. 中国空气动力研究与发展中心计算空气动力研究所, 绵阳 621000;
3. 西南科技大学环境友好能源材料国家重点实验室, 绵阳 621000

收稿日期: 2020-09-03

修回日期: 2020-09-20

网络出版日期: 2020-10-16

基金资助

国家自然科学基金（11702315）；国家数值风洞工程

收起

Knowledge discovery for vehicle aerodynamic configuration design using data mining

LIU Shenshen ,
Chen Jiangtao ,
GUI Yewei ,
TANG Wei ,
WANG Anling ,
HAN Qinghua

Expand

1. State Key Laboratory of Aerodynamics, Mianyang 621000, China;
2. Computational Aerodynamics Institute, China Aerodynamics Research and Development Center, Mianyang 621000, China;
3. State Key Laboratory of Environment-friendly Energy Materials, Southwest University of Science and Technology, Mianyang 621000, China

Received date: 2020-09-03

Revised date: 2020-09-20

Online published: 2020-10-16

Supported by

National Natural Science Foundation of China (11702315);National Numerical Windtunnel Project

Fold

摘要

为了更深入地理解飞行器气动布局设计优化中多目标/多设计变量间的影响关系，提高优化模型的科学性及优化效率，对基于数据挖掘技术的飞行器气动布局隐含设计知识提取问题开展了探索研究。以高升阻比滑翔飞行器布局设计优化问题为例，基于当前比较有代表性的方差分析、等度量映射、决策树、自组织映射4类机器学习算法对气动布局优化设计中产生的中间数据进行了挖掘分析。对不同方法得到的升阻比、横/侧向稳定性及容积率4种目标性能间的权衡关系，目标性能与设计变量间的敏感性关系及产生较优布局外形的设计变量取值规则进行了综合对比分析，凝练形成了适用于该类飞行器的设计知识，同时对4种方法的特点及适用性进行了总结分析，给出了相关结论。

关键词： 气动布局优化设计; 数据挖掘; 知识提取; 等度量映射; 自组织映射; 决策树; 总变差分析

本文引用格式

刘深深 , 陈江涛 , 桂业伟 , 唐伟 , 王安龄 , 韩青华 . 基于数据挖掘的飞行器气动布局设计知识提取[J]. 航空学报, 2021 , 42(4) : 524708 -524708 . DOI: 10.7527/S1000-6893.2020.24708

Abstract

To gain a deeper understanding of the relationship between multiple objectives and multiple design parameters in the optimization process of vehicle aerodynamic configuration design and improve the scientificity and efficiency of the optimization model, we study the knowledge discovery of aircraft aerodynamic configuration design based on data mining methods. Four machine learning methods including analysis of variance, decision tree, isometric mapping, and self-organizing map are applied to data mining for aerodynamic design space of a hypersonic glide vehicle configuration optimization problem. Trade-offs between four objective functions (lift-to-drag ratio, lateral/side stability and volumetric efficiency) and influences of the design variables on the objective functions obtained quantitatively and qualitatively by the four methods are presented and discussed. Meanwhile, the design rules for variable values to generate better results are also analyzed. The features of the four data mining techniques are discussed respectively and the design knowledge obtained which can be applied to hypersonic glide vehicle configuration design is summarized.

Key words： aerodynamic configuration optimization design; data mining; knowledge discovery; isometric mapping; self-organizing map; decision tree; analysis of variance

参考文献

[1] 桂业伟,唐伟,杜雁霞. 临近空间高超声速飞行器热安全[M]. 北京:国防工业出版社, 2019:180-185. GUI Y W,TANG W,DU Y X. Thermal safety issues of near-space hypersonic vehicles[M].Beijing:National Defense Industry Press,2019:180-185(in Chinese).
[2] 唐伟, 冯毅, 杨肖峰, 等. 非惯性弹道气动布局设计实践[J].气体物理,2017,2(1):1-12. TANG W, FENG Y,YANG X F, et al. Practices of aerodynamic configuration design for non-ballistic trajectory vehicles[J].Physics of Gases,2017,2(1):1-12(in Chinese).
[3] 桂业伟, 刘磊, 代光月,等. 高超飞行器流-固-热耦合软件现状与软件开发[J]. 航空学报,2017,38(7):020844. GUI Y W, LIU L, DAI G Y, et al. Research status on hypersonic vehicle fluid-thermal-structural coupling and software development[J]. Acta Aeronautica et Astronautic Sinica, 2017,38(7):020844(in Chinese).
[4] 桂业伟. 高超声速飞行器综合热效应问题[J]. 中国科学:物理学力学天文学, 2019, 49(11):114702. GUI Y W. Combined thermal phenomena of hypersonic vehicle[J]. Scientia Physica, Mechanica & Astronomica, 2019, 49(11):114702(in Chinese).
[5] 桂业伟, 刘磊, 魏东.长航时高超声速飞行器的综合热效应问题[J].空气动力学学报,2020,38(4):641-650. GUI Y W, LIU L,WEI D. Combined thermal phenomena issues of long endurance hypersonic vehicles[J]. Acta Aerodynamica Sinica, 2020,38(4):641-650(in Chinese).
[6] 代光月, 曾磊, 刘深深, 等. 考虑力/热/结构多场耦合效应的飞行弹道预测[J].航空学报,2018, 39(2):122346. DAI G Y, ZENG L,LIU S S, et al. Prediction of flight trajectory considering fluid-thermal-structure coupling effect[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(12):122346(in Chinese).
[7] 汪伟, 莫蓉, 张岩. 叶片气动优化仿真数据的数据挖掘应用研究[J]. 计算机工程与应用, 2013,49(12):11-15. WANG W, MO R, ZHANG Y. Applied research on simulation data of blade optimization designing based on data mining[J].Computer Engineering and Applications,2013,49(12):11-15(in Chinese).
[8] SIMPSON T W, TOROPOV V, BALABANOV V, et al. Design and analysis of computer experiments in multidisciplinary design optimization:a review of how far we have come or not:AIAA-2008-5802[R]. Reston:AIAA, 2008.
[9] 郭振东, 宋立明, 李军, 等. 基于子元模型的全局优化与设计空间知识挖掘方法[J]. 推进技术, 2015, 36(2):207-216. GUO Z D, SONG L M, LI J, et al. Meta model-based global design optimization and exploration method[J]. Journal of Propulsion Technology, 2015, 36(2):207-216(in Chinese).
[10] JEONG S, SHIMOYAMA K. Review of data mining for multi-disciplinary design optimization[J]. Proceedings of the Institution of Mechanical Engineers, Part G:Journal of Aerospace Engineering,2011, 225:465-479.
[11] JEONG S, CHIBA K, OBAYASHI S. Data mining for aerodynamic design space[J]. Journal of Aerospace Computing,Information, and Communication, 2005, 2(11):452-469.
[12] CHIBA K. Knowledge discovery in aerodynamic design space for flyback-booster wing using data mining[C]//14th AIAA/AHI Space Planes and Hypersonic Systems And Technologies Conference. Reston:AIAA, 2006.
[13] CHIBA K, AKIRA O. Multidisciplinary design optimization and data mining for transonic regional-jet wing[J]. Journal of Aircraft,2007,44(4):1100-1112.
[14] 邱亚松. 基于数据降维技术的气动外形设计方法[D].西安:西北工业大学, 2014. QIU Y S. Aerodynamic shape design methods based on data dimension approaches[D]. Xi'an:Northwestern Polytechnical University,2014(in Chinese).
[15] TANG W, GUI Y W, ZHANG Y, et al. Aerodynamic design and optimization for a wing-body vehicle[J]. Journal of Astronautics, 2007,28(1):199-202.
[16] 高清,赵俊波,李潜. 类HTV-2横侧向稳定性研究[J]. 宇航学报, 2014, 35(6):657-662. GAO Q, ZHAO J B, LI Q. Study on lateral-directional stability of HTV-2 like configuration[J]. Journal of Astronautics, 2014, 35(6):657-662(in Chinese).
[17] 刘深深, 解静, 冯毅, 等. 一种仿HX扁平面对称类升力体布局气动特性分析[J].空气动力学学报, 2017,35(6):787-791. LIU S S, XIE J, FENG Y, et al. Aerodynamic characteristics analysis for HX analog lifting body[J]. Acta Aerodynamica Sinica, 2017,35(6):787-791(in Chinese).
[18] 冯毅, 唐伟, 任建勋, 等.飞行器参数化建模方法研究[J].空气动力学学报,2012, 30(4):546-550. FENG Y, TANG W, REN J X, et al. Parametric geometry representation method for hypersonic vehicle configuration[J]. Acta Aerodynamica Sinica, 2012, 30(4):546-550(in Chinese).
[19] 唐伟. 新一代航天机动飞行器气动设计研究[D]. 西安:西北工业大学,2005. TANG W. Aerodynamic design study for new generation aeronautical maneuverable vehicle[D]. Xi'an:Northwestern Polytechnical University, 2005(in Chinese).
[20] 唐伟,张勇,李为吉, 等.可变弯尾飞行器空间螺旋机动的实现[J].空气动力学学报,2006,24(3):375-379. TANG W,ZHANG Y, LI W J, et al.Simulation of spiral maneuvering for a variable-bend-tail vehicle[J].Acta Aerodynamica Sinica, 2006,24(3):375-379(in Chinese).
[21] 唐伟,李为吉,高晓成,等.削面/配平翼飞行器的气动计算及分析[J].西北工业大学学报,2004, 22(5):541-544. TANG W, LI W J, GAO X C, et al. Aerodynamic prediction and analysis for a reentry vehicle with slice-ailerons[J]. Journal of Northwestern Polytechnical University, 2004, 22(5):541-544(in Chinese).
[22] 冯毅,刘深深,卢风顺,等.一种可重复使用天地往返升力体运载器概念及其气动布局优化设计研究[J].空气动力学学报,2017,35(4):563-571. FENG Y, LIU S S, LU F S, et al.Study on a new RLV lifting body concept and its aerodynamic configuration optimization design[J]. Acta Aerodynamica Sinica, 2017, 35(4):563-571(in Chinese).
[23] SOBOL I M. Sensitivity estimates for nonlinear mathematical models[J]. Mathematical Modelling and Computational Experiments, 1993,4:407-414.
[24] TOSHIMITSU H, ANDREA S. Importance measures in global sensitivity analysis of nonlinear models[J]. Reliability Engineering and System Safety, 1996, 52:1-17.
[25] 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).
[26] FABIAN P,GAE··L V. sklearn.tree.DecisionTreeClassifier[EB/OL].[2020-06-05].http://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html.
[27] FABIAN P,GAE··L V. sklearn.manifold.Isomap[EB/OL].[2020-06-05]. http://scikit-learn.org/stable/modules/generated/sklearn.manifold.Isomap.html.
[28] KOHONEN T. Self-organizing maps[M]. Berlin, Heidelberg:Springer, 1995.
[29] 石丽红. 基于SOM算法的高维数据可视化[D]. 秦皇岛:燕山大学,2013. SHI L H. The visualization of the high-dimension data based on som algorithm[D]. Qinhuangdao:Yanshan University, 2013(in Chinese).
[30] VETTIGLI G. MiniSom:minimalistic and NumPy based implementation of the self organizing maps[EB/OL]. (2020-04-25)[2020-06-07]. https://github.com/JustGlowing/MinisomJustGlowing/minisom.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献