面向民机标模的宽域高雷诺数小样本气动建模方法研究

宁晨伽; 吴继飞; 李国帅; 张伟伟

doi:10.7638/kqdlxxb-2023.0208

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

面向民机标模的宽域高雷诺数小样本气动建模方法研究

高雷诺数复杂流动问题研究 | 更新时间：2026-07-27

- 面向民机标模的宽域高雷诺数小样本气动建模方法研究
- Research on few-shot aerodynamic modeling methods for civil aircraft model with wide-range high Reynolds number
- 空气动力学学报 2024年42卷第8期页码：60-76
- 作者机构：
  
  1. 西北工业大学航空学院,西安,710072
  2. 中国空气动力研究与发展中心高速空气动力研究所,绵阳,621000
- 作者简介：
  
  宁晨伽（1998—），研究方向：多源同/异构气动力融合与关联建模研究. E-mail：ningjjx@163.com
  张伟伟*（1979—），教授，研究方向：流体力学/气动弹性力学研究. E-mail：aeroelastic@nwpu.edu.cn
- 基金信息：
  
  国家自然科学基金面上项目（12072282）;国家自然科学基金集成项目（92152301）
- DOI：10.7638/kqdlxxb-2023.0208
  中图分类号： O354;V211.5
- 纸质出版：2024
- 稿件说明：
移动端阅览
宁晨伽, 吴继飞, 李国帅, 等. 面向民机标模的宽域高雷诺数小样本气动建模方法研究[J]. 空气动力学学报, 2024, 42(8): 60−76.

NING Chenjia, WU Jifei, LI Guoshuai, et al. Research on few-shot aerodynamic modeling methods for civil aircraft model with wide-range high Reynolds number[J]. 2024, 42(8): 60-76.
宁晨伽, 吴继飞, 李国帅, 等. 面向民机标模的宽域高雷诺数小样本气动建模方法研究[J]. 空气动力学学报, 2024, 42(8): 60−76. DOI： 10.7638/kqdlxxb-2023.0208

NING Chenjia, WU Jifei, LI Guoshuai, et al. Research on few-shot aerodynamic modeling methods for civil aircraft model with wide-range high Reynolds number[J]. 2024, 42(8): 60-76. DOI： 10.7638/kqdlxxb-2023.0208.

摘要

目前飞行雷诺数下复杂工况地面试验需要的运行成本极高，高雷诺数流态下的试验数据少而稀，变雷诺数气动力精确模化存在严重的数据不均衡和小样本问题，因此，气动仿真精度亟待提升。为解决变雷诺数气动力获取成本与模型精度之间的矛盾，聚焦后续飞行器设计的降本增效，以CHN-T1运输机标模为研究对象，通过数据融合和信息迁移两大策略，降低了预测模型对高雷诺数样本的依赖，实现了宽域高雷诺数小样本气动特性的快速预测。本研究利用覆盖亚跨声速、百万至千万量级变雷诺数下的18条气动力曲线构建了宽域变雷诺数气动数据集，设计了涵盖不同速域、雷诺数和马赫数外插等多种复杂度的算例进行分析验证，将仅利用单一来源试验数据构建的模型精度作为基准，对比了不同方法的特点。结果表明，利用10条左右的高精度气动力曲线作为建模数据时，采用基于神经网络的数据融合方法得到的气动预测模型均方根误差可降低50%以上，信息迁移方法得到的气动力预测模均方根误差也可降低至少40%。

Abstract

To enhance the independent development capability and efficiency of new strategic aircraft

it is crucial to accurately acquire aerodynamic data over a wide range of high Reynolds numbers. There is an urgent need to improve the accuracy of aerodynamic simulations for complex flow conditions at flight Reynolds numbers

and to address the high cost associated with ground testing in cryogenic wind tunnels. The experimental data at high Reynolds numbers are few and sparse

and there are serious data imbalance and few-shot problems in the accurate aerodynamic modeling under wide-range Reynolds numbers. To solve the contradiction between the cost and accuracy of the aerodynamic model under variable Reynolds number

and focus on the cost reduction and efficiency increase of subsequent aircraft design

this study takes the CHN-T1 transport aircraft as the research objective. Based on data fusion and information transfer techniques

we achieve the rapid prediction of variable Reynolds number aerodynamics through few-shot learning. This approach reduces the reliance on high Reynolds number samples in the modeling process. In the present study

a wide-ranging variable Reynolds number aerodynamic dataset is constructed using a combination of 18 aerodynamic curves. These curves encompass sub-transonic speeds and variable Reynolds numbers ranging from millions to tens of millions. Additionally

various complexity cases are designed for demonstration. As a verification

a benchmark is established using high-fidelity experimental data through a single source method. The characteristics of different methods are then compared. The results demonstrate that when approximately 10 high-fidelity aerodynamic curves are utilized as modeling data

the data fusion neural network reduces the root mean square error of aerodynamic modeling by over 50%. Additionally

the information transfer method reduces the error by at least 40%.

关键词

Keywords

references

WANG Q, QIAN W Q, DING D . A review of unsteady aerodynamic modeling of aircrafts at high angles of attack[J ] . Acta Aeronautica et Astronautica Sinica, 2016 , 37 ( 8 ): 2331 − 2347 (in Chinese).

XU R F, QIAN R Z, LEI W T . Numerical investigation of Reynolds number effects on aerodynamics characteristics of high lift system for turboprop aircraft[J ] . Advances in Aeronautical Science and Engineering, 2016 , 7 ( 4 ): 420 − 425 (in Chinese).

XUE R, RUAN Y X, LAI H, et al . Numerical simulation of liquid nitrogen spray cooling in cryogenic wind tunnel[J ] . Cryogenics, 2019 ( 1 ): 35 − 40 (in Chinese).

LOVING D L. Wind-tunnel-flight correlation of shock-induced separated flow[M]. Washington, DC : National Aeronautics and Space Administration, 1966.

KILGORE R. Evolution and development of cryogenic wind tunnels[C]// 43rd AIAA Aerospace Sciences Meeting and Exhibit, Reno, Nevada. Reston, Virigina: AIAA, 2005.

LIAO D X, HUANG Z L, CHEN Z H, et al . Review on large-scale cryogenic wind tunnel and key technologies[J ] . Journal of Experiments in Fluid Mechanics, 2014 , 28 ( 2 ): 1 − 6,20 (in Chinese).

ZHOU Z, HUANG J T, HUANG Y, et al . CFD technology in aerona utic engineering field: applications, challenges and development[J ] . Acta Aeronautica et Astronautica Sinica, 2017 , 38 ( 3 ): 020891 (in Chinese).

BRUCE W, GLOSS B B. The US National Transonic Facility, NTF [R]. 1989.

GREEN J, QUEST J . A short history of the European Transonic Wind Tunnel ETW[J ] . Progress in Aerospace Sciences, 2011 , 47 ( 5 ): 319 − 368 .

PEHERSTORFER B, WILLCOX K, GUNZBURGER M . Survey of multifidelity methods in uncertainty propagation, inference, and optimization[J ] . SIAM Review, 2018 , 60 ( 3 ): 550 − 591 .

GHOREYSHI M, BADCOCK K J, WOODGATE M A . Accelerating the numerical generation of aerodynamic models for flight simulation[J ] . Journal of Aircraft, 2009 , 46 ( 3 ): 972 − 980 .

FORRESTER A I J, SÓBESTER A, KEANE A J. Multi-fidelity optimization via surrogate modelling[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2007, 463(2088): 3251-3269.

GRATIET L L . Recursive co-kriging model for design of computer experiments with multiple levels of fidelity[J ] . International Journal for Uncertainty Quantification, 2014 , 4 ( 5 ): 365 − 386 .

TAO J, SUN G . Application of deep learning based multi-fidelity surrogate model to robust aerodynamic design optimization[J ] . Aerospace Science and Technology, 2019 , 92 : 722 − 737 .

LIU D H, WANG Y . Multi-fidelity physics-constrained neural network and its application in materials modeling[J ] . Journal of Mechanical Design, 2019 , 141 ( 12 ): 121403 .

MENG X H, KARNIADAKIS G E . A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems[J ] . Journal of Computational Physics, 2020 , 401 : 109020 .

XU C Z, DU T, HAN Z H, et al . Comparison of machine learning data fusion methods applied to aerodynamic modeling of rocket first stage with grid fins[J ] . Journal of Experiments in Fluid Mechanics, 2022 , 36 ( 3 ): 79 − 92 .

PENG X H, KOU J Q, ZHANG W W . Multi-fidelity nonlinear unsteady aerodynamic modeling and uncertainty estimation based on Hierarchical Kriging[J ] . Applied Mathematical Modelling, 2023 , 122 : 1 − 21 .

HUANG L K, GAO Z H, ZHANG D H . Research on multi-fidelity aerodynamic optimization methods[J ] . Chinese Journal of Aeronautics, 2013 , 26 ( 2 ): 279 − 286 .

HUANG L K, GAO Z H, ZHANG D H . Aerodynamic optimization based on multi-fidelity surrogate[J ] . Acta Aerodynamica Sinica, 2013 , 31 ( 6 ): 783 − 788 (in Chinese).

PRIYANKA R, SIVAPRAGASAM M . Multi-fidelity surrogate model-based airfoil optimization at a transitional low Reynolds number[J ] . Sādhanā, 2021 , 46 ( 1 ): 58 .

ROHIT R J, GANGULI R . Co-kriging based multi-fidelity uncertainty quantification of beam vibration using coarse and fine finite element meshes[J ] . International Journal for Computational Methods in Engineering Science and Mechanics, 2022 , 23 ( 2 ): 147 − 168 .

LIU X W, ZHAO W W, WAN D C . Multi-fidelity Co-Kriging surrogate model for ship hull form optimization[J ] . Ocean Engineering, 2022 , 243 : 110239 .

ZHANG X S, XIE F F, JI T W, et al . Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization[J ] . Computer Methods in Applied Mechanics and Engineering, 2021 , 373 : 113485 .

WANG X, KOU J Q, ZHANG W W . Unsteady aerodynamic prediction for iced airfoil based on multi-task learning[J ] . Physics of Fluids, 2022 , 34 ( 8 ): 087117 .

HE L, QIAN W Q, ZHAO T, et al . Multi-fidelity aerodynamic data fusion with a deep neural network modeling method[J ] . Entropy, 2020 , 22 ( 9 ): 1022 .

MAHMOUDABADBOZCHELOU M, CAGGIONI M, SHAHSAVARI S, et al . Data-driven physics-informed constitutive metamodeling of complex fluids: a multifidelity neural network (MFNN) framework[J ] . Journal of Rheology, 2021 , 65 ( 2 ): 179 − 198 .

PAN S J, YANG Q . A survey on transfer learning[J ] . IEEE Transactions on Knowledge and Data Engineering, 2010 , 22 ( 10 ): 1345 − 1359 .

HE K F, QIAN W Q, WANG Q, et al . Application of data fusion technique in aerodynamics studies[J ] . Acta Aerodynamica Sinica, 2014 , 32 ( 6 ): 777 − 782 (in Chinese).

LI K, KOU J Q, ZHANG W W . Deep learning for multi-fidelity aerodynamic distribution modeling from experimental and simulation data[J ] . AIAA Journal, 2022 , 60 ( 7 ): 4413 − 4427 .

KOU J Q, NING C J, ZHANG W W . Transfer learning for flow reconstruction based on multifidelity data[J ] . AIAA Journal, 2022 , 60 ( 10 ): 1 − 22 .

SUBEL A, CHATTOPADHYAY A, GUAN Y F, et al . Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning[J ] . Physics of Fluids, 2021 , 33 ( 3 ): 031702 .

DAI J H, LIU P Q, QU Q L, et al . Aerodynamic optimization of high-lift devices using a 2D-to-3D optimization method based on deep reinforcement learning and transfer learning[J ] . Aerospace Science and Technology, 2022 , 121 : 107348 .

CHAKRABORTY S . Transfer learning based multi-fidelity physics informed deep neural network[J ] . Journal of Computational Physics, 2021 , 426 : 109942 .

ZHANG Y B, TANG J, CHEN J T, et al . Aerodynamic characteristics prediction of CHN-T1 standard model with unstructured grid[J ] . Acta Aerodynamica Sinica, 2019 , 37 ( 2 ): 262 − 271 (in Chinese).

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于多精度深度神经网络的汽车气动外形优化设计方法

基于 XGBoost 的多源气动数据融合建模

基于物理信息神经网络的气动数据融合方法

高速空气动力学三大手段数据融合研究进展

基于不确定度和气动模型的气动数据融合算法