基于增量学习的非定常气动力参数化降阶模型

陈志强; 刘战合; 苗楠; 冯伟

doi:10.7527/S1000-6893.2021.25103

航空学报 >

2021 , Vol. 42 >Issue 7: 125103 - 125103

DOI: https://doi.org/10.7527/S1000-6893.2021.25103

流体力学与飞行力学

基于增量学习的非定常气动力参数化降阶模型

陈志强 ,
刘战合 ,
苗楠 ,
冯伟

展开

1. 郑州航空工业管理学院航空工程学院, 郑州 450046;
2. 河南工业大学机电工程学院, 郑州 450046

收稿日期: 2020-12-14

修回日期: 2021-03-23

网络出版日期: 2021-04-27

基金资助

国家自然科学基金（11702255）；河南省科技攻关计划（212102210052，212102210334，202102210267，202102210509，202102210288）

收起

Parametric reduced-order model of unsteady aerodynamics based on incremental learning algorithm

CHEN Zhiqiang ,
LIU Zhanhe ,
MIAO Nan ,
FENG Wei

Expand

1. School of Aeronautical Engineering, Zhengzhou University of Aeronautics, Zhengzhou 450046, China;
2. School of Electromechanical Engineering, Henan University of Technology, Zhengzhou 450046, China

Received date: 2020-12-14

Revised date: 2021-03-23

Online published: 2021-04-27

Supported by

National Natural Science Foundation of China (11702255); The Science and Technology Research Project of Henan Province(212102210052, 212102210334,202102210267, 202102210509, 202102210288)

Fold

摘要

气动降阶模型（ROM）是预测非定常气动力的有效工具，具有高精度和低计算成本的优点，近年来许多研究证实了该方法的有效性。但是关于飞行参数变化时，ROM的鲁棒性还需要进一步提高。为了提高ROM对不同飞行参数下的气动力预测能力，提出了基于最小二乘支持向量回归（LS-SVR）和增量学习算法的参数化降阶模型。LS-SVR是一种具有良好泛化能力的回归方法，基于LS-SVR的增量学习算法的主要贡献是在增加新样本集时，不需要重新学习整个数据集。为说明该方法的有效性，基于两自由度NACA64A010翼型构建参数化非定常气动力降阶模型。为了训练气动力输入和相应输出之间的关系，将马赫数和迎角作为附加的模型输入。仿真结果表明，该降阶模型能够准确描述气动力和气动弹性系统在不同飞行参数下的动态特性。

关键词： 非定常气动力; 参数化降阶模型; 最小二乘支持向量回归; 增量学习算法; 颤振

本文引用格式

陈志强 , 刘战合 , 苗楠 , 冯伟 . 基于增量学习的非定常气动力参数化降阶模型[J]. 航空学报, 2021 , 42(7) : 125103 -125103 . DOI: 10.7527/S1000-6893.2021.25103

Abstract

The aerodynamic Reduced-Order Model (ROM) is a useful tool in the prediction of nonlinear unsteady aerodynamics with reasonable accuracy and low computational cost. The efficacy of this method has been validated by recent studies. However, the robustness of ROMs with respect to flight parameter variations should be further improved. To enhance the prediction capability of ROMs for varying flight parameters, this paper presents two parametric reduced-order models based on the Least Squares Support Vector Regression (LS-SVR) and the incremental learning algorithm. LS-SVR is a class of regression methods with good generalization ability, and the main contribution of the incremental learning algorithm based on LS-SVR is that it is not necessary to relearn the whole data set while the new sample sets are incremented. To illustrate the approach, we construct the parametric unsteady aerodynamic ROMs of the NACA64A010 airfoil model with two degrees of freedom. The Mach number and angle of attack are considered as the additional model inputs to train the relationship between aerodynamic inputs and the corresponding outputs. It is demonstrated that the model can accurately capture the dynamic characteristics of aerodynamic and aeroelastic systems for varying flight parameters.

Key words： unsteady aerodynamics; parametric reduced-order models; least squares support vector regression; incremental learning algorithms; flutter

参考文献

[1] 胡海岩, 赵永辉, 黄锐. 飞机结构气动弹性分析与控制研究[J]. 力学学报, 2016, 48(1):1-27. HU H Y, ZHAO Y H, HUANG R. Studies on aeroelastic analysis and control of aircraft structures[J]. Chinese Journal of Theoretical and Applied Mechanics, 2016, 48(1):1-27(in Chinese).
[2] LUCIA D J, BERAN P S, SILVA W A. Reduced-order modeling:new approaches for computational physics[J]. Progress in Aerospace Sciences, 2004, 40(1-2):51-117.
[3] 陈刚, 李跃明. 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]. Advances in Mechanics, 2011, 41(6):686-701(in Chinese).
[4] 任峰,高传强,唐辉.机器学习在流动控制领域的应用及发展趋势[J].航空学报, 2021, 42(4):524686. REN F, GAO C Q, TANG H. Machine learning for flow control:applications and trends[J].Acta Aeronautica et Astronautica Sinica,2021,42(4):524686(in Chinese).
[5] NOACK B R, AFANASIEV K, MORZYN'SKI M, et al. A hierarchy of low-dimensional models for the transient and post-transient cylinder wake[J]. Journal of Fluid Mechanics, 2003, 497:335-363.
[6] HU J W, LIU H R, WANG Y G, et al. Reduced order model for unsteady aerodynamic performance of compressor cascade based on recursive RBF[J]. Chinese Journal of Aeronautics, 2021, 34(4):341-351.
[7] PROCTOR J L, BRUNTON S L, KUTZ J N. Dynamic mode decomposition with control[DB/OL]. arXiv preprint:1409.6358,2014.
[8] BRUNTON S L, PROCTOR J L, KUTZ J N. Discovering governing equations from data by sparse identification of nonlinear dynamical systems[J]. Proceedings of the National Academy of Sciences of the United States of America, 2016, 113(15):3932-3937.
[9] ROWLEY C W, MEZIC' I, BAGHERI S, et al. Spectral analysis of nonlinear flows[J]. Journal of Fluid Mechanics, 2009, 641:115-127.
[10] SILVA W A, BARTELS R E. Development of reduced-order models for aeroelastic analysis and flutter prediction using the CFL3Dv6.0 code[J]. Journal of Fluids and Structures, 2004, 19(6):729-745.
[11] YAO W, MARQUES S. Prediction of transonic limit-cycle oscillations using an aeroelastic harmonic balance method[J]. AIAA Journal, 2015, 53(7):2040-2051.
[12] WINTER M, BREITSAMTER C. Neurofuzzy-model-based unsteady aerodynamic computations across varying freestream conditions[J]. AIAA Journal, 2016, 54(9):2705-2720.
[13] LI K, KOU J Q, ZHANG W W. Deep neural network for unsteady aerodynamic and aeroelastic modeling across multiple Mach numbers[J]. Nonlinear Dynamics, 2019, 96(3):2157-2177.
[14] SUN Z W, WANG C, ZHENG Y, et al. Non-intrusive reduced-order model for predicting transonic flow with varying geometries[J]. Chinese Journal of Aeronautics, 2020, 33(2):508-519.
[15] WANG Q, QIAN W Q, HE K F. Unsteady aerodynamic modeling at high angles of attack using support vector machines[J]. Chinese Journal of Aeronautics, 2015, 28(3):659-668.
[16] 陈森林, 高正红, 朱新奇, 等. 非稳定动态过程非定常气动力建模[J]. 航空学报, 2020, 41(8):123675. CHEN S L, GAO Z H, ZHU X Q, et al. Unsteady aerodynamic modeling of unstable dynamic process[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(8):123675(in Chinese).
[17] SCHILDERS W H A, VAN DER VORST H A, ROMMES J. Model order reduction:theory, research aspects and applications[M]. Berlin:Springer, 2008.
[18] HUANG R, LIU H J, YANG Z J, et al. Nonlinear reduced-order models for transonic aeroelastic and aeroservoelastic problems[J]. AIAA Journal, 2018, 56(9):3718-3731.
[19] KLOCK R J, CESNIK C E S. Nonlinear thermal reduced-order modeling for hypersonic vehicles[J]. AIAA Journal, 2017, 55(7):2358-2368.
[20] YANG C, LIANG K, RONG Y F, et al. A hybrid reduced-order modeling technique for nonlinear structural dynamic simulation[J]. Aerospace Science and Technology, 2019, 84:724-733.
[21] YANG Z J, HUANG R, LIU H J, et al. An improved nonlinear reduced-order modeling for transonic aeroelastic systems[J]. Journal of Fluids and Structures, 2020, 94:102926.
[22] 张伟伟, 高传强, 叶正寅. 复杂跨声速气动弹性现象及其机理分析[J]. 科学通报, 2018, 63(12):1095-1110. ZHANG W W, GAO C Q, YE Z Y. The complex transonic aeroelastic phenomena and it's mechanisms[J]. Chinese Science Bulletin, 2018, 63(12):1095-1110(in Chinese).
[23] AMSALLEM D, FARHAT C. Interpolation method for adapting reduced-order models and application to aeroelasticity[J]. AIAA Journal, 2008, 46(7):1803-1813.
[24] AMSALLEM D, TEZAUR R, FARHAT C. Real-time solution of linear computational problems using databases of parametric reduced-order models with arbitrary underlying meshes[J]. Journal of Computational Physics, 2016, 326:373-397.
[25] CHEN Z Q, ZHAO Y H, HUANG R. Parametric reduced-order modeling of unsteady aerodynamics for hypersonic vehicles[J]. Aerospace Science and Technology, 2019, 87:1-14.
[26] LIU H J, HU H Y, ZHAO Y H, et al. Efficient reduced-order modeling of unsteady aerodynamics robust to flight parameter variations[J]. Journal of Fluids and Structures, 2014, 49:728-741.
[27] KOU J Q, ZHANG W W. Reduced-order modeling for nonlinear aeroelasticity with varying Mach numbers[J]. Journal of Aerospace Engineering, 2018, 31(6):04018105.
[28] ZHANG W W, KOU J Q, WANG Z Y. Nonlinear aerodynamic reduced-order model for limit-cycle oscillation and flutter[J]. AIAA Journal, 2016, 54(10):3304-3311.
[29] SKUJINS T, CESNIK C E S. Reduced-order modeling of unsteady aerodynamics across multiple Mach regimes[J]. Journal of Aircraft, 2014, 51(6):1681-1704.
[30] LIU H J, HUANG R, ZHAO Y H, et al. Reduced-order modeling of unsteady aerodynamics for an elastic wing with control surfaces[J]. Journal of Aerospace Engineering, 2017, 30(3):04016083.
[31] WINTER M, BREITSAMTER C. Neurofuzzy-model-based unsteady aerodynamic computations across varying freestream conditions[J]. AIAA Journal, 2016, 54(9):2705-2720.
[32] LI K, KOU J Q, ZHANG W W. Deep neural network for unsteady aerodynamic and aeroelastic modeling across multiple Mach numbers[J]. Nonlinear Dynamics, 2019, 96(3):2157-2177.
[33] HORN R A, JOHNSON C R. Matrix analysis[M]. Cambridge:Cambridge University Press, 2009.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献