基于U-Net的磁浮飞行风洞气动力干扰剥离算法

邓果垚; 胡喆; 许德军; 张军; 倪章松

doi:10.7638/kqdlxxb-2024.0197

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U-Net的磁浮飞行风洞气动力干扰剥离算法

研究论文 | 更新时间：2026-05-28

- 基于U-Net的磁浮飞行风洞气动力干扰剥离算法
- Aerodynamic force measurement algorithm based on U-Net in maglev flight wind tunnel
- 空气动力学学报 2026年44卷第2期页码：59-67
- 作者机构：
  
  成都流体动力创新中心,成都,610071
- 作者简介：
  
  邓果垚（1999—），男，四川绵阳人，研究实习员，研究方向：人工智能. E-mail：741533684@qq.com
  张军*，副研究员，研究方向：气动声学及特种风洞试验技术. E-mail：jzhang@nudt.edu.cn
- 基金信息：
- DOI：10.7638/kqdlxxb-2024.0197
  中图分类号： V211.74;TP18;V212.1
- 纸质出版：2026
- 稿件说明：
移动端阅览
邓果垚, 胡喆, 许德军, 等. 基于U-Net的磁浮飞行风洞气动力干扰剥离算法[J]. 空气动力学学报, 2026, 44(2): 59−67.

Deng Guoyao, Hu Zhe, Xu Dejun, et al. Aerodynamic force measurement algorithm based on U-Net in maglev flight wind tunnel[J]. 2026, 44(2): 59-67.
邓果垚, 胡喆, 许德军, 等. 基于U-Net的磁浮飞行风洞气动力干扰剥离算法[J]. 空气动力学学报, 2026, 44(2): 59−67. DOI： 10.7638/kqdlxxb-2024.0197

Deng Guoyao, Hu Zhe, Xu Dejun, et al. Aerodynamic force measurement algorithm based on U-Net in maglev flight wind tunnel[J]. 2026, 44(2): 59-67. DOI： 10.7638/kqdlxxb-2024.0197.

摘要

运动模型加速阶段的气动力测量技术是磁浮飞行风洞中的关键技术难题之一。气动力测量天平在加速段受到惯性力等各种强干扰，致使被测气动力值被掩盖。为在强干扰、低信噪比的严苛条件下还原气动力信号，提出了一种基于深度学习的气动力干扰剥离算法。首先针对天平信号作短时傅里叶变换以确定各干扰频谱特征，从而作为算法模型输入；然后构建“编码器-解码器”架构模型对天平所测复杂信号进行特征提取并精准重建所期望的气动力信号。经过在测试集上的全面评估，该算法在气动力干扰剥离方面表现优秀，在阻力、升力、俯仰力矩三分量上的气动力信号重建精度达到了92.7%。本研究提出的方法为磁浮飞行风洞加速段的气动力测量问题提供了一种可行的技术途径。

Abstract

The aerodynamic force measurement technology during the acceleration phase of the motion model is one of the key technical challenges in the maglev flight wind tunnel. The aerodynamic force measurement balance is subjected to various strong interferences such as inertial forces in the acceleration section

which masks the measured aerodynamic force values. In order to restore the aerodynamic force signal under the harsh conditions of strong interference and low signal-to-noise ratio

this study proposed an aerodynamic force interference stripping algorithm based on deep learning. Firstly

the short-time Fourier transform was applied to the balance signal to determine the spectral characteristics of each interference

which was used as the input of the algorithm model. Then

an "encoder-decoder" architecture model was constructed to extract features from the complex signals measured by the balance and accurately reconstruct the desired aerodynamic force signal. After a comprehensive evaluation on the test set

the proposed algorithm demonstrated excellent performance in aerodynamic interference stripping

achieving a corresponding reconstruction accuracy of approximately 92.7% for the drag

lift

and pitching moment components. This study provides strong support for the aerodynamic force measurement in the future test environment of the maglev flight wind tunnel.

关键词

Keywords

references

Yu Xinning, Jiang Xintong, Zhang Jun, et al. Application of typical magnetic suspension system in maglev flight wind tunnel[J]. Journal of Experiments in Fluid Mecahnics, 2023, 37(3): 27−36 (in Chinese). doi: 10.11729/syltlx20220149

Ni Zhangsong, Zhang Jun, Fu Cheng, et al. Analyses of the test techniques and applications of maglev flight tunnels[J]. Acta Areodynamica Sinica, 2021, 39(5): 95−110 (in Chinese). doi: 10.7638/kqdlxxb-2021.0206

Hu Zhe, Zhang Jun, Ni Zhangsong, et al. Numerical study on the vibration characteristics of a moving model system used in maglev flight wind tunnel[J]. Journal of Vibration and Shock, 2025, 44(2): 143−150 (in Chinese). doi: 10.13465/j.cnki.jvs.2025.02.015

Zhang Xun, Li Fuhua, Zhu Benhua, et al. Development of integrated five component hinge moment balance[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2020, 40(4): 29−33 (in Chinese). doi: 10.15892/j.cnki.djzdxb.2020.04.007

Lyu Jinzhou, Zhang Xiaoqing, Cheng Guangxiong, et al. Transient simulation for dynamic output of force measuring balance in an impulse combustion wind tunnel based on inertia compensation[J]. Journal of Vibration and Shock, 2018, 37(2): 216: 216−222 (in Chinese). doi: 10.13465/j.cnki.jvs.2018.02.032

Li Hongyan, Zhou Yunlong, Tian Feng, et al. Wavelet-based vibration signal denoising algorithm with a new adaptive threshold function[J]. Chinese Journal of Scientific Instrument, 2015, 36(10): 7 (in Chinese).

Nie Shaojun, Wang Yunpeng. Signal analysis and processing of shock tunnel balance based on time-frequency transform[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(1): 232−243 (in Chinese). doi: 10.6052/0459-1879-21-387

Zhu W, Mousavi S M, Beroza G C. Seismic signal denoising and decomposition using deep neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(11): 9476−9488. doi: 10.1109/TGRS.2019.2926772

Tang Zhigong, Zhu Linyang, Xiang Xinghao, et al. Some research progress and prospect of intelligent aerodynamics[J]. Acta Aerodynamica Sinica, 2023, 41(7): 1−35 (in Chinese).

Wang Chao, Wang Guigong, Bai Peng. Machine learning method for aerodynamic modeling based on flight simulation data[J]. Acta Areodynamica Sinica, 2019, 37(3): 488−497 (in Chinese). doi: 10.7638/kqdlxxb-2019.0024

Wang Yunpeng, Yang Ruixin, Nie Shaojun, et al. Deep-learning-based intelligent force measurement system using in a shock tunnel[J]. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(5): 1304−1313 (in Chinese). doi: 10.6052/0459-1879-20-190

Nie Shaojun, Wang Yunpeng, Wang Chun, et al. Deep learning modeling analysis method of frequency-domain data of shock wind tunnel force measurement signals[J]. Journal of Vibration and Shock, 2023, 42(13): 296: 296−302 (in Chinese). doi: 10.13465/j.cnki.jvs.2023.13.035

Zhai Wanming. Vehicle-track coupled dynamics(Volume 1)[M]. Fourth Edition, Beijing: Science Press, 2014 (in Chinese).

Zhang Geng, Li Jie, Yang Zijing. Estimation of power spectrum density track irregularities of low-speed maglev railway lines[J]. Journal of the China Railway Society, 2011, 33(10): 73−78 (in Chinese).

Kiranyaz S, Avci O, Abdeljaber O, et al. 1D convolutional neural networks and applications: a survey[J]. Mechanical Systems and Signal Processing, 2021, 151: 107398. doi: 10.1016/j.ymssp.2020.107398

Kaur M, Mohta A. A review of deep learning with recurrent neural network[C]//2019 International Conference on Smart Systems and Inventive Technology (ICSSIT). 2019: 460−465. doi: 10.1109/ICSSIT46314.2019.8987837

Siddique N, Paheding S, Elkin C P, et al. U-Net and its variants for medical image segmentation: a review of theory and applications[J]. IEEE Access, 2021, 9: 82031−82057. doi: 10.1109/ACCESS.2021.3086020

Li Z, Liu W, Wu G, et al. Semantic segmentation of unmanned aerial vehicle image based on resnet-unet[C]//2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), 2023, 8: 295−299. doi: 10.1109/ICIIBMS60103.2023.10347663

Wang Yi, Gong Xiaojie, Su Hao. Image segmentation method of surface defects of metal workpiece based on improved U-net[J]. Journal of Applied Optics, 2023, 44(1): 86−92 (in Chinese). doi: 10.5768/JAO202344.0102004

Cui H, Xing T, Ren J, et al. eSwin-UNet: a collaborative model for industrial surface defect detection[C]//2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS). 2023: 379-386. doi: 10.1109/ICPADS56603.2022.00056

Moreno-Torres J G, Raeder T, Alaiz-Rodríguez R, et al. A unifying view on dataset shift in classification[J]. Pattern Recognition, 2012, 45(1): 521−530. doi: 10.1016/j.patcog.2011.06.019

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

空气动力学领域大模型研究思考与展望

基于条件扩散模型的火箭气动外形快速设计方法

面向磁浮飞行风洞的运动声源定位和评估方法

定常来流下钝体二维组合断面气动特性与流场的智能预测方法

基于物理约束深度学习的大跨柔性光伏阵列绕流场重构