基于自动核构造高斯过程的导弹气动性能预测

doi:10.7527/S1000-6893.2020.24093

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

基于自动核构造高斯过程的导弹气动性能预测

胡伟杰^1,2, 黄增辉³, 刘学军^1,2, 吕宏强³

1. 南京航空航天大学计算机科学与技术学院/人工智能学院, 模式分析与机器智能工业和信息化部重点实验室, 南京 211106;
2. 软件新技术与产业化协同创新中心, 南京 210023;
3. 南京航空航天大学航空学院, 南京 210016

收稿日期:2020-04-15 修回日期:2020-07-07 发布日期:2020-07-17
通讯作者: 刘学军 E-mail:xuejun.liu@nuaa.edu.cn
基金资助:
航空科学基金（2018ZA52002，2019ZA052011）；空气动力学国家重点实验室基金（SKLA20180102）；气动噪声控制重点实验室基金（ANCL20190103）

Missile aerodynamic performance prediction of Gaussian process through automatic kernel construction

HU Weijie^1,2, HUANG Zenghui³, LIU Xuejun^1,2, LYU Hongqiang³

1. MⅡT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology/College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
2. Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 210023, China;
3. College of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Received:2020-04-15 Revised:2020-07-07 Published:2020-07-17
Supported by:
Aeronautical Science Foundation of China (2018ZA52002,2019ZA052011); Foundation of State Key Laboratory of Aerodynamics (SKLA20180102); Key Laboratory of Aerodynamic Noise Control (ANCL20190103)

摘要/Abstract

摘要： 在导弹的初期设计阶段，通常需要对导弹的气动性能进行快速粗略评估。针对传统工程估算软件计算精度低和CFD方法计算代价大的缺陷，提出一种基于高斯过程回归（GPR）代理模型快速预测典型导弹气动性能的方案。以导弹外形参数和攻角作为模型输入，升力系数、阻力系数和力矩系数作为模型输出，对GPR模型的气动性能预测结果进行分析。首先，与其他常用代理模型的预测精度对比，GPR模型对3种系数的预测误差分别仅为0.24%、0.36%和0.36%，高于其他代理模型的预测精度。其次，考虑GPR模型核函数选择严重依赖人工先验知识的问题，采用了一种自动核构造算法，无需先验知识即可从数据中自动学习核函数。将该算法嵌入GPR框架中，与传统GPR模型比较，实验结果表明：基于该算法的GPR模型对3种系数的预测误差分别降低到0.10%、0.22%和0.17%。最后，给出导弹气动性能快速预测的应用实例，结果表明所提出的GPR模型的导弹气动性能预测方案是有效的，能够满足设计初期快速且精确的气动性能预测需求。

关键词: 导弹气动性能, 预测, 代理模型, 高斯过程回归, 自动核构造, 核函数

Abstract: The initial stage of missile design usually requires quick and rough evaluation of missile aerodynamic performance. To improve the low calculation accuracy of traditional engineering estimation software and reduce the high calculation cost of CFD method, we propose a scheme based on the Gaussian Process Regression (GPR) surrogate model to quickly and accurately predict the aerodynamic performance of typical missiles. The prediction results of the GPR model are analyzed, taking the missile shape parameters and angle of attack as the input and the lift coefficient, drag coefficient and moment coefficient as the output. First of all, compared with the prediction accuracy of other commonly used surrogate models, the prediction errors of the GPR model for the three coefficients are only 0.24%, 0.36% and 0.36%, respectively, lower than those of other surrogate models. Secondly, considering the problem that the kernel function selection of the GPR model depends heavily on artificial prior knowledge, we embed an automatic kernel construction algorithm which can automatically learn the kernel function from data without prior knowledge into the GPR framework. Compared with the traditional GPR model, the prediction errors of the GPR model incorporating the algorithm for the three coefficients are reduced to 0.10%, 0.22% and 0.17%, respectively. Finally, an application example of rapid prediction of missile aerodynamic performance is conducted, and the results show that the prediction scheme of the missile aerodynamic performance based on the GPR model is effective and can meet the requirements of fast and accurate aerodynamic performance prediction in the initial stage of missile design.

Key words: missile aerodynamic performance, prediction, surrogate models, Gaussian process regression, automatic kernel construction, kernel function

中图分类号:

胡伟杰, 黄增辉, 刘学军, 吕宏强. 基于自动核构造高斯过程的导弹气动性能预测[J]. 航空学报, 2021, 42(4): 524093-524093.

HU Weijie, HUANG Zenghui, LIU Xuejun, LYU Hongqiang. Missile aerodynamic performance prediction of Gaussian process through automatic kernel construction[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524093-524093.

参考文献

[1] 陈卫东, 唐小平, 曾奎, 等. 基于工程和数值方法的导弹气动特性计算[J]. 航空计算技术, 2012, 42(3):1-5. CHEN W D, TANG X P, ZENG K, et al. Calculation of missile aerodynamic characteristics based on engineering and numerical methods[J]. Aeronautical Computing Technique, 2012, 42(3):1-5(in Chinese).
[2] ROSEMA C, DOYLE J, AUMAN L, et al. Missile datcom user's manual-2011 revision[R]. Army Aviation and Missile Research Development Eng Ctr Redstone Arsenal Al System Simulation and Development Directorate, 2011.
[3] ROSEMA C C. A comparison of predictive methodologies for missile configurations with strakes[C]//33rd AIAA Applied Aerodynamics Conference. Reston:AIAA, 2015.
[4] LEVIN D, SIGAL A. Wind tunnel tests of a missile having elliptic cross sectioned body[C]//AIAA Atmospheric Flight Mechanics Conference and Exhibit. Reston:AIAA, 2002.
[5] ABNEY E, MCDANIEL M. High angle of attack aerodynamic predictions using missile datcom[C]//23rd AIAA Applied Aerodynamics Conference. Reston:AIAA, 2005.
[6] COIRIER W J, STUTTS J, ROSEMA C C. Development of a transonic fin aerodynamic database for incorporation into missile datcom[C]//32nd AIAA Applied Aerodynamics Conference. Reston:AIAA, 2014.
[7] DESPIRITO J. CFD aerodynamic characterization of 155-mm projectile at high angles-of-attack[C]//35th AIAA Applied Aerodynamics Conference. Reston:AIAA, 2017.
[8] 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).
[9] 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综述方法研究进展[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).
[10] AHEMD M Y. Surrogates for the aerodynamic coefficients of supersonic airfoils[C]//53rd AIAA Aerospace Sciences Meeting. Reston:AIAA, 2015.
[11] 彭博, 聂蓉梅, 陈海东. 基于支持向量机的火箭气动学科代理模型构建方法[J]. 导弹与航天运载技术, 2013(4):33-37. PENG B, NIE R M, CHEN H D. Surrogate model construction for rocket aerodynamic discipline based on support vector machine[J]. Missiles and Space Vehicles, 2013(4):33-37(in Chinese).
[12] CARPENTER M, HARTFIELD R, BURKHALETR J. A comprehensive approach to cataloging missile aerodynamic performance using surrogate modeling techniques and statistical learning[C]//29th AIAA Applied Aerodynamics Conference. Reston:AIAA, 2011.
[13] RITZ S G, HARTFIELD R J, DANLEN J A, et al. Rapid calculation of missile aerodynamic coefficients using artificial neural networks[C]//2015 IEEE Aerospace Conference, 2015:1-19.
[14] HAN Z H, GORTZ S. Hierarchical kriging model for variable-fidelity surrogate modeling[J]. AIAA Journal, 2012, 50(9):1885-1896.
[15] 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).
[16] ÇETINER A E, YSGIZ B, GUZEL G, et al. CFD based response surface modeling with an application in missile aerodynamics[C]//34th AIAA Applied Aerodynamics Conference. Reston:AIAA, 2016.
[17] WILLIAMS C K I, RASMUSSEN C E. Gaussian processes for machine learning[M]. Cambridge:MIT Press, 2006.
[18] ZHANG Y, SUNG W J, MAVRIS D N. Application of convolutional neural network to predict airfoil lift coefficient[C]//2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference. Reston:AIAA, 2018.
[19] YILMAZ E, GERMAN B. A convolutional neural network approach to training predictors for airfoil performance[C]//18th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. Reston:AIAA, 2017.
[20] 韩忠华, 张瑜, 许晨舟, 等. 基于代理模型的大型民机机翼气动优化设计[J]. 航空学报, 2019,40(1):522398. HAN Z H, ZHANG Y, XU C Z, et al. Aerodynamic optimization design of large civil aircraft wings using surrogate-based model[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(1):522398(in Chinese).
[21] 韩少强, 宋文萍, 韩忠华, 等. 基于梯度增强型Kriging模型的气动反设计方法[J]. 航空学报, 2017, 38(7):120817. HAN S Q, SONG W P, HAN Z H, et al. Aerodynamic inverse design method based on gradient-enhanced Kriging model[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(7):120817(in Chinese).
[22] LIU Z J, LIU X J, LYU H Q. A new hybrid aerodynamic optimization framework based on differential evolution and invasive weed optimization[J]. Chinese Journal of Aeronautics, 2018, 31(7):1437-1448.
[23] LE N D, ZIDEK J V. Statistical analysis of environmental space-time processes[M]. Springer Science & Business Media, 2006.
[24] DUVENAUD D, LLOYD J R, GROSSE R, et al. Structure discovery in nonparametric regression through compositional kernel search[DB/OL]. arXiv preprint:1302.4922, 2013.
[25] REGGENTE M, PETERS J, THEUNIS J, et al. Prediction of ultrafine particle number concentrations in urban environments by means of Gaussian process regression based on measurements of oxides of nitrogen[J]. Environmental Modelling & Software, 2014, 61:135-150.
[26] RICHARDSON R R, OSBORNE M A, HOWEY D A, et al. Gaussian process regression for forecasting battery state of health[J]. Journal of Power Sources, 2017,357:209-219.
[27] TOLBA H, DKHILI N, NOU J, et al. GHI forecasting using Gaussian process regression[C]. 2019.
[28] 高赫, 刘学军, 郭晋, 等. 基于高斯过程回归的连续式风洞马赫数控制[J]. 空气动力学学报, 2019, 37(3):480-487. GAO H, LIU X J, GUO J, et al. Mach number control of continuous wind tunnel based on Gaussian process regression[J]. Acta Aerodynamica Sinica, 2019, 37(3):480-487(in Chinese).
[29] HU J, WANG J. Short-term wind speed prediction using empirical wavelet transform and Gaussian process regression[J]. Energy, 2015, 93:1456-1466.
[30] DUVENAUD D. Automatic model construction with Gaussian processes[D]. Cambridge:University of Cambridge, 2014:1-47.
[31] MICCHELLI C A, XU Y, ZHANG H. Universal kernels[J]. Journal of Machine Learning Research, 2006, 7:2651-2667.
[32] DUVENAUD D K, NICKISCH H, RASMUSSEN C E. Additive gaussian processes[C]//Advances in Neural Information Processing Systems, 2011:226-234.
[33] SCHWARZ G. Estimating the dimension of a model[J]. The Annals of Statistics, 1978, 6(2):461-464.
[34] RASMUSSEN C E, NICKISCH H. The gpml toolbox version 4.0[R]. 2016.

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

基于自动核构造高斯过程的导弹气动性能预测

Missile aerodynamic performance prediction of Gaussian process through automatic kernel construction

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]	崔壮壮, 原昕, 赵国庆, 井思梦, 招启军. 共轴刚性旋翼高速直升机前飞性能操纵策略影响[J]. 航空学报, 2024, 45(9): 529256-529256.
[2]	柳家齐, 陈荣钱, 楼锦华, 韩旭, 吴昊, 尤延铖. 基于深度学习的高速直升机旋翼翼型气动优化设计[J]. 航空学报, 2024, 45(9): 529828-529828.
[3]	高同州, 贺小帆, 王晓雷, 李紫光, 朱振涛, 詹志新. 基于CDM理论与SVM模型的2014-T6铝合金疲劳寿命预测[J]. 航空学报, 2024, 45(7): 228952-228952.
[4]	张春云, 陈雄斌, 刘健, 崔苗. 酚醛树脂气凝胶复合材料热物性参数预测方法[J]. 航空学报, 2024, 45(6): 428848-428848.
[5]	陈树生, 冯聪, 张兆康, 赵轲, 张新洋, 高正红. 基于全局/梯度优化方法的宽速域乘波-机翼布局气动设计[J]. 航空学报, 2024, 45(6): 629596-629596.
[6]	李玉涵, 杨宝玉, 吴亦农, 张强, 唐晓. 卫星光机载荷热模型参数高效修正方法研究进展[J]. 航空学报, 2024, 45(6): 628814-628814.
[7]	倪育德, 闫苗玉, 刘瑞华. 基于DOA-BP神经网络的电离层TEC短期预测[J]. 航空学报, 2024, 45(4): 328707-328707.
[8]	郝振洋, 秦岭, 曹鑫, 张绮瑶, 周强. 机械天线阵列系统的伺服优化及调制方式[J]. 航空学报, 2024, 45(3): 328692-328692.
[9]	杨倩, 王彦哲, 杨迪, 李泽众, 曲巍崴. 基于数据驱动的纤维增强复合材料自动铺放速度预测与规划[J]. 航空学报, 2024, 45(10): 429313-429313.
[10]	张大蔚, 刘国平. 时变通信约束下航天器绕飞的高阶全驱预测控制方法[J]. 航空学报, 2024, 45(1): 628633-628633.
[11]	熊华杰, 安怡竞, 吴主龙, 周志宏. 欧拉壁膜模型在结冰模拟中的扩展[J]. 航空学报, 2023, 44(S2): 729287-729287.
[12]	刘哲, 张羲格, 韦常柱, 崔乃刚. 亚轨道飞行器再入轨迹高精度自适应凸规划[J]. 航空学报, 2023, 44(S2): 729430-729430.
[13]	曹煜琪, 付皓然, 高飞, 吕熙敏. 基于MPCC的鸭翼尾座式垂直起降无人机轨迹跟踪控制算法[J]. 航空学报, 2023, 44(S2): 729950-729950.
[14]	董豪泽, 陈昱达, 刘丹, 李忠奎. 障碍物空间下分布式轨迹规划的死锁破解[J]. 航空学报, 2023, 44(S2): 729771-729771.
[15]	杨倩, 郑皓冉, 程显达, 董威. 基于引气控制的热气防冰优化设计方法[J]. 航空学报, 2023, 44(S2): 729285-729285.