基于深度自动编码器神经网络的飞行器翼型参数降维与优化设计

doi:10.12382/bgxb.2021.0346

摘要/Abstract

摘要： 传统飞行器翼型参数化描述方法在翼型优化设计研究中因变量较多导致优化效率低、计算工作量大，为此提出一种基于深度自动编码器（DAE）的神经网络模型。将该模型用于翼型优化设计研究中描述参数降维问题，研究经该模型降维后各翼型描述参数的物理意义，并与本征正交分解法（POD）对翼型描述参数降维效果进行对比。在给定的优化设计目标与约束条件下，设计基于代理模型和遗传算法的翼型优化方法，对RAE2822翼型进行跨声速来流下的优化设计，将所提模型与类别形状函数变换法（CST）、POD方法的优化效率与翼型优化效果进行对比。对比结果表明，所提利用DAE神经网络模型的方法优化效率更高，在跨声速来流下对RAE2822进行减阻优化设计结果明显优于CST方法、POD方法。

关键词: 飞行器, 翼型优化设计, 参数降维, 深度自动编码器, 神经网络, 代理模型

Abstract: The traditional parametric description methods of aircraft airfoil have lead to low optimization efficiency and heavy calculation workload because of large amount of variables in optimization design.A neural network model based on deep autoencoder(DAE) is proposed to solve the dimensionality reduction of description parameters in airfoil optimization design. The physical meaning of each parameter output by the model is analyzed，the dimensionality reduction effect of the model on airfoil description parameters is compared with that of the proper orthogonal decomposition(POD) method. Under the given design objectives and constraints，an optimization design framework based on surrogate model and genetic algorithm is used for RAE2822 airfoil optimization in the transonic flow.The airfoil optimization design effects of the proposed model，Class Shape Function Transformation(CST) method and POD method are compared，which proves that the proposed method with neural network based on DAE has higher optimization efficiency，and it performs obviously better than both CST and POD methods in drag reduction design of RAE2822 in transonic flow.

Key words: aircraft, airfoiloptimizationdesign, parameterdimensionalityreduction, deepautoencoder, neuralnetwork, surrogatemodel

中图分类号:

V211

吴则良，叶建川，王江，金忍. 基于深度自动编码器神经网络的飞行器翼型参数降维与优化设计[J]. 兵工学报, 2022, 43(6): 1326-1336.

WU Zeliang， YE Jianchuan， WANG Jiang， JIN Ren. Parameter Dimensionality Reduction and Optimal Design of Aircraft Airfoil Based on Deep Autoencoder Neural Network[J]. Acta Armamentarii, 2022, 43(6): 1326-1336.

参考文献

［1］ SHAHROKHI A，JAHANGIRIAN A.Airfoil shape parameterization for optimum Navier-Stokes design with genetic algorithm[J].Aerospace Science & Technology，2007，11 (6): 443-450.
[2］ WU X，ZHANG W，PENG X，et al.Benchmark aerodynamic shape optimization with the POD-based CST airfoil parametric method[J].Aerospace Ence and Technology，2018，84: S1270963817323532.
[3］廖炎平，刘莉，龙腾.几种翼型参数化方法研究[J].弹箭与制导学报，2011，32(3):160-164.
LIAO Y P，LIU L，LONG T.The Research on some parameterized methods for airfoil[J].Journal of Projectiles Rockets Missiles and Guidance，2011，32(3):160-164.(in Chinese)
[4］ TSAI J T，LIU T K，CHOU J H.Hybrid Taguchi-genetic algorithm for global numerical optimization[J].IEEE Transactions on Evolutionary Computation，2004，8(4):365-377.
[5］ LI J，CAI J，QU K.Surrogate-based aerodynamic shape optimization with the active subspace method[J].Structural and Multidisciplinary Optimization，2019，59(2):403-419.
[6］ IULIANO E.Global optimization of benchmark aerodynamic cases using physics-based surrogate models[J].Aerospace Science and Technology，2017，67: 273-286.
[7］ ARIYARIT A，KANAZAKI M.Multi-fidelity multi-objective efficient global optimization applied to airfoil design problems[J].Applied Sciences，2017，7(12):1318.
[8］ HAN Z H，GOERTZ S.Hierarchical kriging model for variable-fidelity surrogate modeling[J].AIAA Journal，2012，50(9):1885-1896.
[9］ KULFAN B M.The “CST” universal parametric geometry representation method，recent extensions and applications[C]∥Proceedings of Royal Aeronautical Society Confrences. Hamilton Place, London, UK:AIAA, 2007:157-176.
[10］ KULFAN B M.Recent extensions and applications of the ‘CST’universal parametric geometry representation method[J].The Aeronautical Journal，2010，114(1153):157-176.
[11］ KULFAN B M.Universal parametric geometry representation method[J].Journal of Aircraft，2008，45(1):142-158.
[12］ JEONG S，MURAYAMA M，YAMAMOTO K.Efficient optimization design method using kriging model[J].Journal of Aircraft，2005，42(5):1375-1375.
[13］ HOTELLING H.Analysis of a complex of statistical variables in principal components[J].Journal of Educational Psychology，1933，24(7):498-520.
[14］ TAO J，SUN G，GUO L，et al.Application of a PCA-DBN-based surrogate model to robust aerodynamic design optimization[J].Chinese Journal of Aeronautics，2020，33(12):1573-1588.
[15］ CHATTERJEE A.An introduction to the proper orthogonal decomposition[J].Current Science，2000，78(7):171-174.
[16］ RUMELHART D E，HINTON G E，WILLIAMS R J.Learning representations by back-propagating errors[J].Nature，1986，323(6088): 533-536.
[17］ KRIZHEVSKY A，SUTSKEVER I，HINTON G E.Imagenet classification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems，2012，25:1097-1105.
[18］ IOFFE S,NORMALIZATION C S B.Accelerating deep network training by reducing internal covariate shift［J］.arXiv preprint arXiv:1502.03167,2014.
[19］ CHENG X，ZHANG Y，CHEN Y，et al.Pest identification via deep residual learning in complex background[J].Computers and Electronics in Agriculture，2017，141:351-356.
[20］ OWEN A B.Latin supercube sampling for very high-dimensional simulations[J].ACM Transactions on Modeling and Computer Simulation (TOMACS)，1998，8(1): 1-102.
［21］钱龙,常思江,倪旖.旋转稳定弹扰流片气动外形多目标优化设计［J］.兵工学报,2021,42(12):2575-2585.
QIAN L，CHANG S J，NI Y.Multi-objective optimization of aerodynamic shape of microspoiler for spin-stabilized projectile［J］.Acta Armamentarii,2021,42(12):2575-2585.
(in Chinese)
[22］ GOLBERG D E.Genetic algorithms in search，optimization，and machine learning[J].Addion Wesley，1989，1989(102):36.

[1]	崔令飞，郭永红，修全发，史超，张硕阳. 基于国产嵌入式智能计算平台的无人机检测方法[J]. 兵工学报, 2022, 43(S1): 146-154.
[2]	赵春明，焦胜海，王晓飞，姚跃民，黄朝东. 柔性充气空间飞行器姿态控制系统设计[J]. 兵工学报, 2022, 43(6): 1346-1354.
[3]	李彬，谢新，唐文勇，陶江平，孙宜强，张辉. 基于近似模型的复合材料导管支臂结构性能分析[J]. 兵工学报, 2022, 43(6): 1435-1446.
[4]	励明君，姜毅，马立琦，潘霄. 基于神经网络算法的发射场坪承载能力预测方法[J]. 兵工学报, 2022, 43(5): 982-991.
[5]	袁航，罗迎，李开明，陈怡君，张群. 基于涡旋电磁波雷达的人体目标步态精细识别[J]. 兵工学报, 2022, 43(5): 1167-1174.
[6]	赵文辉，孙晓恒，张伟东，郑鹏，杨帆. 四旋翼飞行器齿轮箱-支臂组件动态特性分析[J]. 兵工学报, 2022, 43(5): 1175-1184.
[7]	辛大钧，薛琨. 基于人工神经网络的非球形破片阻力系数预测模型[J]. 兵工学报, 2022, 43(5): 1083-1092.
[8]	石安华，李海燕，石卫波，梁世昌. 临近空间高超声速巡航飞行器红外特征[J]. 兵工学报, 2022, 43(4): 796-803.
[9]	张通彤, 姜湖海, 岳巍, 司晨, 袁满. 基于径向基函数神经网络的光电系统自适应控制[J]. 兵工学报, 2022, 43(3): 556-564.
[10]	田北晨，刘涛涛，吴钦，黄彪. 跨介质飞行器触水滑跳运动特性数值模拟[J]. 兵工学报, 2022, 43(3): 586-598.
[11]	骆亮，裴扬，侯鹏，张梦涛，李明锁. 飞机燃油箱油气空间引燃概率函数预测模型[J]. 兵工学报, 2022, 43(2): 383-390.
[12]	周颖，谢振平，蒋晓军. 基于演化计算的迷彩目标隐蔽策略仿真设计[J]. 兵工学报, 2021, 42(9): 1987-1997.
[13]	李恒, 叶祖坤, 查文彬, 王禹林. 基于多传感器信息决策级融合的刀具磨损在线监测[J]. 兵工学报, 2021, 42(9): 2024-2031.
[14]	普运伟，刘涛涛，郭江，吴海潇. 基于卷积神经网络和模糊函数主脊坐标变换的雷达辐射源信号识别[J]. 兵工学报, 2021, 42(8): 1680-1689.
[15]	杨昌志，姜毅，牛钰森，王璟慧. 飞行器往复式滑翔延时弹道特性[J]. 兵工学报, 2021, 42(7): 1372-1380.