基于柔性智能蒙皮的翼型流场预测和重建方法

来五星; 赵浩哲; 黄林; 冀晶晶; 黄永安

doi:10.7638/kqdlxxb-2024.0139

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 >

基于柔性智能蒙皮的翼型流场预测和重建方法

研究论文 | 更新时间：2026-05-28

- 基于柔性智能蒙皮的翼型流场预测和重建方法
- Flow field prediction and reconstruction of aircraft based on flexible smart skin
- 空气动力学学报 2025年43卷第12期页码：121-134
- 作者机构：
  
  华中科技大学智能制造装备与技术全国重点实验室,武汉,430074
- 作者简介：
  
  来五星（1972—），男，湖北赤壁人，副教授，研究方向：智能制造、智能预测. E-mail：wxlai@hust.edu.cn
  黄永安*，教授，研究方向：柔性电子器件制造与应用（飞行器智能蒙皮等）. E-mail： yahuang@hust.edu.cn
- 基金信息：
  
  国家重点研发计划（2021YFB3200700）;国家自然科学基金（52175536，U23A20111）
- DOI：10.7638/kqdlxxb-2024.0139
  中图分类号： V211.3
- 纸质出版：2025
- 稿件说明：
移动端阅览
来五星, 赵浩哲, 黄林, 等. 基于柔性智能蒙皮的翼型流场预测和重建方法[J]. 空气动力学学报, 2025, 43(12): 121−134.

LAI Wuxing, ZHAO Haozhe, HUANG Lin, et al. Flow field prediction and reconstruction of aircraft based on flexible smart skin[J]. 2025, 43(12): 121-134.
来五星, 赵浩哲, 黄林, 等. 基于柔性智能蒙皮的翼型流场预测和重建方法[J]. 空气动力学学报, 2025, 43(12): 121−134. DOI： 10.7638/kqdlxxb-2024.0139

LAI Wuxing, ZHAO Haozhe, HUANG Lin, et al. Flow field prediction and reconstruction of aircraft based on flexible smart skin[J]. 2025, 43(12): 121-134. DOI： 10.7638/kqdlxxb-2024.0139.

摘要

飞行器的气动问题会引发机翼结冰、飞行失速等安全隐患，通过监测气动载荷数据、研究其流场特性有助于解决这一问题。柔性智能蒙皮提供了温敏漆、压敏漆等风洞试验手段不具备的飞行过程数据采集功能，在获取飞行数据方面展现出巨大潜力。但感知的多物理场数据分布稀疏、数量有限，难以实现转捩、失速位置精确识别。本文针对机翼全流场重构问题，提出了一种基于柔性智能蒙皮的流场高分辨率的快速重建方法，以获取空间密度更大的气动载荷数据，开发了基于编码器-解码器网络架构的双分支通道注意力融合模型，该模型能够快速预测52种NACA翼型在156种不同自由来流条件下的二维流场，实现相对误差为3.68%的二维翼型流场快速预测；利用快速预测模型生成的M6翼型周围流场数据，基于浅层神经网络开发了流场重建模型，在2.73%相对误差内快速重建空间分辨率更高的全域流场分布，为智能蒙皮进一步飞行应用提供数据支撑。

Abstract

Real-time analysis and prediction of flow field characteristics are essential for flight safety and necessitating in-flight data acquisition

an almost impossible task for traditional techniques such as temperature/pressure-sensitive paints. Flexible smart skins demonstrate great promise for acquiring in-flight data. Nevertheless

the multi-physical data collected are usually sparsely in distribution and limited in quantity

making it difficult to accurately identify transition and stall locations. To overcome this limitation

we introduce a novel method for rapidly reconstructing high-resolution flow fields around aircraft wings from sparse data. Leveraging the flow fields computed by CFL3D

a dual-branch attention fusion model is developed based on an encoder-decoder network. This model facilitates rapid prediction of 2D flow fields for 52 types of NACA airfoils under 156 different freestream conditions

achieving an average relative error of 3.68% and providing a substantial amount of high-fidelity training data for the reconstruction process. Furthermore

using flow fields around the M6 airfoil generated by the rapid prediction model

a flow field reconstruction model is developed based on a shallow neural network. This model fulfills rapid reconstruction of high-resolution flow fields with a relative error of 2.73%. This work establishes a valuable data foundation for the in-flight application of smart skins

enhancing real-time monitoring capabilities and improving flight safety through accurate flow field reconstructions and insights.

关键词

Keywords

references

TABRIZIAN A, TATAR M, EIVAZI H, et al. An experimental study on boundary layer transition detection over a pitching supercritical airfoil using hot-film sensors[J]. International Journal of Heat and Fluid Flow, 2020, 86: 108743. doi: 10.1016/j.ijheatfluidflow.2020.108743

DU W C, CHEN Z. Data-driven rapid prediction of surface heat flux for lifting-body aircraft[J]. Acta Aerodynamica Sinica, 2025, 43(7): 93−107 (in Chinese). doi: 10.7638/kqdlxxb-2025.0109

LI Z H, CHEN A G, YANG Y G, et al. Numerical study of vibrational non-equilibrium flow at low temperature[J]. Acta Aerodynamica Sinica, 2024, 42(11): 55−62 (in Chinese). doi: 10.7638/kqdlxxb-2023.0149

RUDMIN D, BENAISSA A, POIREL D. Detection of laminar flow separation and transition on a NACA-0012 airfoil using surface hot-films[J]. Journal of Fluids Engineering, 2013, 135(10): 101104. doi: 10.1115/1.4024807

CHEN S Y, GUO X D, WANG Z X, et al. Preliminary research on size measurement of supercooled large droplet in icing wind tunnel[J]. Journal of Experiments in Fluid Mechanics, 2021, 35(3): 22−29 (in Chinese). doi: 10.11729/syltlx20200104

GAO W T, ZHANG W L, KOU B Z. Study on buffet flight test of aircraft with T-tail[J]. Journal of Experiments in Fluid Mechanics, 2020, 34(6): 45−51 (in Chinese). doi: 10.11729/syltlx20200040

KUESTER M S, BORGOLTZ A, DEVENPORT W J. Pressure tap effects on the lift measurement of an airfoil section[C]//32nd AIAA Aerodynamic Measurement Technology and Ground Testing Conference, Washington, USA. AIAA, 2016. doi: 10.2514/6.2016-3654

LI G, HAN J, WANG F. Influence and resolution of variable frequency speed regulation system of wind tunnel on hot-wire anemometer[J]. Measurement Control Technology, 2022, 41(11): 78−83 (in Chinese). doi: 10.19708/j.ckjs.2022.11.012

HUO J J, YI S H, NIU H B, et al. Experimental study of flow on the leeward side of a cone at a high angle of attack based on temperature sensitive paint[J]. Physics of Gases, 2022, 7(4): 67−76 (in Chinese).

SUN X G, LI Y H. Review of the development of temperature measurement technology with infrared thermal imager[J]. Laser Infrared, 2008, 38(2): 101−104 (in Chinese). doi: 10.3969/j.issn.1001-5078.2008.02.001

LI X T, LIU X, LIU Y Z, et al. Experimental study of near-wall underexpanded jet impingement on a flat plate using temperature-insensitive semi-transparent pressure-sensitive paint[J]. Experiments in Fluids, 2020, 61(11): 232. doi: 10.1007/s00348-020-03068-5

CHEN H, GUO M M, TIAN Y, et al. Progress of convolution neural networks in flow field reconstruction[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(9): 2343−2360 (in Chinese). doi: 10.6052/0459-1879-22-130

ZHAO X, DENG Z C, ZHANG W W. Sparse reconstruction of surface pressure coefficient based on compressed sensing[J]. Experiments in Fluids, 2022, 63(10): 156. doi: 10.1007/s00348-022-03505-7

ZHAO X, DU L, PENG X H, et al. Research on refined reconstruction method of airfoil pressure based on compressed sensing[J]. Theoretical and Applied Mechanics Letters, 2021, 11(2): 100223. doi: 10.1016/j.taml.2021.100223

ZHAO X, PENG X H, DENG Z C, et al. Fine reconstruction method of airfoil surface pressure based on multi-source data fusion[J]. Journal of Experiments in Fluid Mechanics, 2022, 36(3): 93−101 (in Chinese). doi: 10.11729/syltlx20210166

ZHANG Q, ZHAO X, LI K, et al. Prediction model of aircraft hinge moment: Compressed sensing based on proper orthogonal decomposition[J]. Physics of Fluids, 2024, 36(7): 076102. doi: 10.1063/5.0214653

ZHANG Q, WANG X, YANG D G, et al. Data-driven prediction of aerodynamic noise of transonic buffeting over an airfoil[J]. Engineering Analysis with Boundary Elements, 2024, 163: 549−561. doi: 10.1016/j.enganabound.2024.04.006

HUANG J, GUO Y X, JI J J, et al. Aerodynamic pressure field reconstruction from sparse points using data assimilation method[J]. Journal of Experiments in Fluid Mechanics, 2023, 37(5): 9−17 (in Chinese). doi: 10.11729/syltlx20230021

SUN L N, WANG J X. Physics-constrained Bayesian neural network for fluid flow reconstruction with sparse and noisy data[J]. Theoretical and Applied Mechanics Letters, 2020, 10(3): 161−169. doi: 10.1016/j.taml.2020.01.031

YILMAZ E, GERMAN B. A convolutional neural network approach to training predictors for airfoil performance[C]//18th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Denver, Colorado. AIAA, 2017. doi: 10.2514/6.2017-3660

LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 86(11): 2278-2324. doi: 10.1109/5.726791

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, Kissimmee, Florida. AIAA, 2018. doi: 10.2514/6.2018-1903

TOLSTIKHIN L, HOULSBY N, KOLESNIKOV A, et al. Mlp-mixer: An all-mlp architecture for vision[C]//35th International Conference on Neural Information Processing Systems, 2021.

GUO M H, LIU Z N, MU T J, et al. Beyond self-attention: External attention using two linear layers for visual tasks[J]. IEEE Trans Pattern Anal Mach Intell, 2023, 45(5): 5436−5447. doi: 10.1109/tpami.2022.3211006

CHEN H, HE L, QIAN W Q, et al. Multiple aerodynamic coefficient prediction of airfoils using a convolutional neural network[J]. Symmetry, 2020, 12(4): 544. doi: 10.3390/sym12040544

ÖZBAY A G, LAIZET S. Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappings[J]. 2022, 12(4): 045126. doi: 10.1063/5.0087488

RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Cham: Springer International Publishing, 2015: 234-241. doi: 10.1007/978-3-319-24574-4_28

ERICHSON N B, MATHELIN L, YAO Z W, et al. Shallow neural networks for fluid flow reconstruction with limited sensors[J]. Proceedings Mathematical, Physical, and Engineering Sciences, 2020, 476(2238): 20200097. doi: 10.1098/rspa.2020.0097

LIU B, TANG J P, HUANG H B, et al. Deep learning methods for super-resolution reconstruction of turbulent flows[J]. Physics of Fluids, 2020, 32(2): 025105. doi: 10.1063/1.5140772

LIU Q, WANG D L. Stein variational gradient descent: A general purpose bayesian inference algorithm[C]//30th Conference on Neural Information Processing Systems, Barcelona, Spain. 2016.

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

多种SST湍流模型对典型分离流动的预测性能

基于多支微射流的超声速射流主动控制

无人机气动/风能获取一体化设计

基于稀疏神经核的多保真度代理模型

数据驱动的升力体飞行器表面热流快速预测