收稿日期:
2022-05-09
修回日期:
2022-06-04
接受日期:
2022-09-15
出版日期:
2023-03-25
发布日期:
2022-09-30
通讯作者:
岳振江
E-mail:mountain_yue@bit.edu.cn
基金资助:
Guotao YANG1, Zhenjiang YUE1,2(), Li LIU1,2
Received:
2022-05-09
Revised:
2022-06-04
Accepted:
2022-09-15
Online:
2023-03-25
Published:
2022-09-30
Contact:
Zhenjiang YUE
E-mail:mountain_yue@bit.edu.cn
Supported by:
摘要:
高超声速飞行器热防护系统设计中高精度气动热分析模型使得设计计算成本不断增加,基于数据驱动的气动热环境预示方法受到广泛关注。针对有限高精度模型计算成本下提升全局预示精度的问题,提出一种基于模糊聚类的批量自适应采样方法。根据预示误差分布特征通过聚类采用超球分割构建采样影响域,兼顾误差较大的重点采样域与全局探索;通过当地误差评分系数加权构建采样拒绝域,减小新增样本冗余;结合maxmin准则在综合确定的重点采样空间中新增样本,提升采样质量,进而实现预示模型全局精度快速提升。数值测试算例表明,所提方法与One-Shot、APSFC、CV-Voronoi方法相比能有效降低所需采样规模,加速提升预示精度。通过类HTV-2飞行器气动热快速预示实例,验证了方法的有效性与工程实用性。
中图分类号:
杨国涛, 岳振江, 刘莉. 基于自适应采样的高超声速飞行器气动热全局快速预示[J]. 航空学报, 2023, 44(6): 127391-127391.
Guotao YANG, Zhenjiang YUE, Li LIU. Rapid prediction of global hypersonic vehicle aerothermodynamics based on adaptive sampling[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(6): 127391-127391.
表 1
FCHSW与One-Shot、CV-Voronoi、APSFC测试结果对比
测试 函数 | One-Shot | CV-Voronoi | APSFC | FCHSW |
---|---|---|---|---|
TG | 27.7 | 27.3 | 30.5 | 27.2 |
ES | 41.2 | 26.8 | 50.0 | 26.5 |
PK | 54.3 | 43.9 | 57.9 | 41.8 |
AK | 163.2 | 165.8 | 226.4 | 132.4 |
GP | 36.4 | 40.4 | 40.4 | 36.3 |
MZ | 303.3 | 289.9 | 417.6 | 227.6 |
HT | 157.9 | 132.6 | 193.0 | 132.1 |
CH | 132.9 | 126.9 | 150.6 | 125.0 |
DP | 280.8 | 283.2 | 288.6 | 279.0 |
表 2
计算过程中产生的建模次数及所需时间
测试 函数 | CV-Voronoi | APSFC | FCHSW | |||
---|---|---|---|---|---|---|
建模次数 | 训练时间/s | 建模次数 | 训练时间/s | 建模次数 | 训练时间/s | |
TG | 335.0±59.7 | 1.4±0.2 | 209.7±37.1 | 0.5±0.2 | 153.3±31.1 | 0.8±0.2 |
ES | 320.0±62.8 | 1.3±0.2 | 633.9±314.4 | 1.3±0.8 | 147.8±33.4 | 0.6±0.2 |
PK | 952.0±297.7 | 3.1±0.9 | 833.8±267.1 | 1.7±0.6 | 399.5±83.7 | 1.5±0.3 |
AK | 13 850.1±2 054.2 | 50.3±12.6 | 13 284.7±5 809.0 | 77.1±82.5 | 4 880.1±1 099.4 | 18.3±9.3 |
GP | 792.2±173.2 | 2.7±0.6 | 393.0±120.9 | 0.8±0.2 | 313.7±65.5 | 1.3±0.3 |
MZ | 42 466.6±7 781.3 | 539.8±20.7 | 45 708.1±23 123.0 | 1 346.5±113.4 | 14 624.6±2 448.4 | 114.8±23.0 |
HT | 8 831.3±1 885.8 | 52.2±15.9 | 6 542.3±3 395.1 | 67.9±67.9 | 2 862.4±436.4 | 19.8±4.2 |
CH | 7 953.6±1 255.7 | 66.7±13.5 | 2 778.5±546.8 | 18.1±6.4 | 1 683.7±272.5 | 22.7±14.7 |
DP | 39 985.3±5 723.6 | 1 201.9±360.3 | 7 030.8±1 527.0 | 127.8±54.8 | 6 870.2±956.5 | 353.4±73.8 |
表 4
每轮新增样本数的影响
测试函数 | |||||
---|---|---|---|---|---|
TG | 27.2 | 29.8 | 30.8 | 31.6 | 32.2 |
ES | 26.5 | 27.9 | 30.9 | 33.0 | 36.6 |
PK | 41.8 | 44.0 | 43.7 | 45.8 | 48.3 |
AK | 132.4 | 133.9 | 134.5 | 134.3 | 137.9 |
GP | 36.3 | 39.0 | 40.5 | 41.8 | 43.9 |
MZ | 227.6 | 229.4 | 229.2 | 231.7 | 235.6 |
HT | 132.1 | 140.7 | 138.1 | 139.4 | 141.4 |
CH | 125.0 | 132.8 | 128.7 | 135.6 | 134.8 |
DP | 279.0 | 287.9 | 297.9 | 301.9 | 297.6 |
表 5
波动系数的影响
测试函数 | |||||||
---|---|---|---|---|---|---|---|
TG | 26.8 | 26.5 | 27.0 | 27.2 | 28.3 | 28.6 | 29.1 |
ES | 38.8 | 34.4 | 30.5 | 26.5 | 26.8 | 28.4 | 30.6 |
PK | 44.8 | 43.5 | 42.3 | 41.8 | 41.8 | 42.7 | 46.8 |
AK | 130.4 | 129.6 | 131.3 | 132.4 | 141.2 | 143.5 | 156.7 |
GP | 35.8 | 35.3 | 36.2 | 36.3 | 37.2 | 37.1 | 40.6 |
MZ | 232.7 | 233.4 | 229.4 | 227.6 | 232.2 | 233.7 | 244.7 |
HT | 147.1 | 142.3 | 137.7 | 132.1 | 133.0 | 136.1 | 136.6 |
CH | 134.6 | 129.7 | 131.0 | 125.0 | 123.6 | 127.9 | 126.7 |
DP | 287.1 | 293.9 | 292.4 | 279.0 | 283.9 | 288.8 | 288.5 |
表 7
RPM在10个测试集上误差对比
测试工况 | Ma | α/(°) | H/km | 驻点热流/( | 驻点误差/% | 整体误差/% | |
---|---|---|---|---|---|---|---|
RPM | CFD | ||||||
Test1 | 5.0 | 8.9 | 43.3 | 207.8 | 215.3 | 3.6 | 6.9 |
Test2 | 6.7 | 17.8 | 53.3 | 291.1 | 299.6 | 2.9 | 5.0 |
Test3 | 8.3 | 2.2 | 56.7 | 475.5 | 455.5 | 4.2 | 7.1 |
Test4 | 10.0 | 15.6 | 33.3 | 3 661.9 | 3 698.7 | 1.0 | 5.0 |
Test5 | 11.7 | 0.0 | 36.7 | 4 703.2 | 4 679.3 | 0.5 | 4.8 |
Test6 | 13.3 | 11.1 | 60.0 | 1 525.8 | 1 519.6 | 0.4 | 2.6 |
Test7 | 15.0 | 20.0 | 46.7 | 5 312.3 | 5 287.0 | 0.5 | 4.9 |
Test8 | 16.7 | 6.7 | 30.0 | 22 447.9 | 22 863.0 | 1.9 | 5.1 |
Test9 | 18.3 | 4.4 | 50.0 | 8 062.7 | 8 054.3 | 0.1 | 3.3 |
Test10 | 20.0 | 13.3 | 40.0 | 18 983.5 | 19 233.9 | 1.3 | 3.4 |
1 | 黄伟, 罗世彬, 王振国. 临近空间高超声速飞行器关键技术及展望[J]. 宇航学报, 2010, 31(5): 1259-1265. |
HUANG W, LUO S B, WANG Z G. Key techniques and prospect of near-space hypersonic vehicle[J]. Journal of Astronautics, 2010, 31(5): 1259-1265 (in Chinese). | |
2 | 彭治雨, 石义雷, 龚红明, 等. 高超声速气动热预测技术及发展趋势[J]. 航空学报, 2015, 36(1): 325-345. |
PENG Z Y, SHI Y L, GONG H M, et al. Hypersonic aeroheating prediction technique and its trend of development[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36(1): 325-345 (in Chinese). | |
3 | 喻成璋, 刘卫华. 高超声速飞行器气动热预测技术研究进展[J]. 航空科学技术, 2021, 32(2): 14-21. |
YU C Z, LIU W H. Research status of aeroheating prediction technology for hypersionic aircraft[J]. Aeronautical Science & Technology, 2021, 32(2): 14-21 (in Chinese). | |
4 | 杨恺, 高效伟. 高超声速气动热环境工程算法[J]. 导弹与航天运载技术, 2010(4): 19-23. |
YANG K, GAO X W. Engineering algorithm for aeroheating environment of hypersonic aircrafts[J]. Missiles and Space Vehicles, 2010(4): 19-23 (in Chinese). | |
5 | DOWELL E H. Eigenmode analysis in unsteady aerodynamics-reduced-order models[J]. AIAA Journal, 1996, 34(8): 1578-1583. |
6 | YONDO R, ANDRéS E, VALERO E. A review on design of experiments and surrogate models in aircraft real-time and many-query aerodynamic analyses[J]. Progress in Aerospace Sciences, 2018, 96: 23-61. |
7 | 陈海昕, 邓凯文, 李润泽. 机器学习技术在气动优化中的应用[J]. 航空学报, 2019, 40(1): 522480. |
CHEN H X, DENG K W, LI R Z. Utilization of machine learning technology in aerodynamic optimization[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(1): 522480 (in Chinese). | |
8 | YAN X X, HAN J L, ZHANG B, et al. Model reduction of aerothermodynamic for hypersonic aerothermoelasticity based on POD and Chebyshev method[J]. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 2019, 233(10): 3734-3748. |
9 | 张智超, 高太元, 张磊, 等. 基于径向基神经网络的气动热预测代理模型[J]. 航空学报, 2021, 42(4): 524167. |
ZHANG Z C, GAO T Y, ZHANG L, et al. Aeroheating agent model based on radial basis function neural network[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 524167 (in Chinese). | |
10 | GARUD S S, KARIMI I A, KRAFT M. Design of computer experiments: A review[J]. Computers & Chemical Engineering, 2017, 106: 71-95. |
11 | FORRESTER A I J, SOBESTER A, KEANE A J. Engineering design via surrogate modelling: A practical guide[M]. New York: John Wiley & Sons, 2008: 13-29. |
12 | CROMBECQ K, GORISSEN D, DESCHRIJVER D, et al. A novel hybrid sequential design strategy for global surrogate modeling of computer experiments[J]. SIAM Journal on Scientific Computing, 2011, 33(4): 1948-1974. |
13 | LIU H T, ONG Y S, CAI J F. A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design[J]. Structural and Multidisciplinary Optimization, 2018, 57(1): 393-416. |
14 | FORRESTER A I J, KEANE A J. Recent advances in surrogate-based optimization[J]. Progress in Aerospace Sciences, 2009, 45(1-3): 50-79. |
15 | 李春娜, 张阳康. 一种适用于气动优化的高效自适应全局优化方法[J]. 航空学报, 2020, 41(5): 623352. |
LI C N, ZHANG Y K. An efficient adaptive global optimization method suitable for aerodynamic optimization[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(5): 623352 (in Chinese). | |
16 | 韩忠华, 许晨舟, 乔建领, 等. 基于代理模型的高效全局气动优化设计方法研究进展[J]. 航空学报, 2020, 41(5): 623344. |
HAN Z H, XU C Z, QIAO J L, et al. Recent progress of efficient global aerodynamic shape optimization using surrogate-based approach[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(5): 623344 (in Chinese). | |
17 | SIMPSON T W, MAUERY T M, KORTE J J, et al. Kriging models for global approximation in simulation-based multidisciplinary design optimization[J]. AIAA Journal, 2001, 39(12): 2233-2241. |
18 | LIU H T, XU S L, MA Y, et al. An adaptive Bayesian sequential sampling approach for global metamodeling[J]. Journal of Mechanical Design, 2016, 138(1): 011404. |
19 | XIONG Y, CHEN W, APLEY D, et al. A non-stationary covariance-based Kriging method for metamodelling in engineering design[J]. International Journal for Numerical Methods in Engineering, 2007, 71(6): 733-756. |
20 | YAO W, CHEN X Q, LUO W C. A gradient-based sequential radial basis function neural network modeling method[J]. Neural Computing and Applications, 2009, 18(5): 477-484. |
21 | FARHANG-MEHR A, AZARM S. Bayesian meta-modelling of engineering design simulations: A sequential approach with adaptation to irregularities in the response behaviour[J]. International Journal for Numerical Methods in Engineering, 2005, 62(15): 2104-2126. |
22 | TURNER C J, CRAWFORD R H, CAMPBELL M I. Multidimensional sequential sampling for NURBs-based metamodel development[J]. Engineering With Computers, 2007, 23(3): 155-174. |
23 | LI G Z, AUTE V, AZARM S. An accumulative error based adaptive design of experiments for offline metamodeling[J]. Structural and Multidisciplinary Optimization, 2010, 40(1): 137-155. |
24 | AUTE V, SALEH K, ABDELAZIZ O, et al. Cross-validation based single response adaptive design of experiments for Kriging metamodeling of deterministic computer simulations[J]. Structural and Multidisciplinary Optimization, 2013, 48(3): 581-605. |
25 | CHEN X, LIU L, ZHOU S, et al. Adding-point strategy for reduced-order hypersonic aerothermodynamics modeling based on fuzzy clustering[J]. Chinese Journal of Mechanical Engineering, 2016, 29(5): 983-991. |
26 | XU S L, LIU H T, WANG X F, et al. A robust error-pursuing sequential sampling approach for global metamodeling based on voronoi diagram and cross validation[J]. Journal of Mechanical Design, 2014, 136(7): 69-74. |
27 | KAMINSKY A L, WANG Y, PANT K, et al. Adaptive sampling techniques for surrogate modeling to create high-dimension aerodynamic loading response surfaces[C]∥ 2018 Applied Aerodynamics Conference. Reston: AIAA, 2018. |
28 | JOHNSON M E, MOORE L M, YLVISAKER D. Minimax and maximin distance designs[J]. Journal of Statistical Planning and Inference, 1990, 26(2): 131-148. |
29 | BEZDEK J C. Pattern recognition with fuzzy objective function algorithms[M]. New York: Springer Science & Business Media, 2013: 1-7. |
30 | ROUSSEEUW P J. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational and Applied Mathematics, 1987, 20: 53-65. |
31 | OLIVER M A. A tutorial guide to geostatistics: Computing and modelling variograms and Kriging[J]. CATENA, 2014, 113: 56-69. |
32 | 韩忠华. Kriging模型及代理优化算法研究进展[J]. 航空学报, 2016, 37(11): 3197-3225. |
HAN Z H. Kriging surrogate model and its application to design optimization: A review of recent progress[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(11): 3197-3225 (in Chinese). | |
33 | 甄华萍, 蒋崇文. 高超声速技术验证飞行器HTV-2综述[J]. 飞航导弹, 2013(6): 7-13. |
ZHEN H P, JIANG C W. Overview of hypersonic technology verification vehicle HTV-2[J]. Aerodynamic Missile Journal, 2013(6): 7-13 (in Chinese). | |
34 | SHI J T, ZHANG L, JIANG B S, et al. Aerodynamic force and heating optimization of HTV-2 typed vehicle[C]∥ 21st AIAA International Space Planes and Hypersonics Technologies Conference. Reston: AIAA, 2017. |
[1] | 郑建成, 曲智国, 谭贤四, 李志淮, 朱刚, 李陆军, 刘伟. 基于责任区划分的雷达网探测高超声速目标资源管理[J]. 航空学报, 2024, 45(8): 329022-329022. |
[2] | 蔡章博, 张征宇, 余皓, 占书恒. 荧光油膜速度场的自适应快速光流解法[J]. 航空学报, 2024, 45(7): 128047-128047. |
[3] | 戴今钊, 陈海昕. 流场波系引导的三维消波翼优化设计方法[J]. 航空学报, 2024, 45(6): 628942-628942. |
[4] | 刘小勇, 王明福, 刘建文, 任鑫, 张轩. 超燃冲压发动机研究回顾与展望[J]. 航空学报, 2024, 45(5): 529878-529878. |
[5] | 杨博, 于贺, 樊子辰. 微观能量分析气动光学效应时变误差的方法[J]. 航空学报, 2024, 45(4): 128703-128703. |
[6] | 李学良, 李创创, 苏伟, 吴杰. 分布式粗糙元对高超声速边界层不稳定性的影响试验[J]. 航空学报, 2024, 45(2): 128627-128627. |
[7] | 赖江, 范召林, 王乾, 董思卫, 童福林, 袁先旭. 高超声速有攻角锥裙直接数值模拟[J]. 航空学报, 2024, 45(2): 128610-128610. |
[8] | 熊有德, 李创创, 张振辉, 吴杰. 高超声速风洞自由来流扰动热线测量技术[J]. 航空学报, 2024, 45(10): 129042-129042. |
[9] | 倪炜霖, 王永海, 徐聪, 赤丰华, 梁海朝. 基于强化学习的高超飞行器协同博弈制导方法[J]. 航空学报, 2023, 44(S2): 729400-729400. |
[10] | 于哲峰, 梁世昌, 石卫波, 田得阳, 石安华, 廖东骏, 杨鹰. 类HTV⁃2飞行器光电特性的分析评估技术[J]. 航空学报, 2023, 44(S2): 729465-729465. |
[11] | 马平, 张宁, 石安华, 于哲峰, 梁世昌, 黄洁. 典型微波波段信号在模拟等离子体中的传输特性[J]. 航空学报, 2023, 44(S2): 729476-729476. |
[12] | 陈浩宇, 王彬文, 宋巧治, 李晓东. 热颤振地面模拟试验技术[J]. 航空学报, 2023, 44(8): 227295-227295. |
[13] | 常思源, 肖尧, 李广利, 田中伟, 张凯凯, 崔凯. 翼反角对高压捕获翼构型高超气动特性的影响[J]. 航空学报, 2023, 44(8): 127349-127349. |
[14] | 刘宏康, 陈坚强, 向星皓, 赵雅甜. 改进k-ω-γ转捩模式对不同雷诺数下HIAD的转捩预测[J]. 航空学报, 2023, 44(6): 126868-126868. |
[15] | 马崇立, 刘景源. 网格对高超声速钝头体表面热流数值模拟结果的影响[J]. 航空学报, 2023, 44(5): 126710-126710. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||
版权所有 © 航空学报编辑部
版权所有 © 2011航空学报杂志社
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