基于径向基神经网络的气动热预测代理模型

doi:10.7527/S1000-6893.2020.24167

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

基于径向基神经网络的气动热预测代理模型

张智超, 高太元, 张磊, 拓双芬

北京机电工程总体设计部, 北京 100039

收稿日期:2020-04-30 修回日期:2020-06-19 发布日期:2020-07-10
通讯作者: 张智超 E-mail:zhichaozhang_buaa@buaa.edu.cn

Aeroheating agent model based on radial basis function neural network

ZHANG Zhichao, GAO Taiyuan, ZHANG Lei, TUO Shuangfen

Beijing System Design Institute of Electro-mechanic Engineering, Beijing 100039, China

Received:2020-04-30 Revised:2020-06-19 Published:2020-07-10

摘要/Abstract

摘要： 为快速获取高超声速飞行器表面热流数据并缩短飞行器气动热设计周期，提出了一种基于径向基神经网络的气动热快速预测代理模型方法。首先，在飞行器表面每一个离散化的网格节点单独构造一种正则化的径向基神经网络。随后，通过训练集对所有网络同时进行训练，获得各自网络的连接权值。最后，所有网格节点的神经网络协同预测飞行器表面不同位置的热流。对NASA火星实验室的椭圆钝化高超声速飞行器的应用表明，所提出的代理模型方法在模型训练完成后能够快速进行飞行器表面热流预测，并且模型具有良好的泛化能力，在驻点及迎风大面积区域热流预测结果与数值模拟的偏差在10%以内。

关键词: 神经网络, 径向基函数, 高超声速, 气动热, 代理模型

Abstract: An aeroheating agent model based on the radial basis function neural network is proposed to rapidly acquire heat flux on the surface of hypersonic vehicles and shorten the aeroheating design cycle. A regularization radial basis function neural network is firstly constructed on each grid node of the solid surface, followed by the acquisition of the connection weights of different nerve cells through simultaneous training of all neural networks based on the data of the train set. Finally, the heat flux results of different positions on the surface of vehicles are predicted synergistically by the neural networks on grid nodes. The simulation results of the elliptical blunt vehicle designed by the Mars Science Laboratory of NASA indicate that the agent model can be employed to rapidly predict heat flux of hypersonic vehicles with good generalization capability. In addition, the results of heat flux on the stagnation point and the windward wall prove that the heat flux deviations between the agent model and numerical simulation are smaller than 10%.

Key words: neural networks, radial basis function, hypersonic, aeroheating, agent models

中图分类号:

V211.3

张智超, 高太元, 张磊, 拓双芬. 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): 524167-524167.

ZHANG Zhichao, GAO Taiyuan, ZHANG Lei, TUO Shuangfen. Aeroheating agent model based on radial basis function neural network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524167-524167.

参考文献

[1] 彭志雨, 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).
[2] 刘房彬, 袁军娅. 火星再入飞行器风洞实验与真实飞行之间相关性的探讨[J]. 北京航空航天大学学报, 2019, 45(4):787-795. LIU F B, YUAN J Y. Discussion on correlation between wind tunnel test and flight of Mars reentry vehicle[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(4):787-795(in Chinese).
[3] 陶阳, 宗群, 曾凡林. 高超声速飞行器气动模型数据拟合方法研究[C]//第三十一届中国控制会议论文集. 北京:中国自动化学会控制理论专业委员会, 2012:1275-1278. TAO Y, ZONG Q, ZENG F L. Research on data fitting method of aerodynamic model of hypersonic vehicle[C]//Proceedings of the 31 st Chinese Control Conference. Beijing:Technical Committee on Control Theory, Chinese Association of Automation, 2012:1275-1278(in Chinese).
[4] DOWELL E H. Eigenmode analysis in unsteady aerodynamics:Reduced order models[J]. AIAA Journal, 1996, 34(8):1578-1583.
[5] SILVA W. Identification of linear and nonlinear aerodynamic impulse responses using digital filter techniques:AIAA-1997-3712[R]. Reston:AIAA, 1997.
[6] 陈刚, 李跃名. 非定常流场降阶模型及其应用研究进展与展望[J]. 力学进展, 2011, 41(6):686-701. CHEN G, LI Y M. Advances and prospects of the reduced order model for unsteady flow and its application[J]. Advance in Mechanics, 2011, 41(6):686-701(in Chinese).
[7] 张伟, 高正红, 周琳, 等. 基于代理模型全局优化的自适应参数化方法[J]. 航空学报, 2020, 41(10):123815. ZHANG W, GAO Z H, ZHOU L, et al. Adaptive parameterization method for surrogate-based global optimization[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(10):123815(in Chinese).
[8] 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.
[9] 聂春生, 黄建栋, 王迅, 等. 基于POD方法的复杂外形飞行器热环境快速预测方法[J]. 空气动力学学报, 2017, 35(6):760-765. NIE C S, HUANG J D, WANG X, et al. Fast aeroheating prediction method for complex shape vehicles based on proper orthogonal decomposition[J]. Acta Aerodynamica Sinica, 2017, 35(6):760-765(in Chinese).
[10] 张天娇, 钱炜祺, 周宇, 等. 人工智能与空气动力学结合的初步思考[J]. 航空工程进展, 2019, 10(1):1-11. ZHANG T J, QIAN W Q, ZHOU Y, et al. Preliminary thoughts on the combination of artificial intelligence and aerodynamics[J]. Advances in Aeronautical Science and Engineering, 2019, 10(1):1-11(in Chinese).
[11] 陈海昕, 邓凯文, 李润泽. 机器学习技术在气动优化设计中的应用[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).
[12] 王孝学. RBF神经网络在再入体气动参数辨识中的应用研究[J]. 导弹与航天运载技术, 2002(6):5-8. WANG X X. Application of a RBF neural network in aerodynamic parameter indentification of a reentry body[J]. Missiles and Space Vehicles, 2002(6):5-8(in Chinese).
[13] 张锋涛, 崔凯, 杨国伟, 等. 基于神经网络技术的乘波体优化设计[J]. 力学学报, 2009, 41(3):418-424. ZHANG F T, CUI K, YANG G W, et al. Optimization design of waverider based on the artificial neural networks[J]. Chinese Journal of Theoretical and Applied Mechanics, 2009, 41(3):418-424(in Chinese).
[14] 寇家庆, 张伟伟. 基函数宽度对递归RBF神经网络气动力模型精度的影响研究[J]. 航空工程进展, 2015, 6(3):261-270. KOU J Q, ZJAMG W W. Research on the effects of function widths of aerodynamic modeling based on recursive RBF neural network[J]. Advances in Aeronautical Science and Engineering, 2015, 6(3):261-270(in Chinese).
[15] 白俊强, 王丹, 何小龙, 等. 改进的RBF神经网络在翼梢小翼优化设计中的应用[J]. 航空学报, 2014, 35(7):1865-1873. BAI J Q, WANG D, HE X L, et al. Application of an improved RBF neural network on aircraft winglet optimization design[J]. Acta Aeronautica et Astronautica Sinica, 2014, 35(7):1865-1873(in Chinese).
[16] 尹明朗, 寇家庆, 张伟伟. 一种高泛化能力的神经网络气动力降阶模型[J]. 空气动力学学报, 2017, 35(2):205-213. YIN M L, KOU J Q, ZHANG W W. A reduced-order aerodynamic model with high generalization capability based on neural network[J]. Acta Aerodynamica Sinica, 2017, 35(2):205-213(in Chinese).
[17] 张栋. 飞行仿真气动数据处理的神经网络应用[J]. 航空计算技术, 2002, 32(4):12-19. ZHANG D. Numerical simulation of a mixed compression supersonic inlet flow[J]. Aeronautical Computer Technique, 2002, 32(4):12-19(in Chinese).
[18] BROOMHEAD D S, LOWE D. Multivariable functional interpolation and adaptive networks[J]. Complex System, 1988, 2(3):321-355.
[19] MOODY J, DARKEN C J. Fast learning in network of locally-tuned processing units[J]. Neural Computation, 1989, 1(2):281-294.
[20] HOLLIS B R, HOLLINGSWORTH K E. Laminar, transitional, and turbulent heating on mid lift-to-drag ratio entry vehicles[J]. Journal of Spacecraft and Rockets, 2013, 50(5):937-949.
[21] 张智超, 高振勋, 蒋崇文, 等. 高超声速气动热数值计算壁面网格准则[J]. 北京航空航天大学学报, 2015, 41(4):594-600. ZHANG Z C, GAO Z X, JIANG C W, et al. Grid generation criterion in hypersonic aeroheating computations[J]. Journal of Beijing University of Aeronautics and Astronautics, 2015, 41(4):594-600(in Chinese).
[22] ZHANG Z C, GAO Z X, JIANG C W, et al. A RANS model correction on unphysical over-prediction of turbulent quantities across shock wave[J]. International Journal of Heat and Mass Transfer, 2017, 106:1107-1119.

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

基于径向基神经网络的气动热预测代理模型

Aeroheating agent model based on radial basis function neural network

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]	杨倩, 郭晓峰, 李芹, 董威. 基于POD和代理模型的热气防冰性能预测方法[J]. 航空学报, 2023, 44(1): 626992-626992.
[2]	牛俊杰, 桑为民, 李栋, 郝莲, 王泽林. 一种基于水滴收集量代理模型的结冰试飞空域确定方法[J]. 航空学报, 2023, 44(1): 627697-627697.
[3]	郭琪磊, 桑为民, 牛俊杰, 袁烨. 复杂气象条件下考虑结冰风险的无人机飞行策略[J]. 航空学报, 2023, 44(1): 627518-627518.
[4]	李昊歌, 杨华, 杨雨欣, 陈伟芳. 高超声速升力体迎风面精细化降热优化设计[J]. 航空学报, 2022, 43(S2): 124-137.
[5]	吴东, 杨鸿, 赵文峰, 罗跃. 高超声速飞行器碳基结构高温应变测量[J]. 航空学报, 2022, 43(S2): 160-169.
[6]	聂春生, 袁野, 马伟, 曹占伟, 于明星. 主动引射气体参数对平板空气舵气动热影响[J]. 航空学报, 2022, 43(S2): 170-179.
[7]	马正雪, 罗振兵, 赵爱红, 周岩, 谢玮, 刘强, 朱寅鑫, 彭文强. 高超声速流场等离子体合成射流逆向喷流特性[J]. 航空学报, 2022, 43(S2): 192-203.
[8]	化为卓, 高岭, 陈戈, 李益文, 巩耕, 王延涛, 魏彪. 基于等离子体炬的磁流体动力学实验系统[J]. 航空学报, 2022, 43(S2): 1-7.
[9]	黄依峰, 曾舒华, 江中正, 陈伟芳. 非线性耦合本构在高空侧向喷流中的数值研究[J]. 航空学报, 2022, 43(S2): 8-22.
[10]	罗凯, 王永海, 汪球, 栗继伟, 李峥, 聂春生, 李铮. 高焓风洞中等离子体激励流动控制试验[J]. 航空学报, 2022, 43(S2): 89-96.
[11]	张旭东, 李铮, 董昊, 高思源, 纪祖赑, 黎凯昕, 白光辉. 高超声速流场等离子体逆向喷流减阻特性[J]. 航空学报, 2022, 43(S2): 115-123.
[12]	胡守超, 庄宇, 李贤, 江涛. 高超声速气动热标模HyHERM-Ⅰ试验[J]. 航空学报, 2022, 43(S2): 233-248.
[13]	孙志坤, 史志伟, 张伟麟, 李铮, 孙琪杰. 等离子体激励器对高速翼型升阻特性的影响[J]. 航空学报, 2022, 43(S2): 23-39.
[14]	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.
[15]	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.