基于DCGAN的终端区激光雷达晴空湍流识别

doi:10.7527/S1000-6893.2024.29748

Abstract

Abstract:

A study was conducted on the problem of insufficient turbulence samples and low recognition rate when using Doppler wind lidar for clear-air turbulence recognition in the flight terminal area. An improved Deep Convolutional Generative Adversarial Network （DCGAN） algorithm was proposed. Eddy Dissipation Rate （EDR） images were constructed using the radial wind speed data of nine months from the Doppler wind lidar experimental platform of the Lanzhou Zhongchuan International Airport. Samples with clear-air turbulence were selected to construct a turbulence sample set， the DCGAN structure was improved by expanding the convolutional layer and transposing the convolutional layer， so as to achieve sample expansion. The post-confrontation was then used for recognition. The results show that the recognition accuracy of the post-confrontation discriminator trained with the original sample set and that trained with the augmented sample set are both better than that trained with the Convolutional Neural Network （CNN） and the pre-confrontation discriminator， with improvements of 6.55%， 8.25%， and 0.31%， 1.9%， respectively. A comparison with the measured samples shows that the recognition accuracy was improved by 3.33% and 6.67%， verifying the feasibility of the proposed method.

Key words: Doppler wind lidar, clear-air turbulence, Eddy Dissipation Rate (EDR), Deep Convolutional Generative Adversarial Network (DCGAN), discriminator

CLC Number:

V321.2⁺25

Zibo ZHUANG, Chunhui ZHANG, Xing CHEN, Jingyuan SHAO, Pakwai CHAN. Clear⁃air turbulence recognition by Doppler⁃wind⁃lidar in terminal area based on DCGAN[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(16): 329748-329748.

Figures/Tables 17

Fig.1

Fig.2

Fig.3

Table 1

Fig.4

Table 2

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

Table 3

Fig.14

References 40

1	PROSSER M C， WILLIAMS P D， MARLTON G J， et al. Evidence for large increases in clear-air turbulence over the past four decades［J］. Geophysical Research Letters， 2023， 50（11）： 1-8.
2	STORER L N， WILLIAMS P D， JOSHI M M. Global response of clear‐air turbulence to climate change［J］. Geophysical Research Letters， 2017， 44（19）： 9976-9984.
3	SOLANKI R， GUO J P， LV Y M， et al. Elucidating the atmospheric boundary layer turbulence by combining UHF radar wind profiler and radiosonde measurements over urban area of Beijing［J］. Urban Climate， 2022， 43： 101151.
4	LV Y M， GUO J P， LI J， et al. Spatiotemporal characteristics of atmospheric turbulence over China estimated using operational high-resolution soundings［J］. Environmental Research Letters， 2021， 16（5）： 05405.
5	WU Y Z， GUO J P， CHEN T M， et al. Forecasting precipitation from radar wind profiler mesonet and reanalysis using the random forest algorithm［J］. Remote Sensing， 2023， 15（6）： 1635.
6	YANG R F， GUO J P， DENG W L， et al. Investigation of turbulent dissipation rate profiles from two radar wind profilers at plateau and plain stations in the North China Plain［J］. Remote Sensing， 2023， 15（16）： 4103.
7	WILDMANN N， PÄSCHKE E， ROIGER A， et al. Towards improved turbulence estimation with Doppler wind lidar Velocity-Azimuth Display（VAD） scans［J］.Atmospheric Measurement Techniques， 2020， 13（8）： 4141-4158.
8	VAN DYK R N， PARISEAU D H， DODSON R E， et al. Systems integration of unmanned aircraft into the national airspace： Part of the Federal Aviation Administration next generation air transportation system［C］∥ 2012 IEEE Systems and Information Engineering Design Symposium. Piscataway： IEEE Press， 2012： 156-161.
9	方向，林雯，陶韬. 南京信息工程大学智能遥感工程研究院夏海云：争气，为祖国做最好的激光雷达！［N］. 江苏科技报，2022-05-27（A08）.
	FANG X， LIN W， TAO T. Xia Haiyun， Institute of intelligent remote sensing engineering， Nanjing university of information science and technology： Make the best lidar for the motherland！［N］. Jiangsu Science and Technology News，2022-05-27（A08） .（in Chinese）
10	董骁，胡以华，徐世龙，等. 不同气溶胶环境中相干激光雷达回波特性［J］. 光学学报， 2018， 38（1）： 0101001.
	DONG X， HU Y H， XU S L， et al. Echoing characteristics of coherent lidar in different aerosol environments［J］. Acta Optica Sinica， 2018， 38（1）： 0101001 （in Chinese）.
11	方巍，庞林，张飞鸿，等. 对抗型长短期记忆网络的雷达回波外推算法［J］. 中国图象图形学报， 2021， 26（5）： 1067-1080.
	FANG W， PANG L， ZHANG F H， et al. Radar echo extrapolation algorithm based on adversarial long short-term memory network［J］. Journal of Image and Graphics， 2021， 26（5）： 1067-1080 （in Chinese）.
12	KRIZHEVSKY A， SUTSKEVER I， HINTON G E. ImageNet classification with deep convolutional neural networks［J］. Communications of the ACM， 2017， 60（6）： 84-90.
13	SZEGEDY C， LIU W， JIA Y Q， et al. Going deeper with convolutions［C］∥ 2015 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2015： 1-9.
14	HE K M， ZHANG X Y， REN S Q， et al. Deep residual learning for image recognition［C］∥ 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2016： 770-778.
15	王佳宇. 基于深度学习的变电设备铭牌文本识别研究［D］. 南京：东南大学， 2020.
	WANG J Y. Research on text recognition of substation equipment nameplate based on deep learning［D］.Nanjing： Southeast University， 2020 （in Chinese）.
16	CHUQUICUSMA M J M， HUSSEIN S， BURT J， et al. How to fool radiologists with generative adversarial networks？ A visual turing test for lung cancer diagnosis［C］∥ 2018 IEEE 15th International Symposium on Biomedical Imaging （ISBI 2018）. Piscataway： IEEE Press， 2018： 240-244.
17	GOODFELLOW I J， POUGET-ABADIE J， MIRZA M， et al. Generative adversarial nets［C］∥ Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. New York： ACM， 2014： 2672–2680.
18	田洁华，孙迪，屈峰，等. 基于CST-GAN的翼型参数化方法［J］. 航空学报， 2023， 44（18）： 128280.
	TIAN J H， SUN D， QU F， et al. Airfoil parameterization method based on CST-GAN［J］. Acta Aeronautica et Astronautica Sinica， 2023， 44（18）： 128280 （in Chinese）.
19	HUANG R， DUAN B K， ZHANG Y X， et al. Prior-guided GAN-based interactive airplane engine damage image augmentation method［J］. Chinese Journal of Aeronautics， 2022， 35（10）： 222-232.
20	ZHOU H J， BAI J， WANG Y R， et al. Few-shot electromagnetic signal classification： A data union augmentation method［J］. Chinese Journal of Aeronautics， 2022， 35（9）： 49-57.
21	WU H Z， LIU X J， AN W， et al. A generative deep learning framework for airfoil flow field prediction with sparse data［J］. Chinese Journal of Aeronautics， 2022， 35（1）： 470-484.
22	WANG J， LI R Z， HE C， et al. An inverse design method for supercritical airfoil based on conditional generative models［J］. Chinese Journal of Aeronautics， 2022， 35（3）： 62-74.
23	孙磊，杨宇，毛秀青，等. 基于空间特征的生成对抗网络数据生成方法［J］. 电子与信息学报， 2023， 45（6）： 1959-1969.
	SUN L， YANG Y， MAO X Q， et al. Data generation based on generative adversarial network with spatial features［J］. Journal of Electronics & Information Technology， 2023， 45（6）： 1959-1969 （in Chinese）.
24	CAI J X， ZHANG Y， DOVIAK R J， et al. Diagnosis and classification of typhoon-associated low-altitude turbulence using HKO-TDWR radar observations and machine learning［J］. IEEE Transactions on Geoscience and Remote Sensing， 2019， 57（6）： 3633-3648.
25	OLIVEIRA M M， BIDINOTTO J H. flight turbulence level classificator using a multilayer perceptron network trained with flight test data［J］. IEEE Latin America Transactions， 2020， 18（5）： 954-961.
26	MUÑOZ-ESPARZA D， SHARMAN R D， DEIERLING W. Aviation turbulence forecasting at upper levels with machine learning techniques based on regression trees［J］. Journal of Applied Meteorology and Climatology， 2020， 59（11）： 1883-1899.
27	叶舒然，张珍，王一伟，等. 基于卷积神经网络的深度学习流场特征识别及应用进展［J］. 航空学报， 2021， 42（4）： 524736.
	YE S R， ZHANG Z， WANG Y W， et al. Progress in deep convolutional neural network based flow field recognition and its applications［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（4）： 524736 （in Chinese）.
28	魏晓良，潮群，陶建峰，等. 基于LSTM和CNN的高速柱塞泵故障诊断［J］. 航空学报， 2021， 42（3）： 423876.
	WEI X L， CHAO Q， TAO J F， et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（3）： 423876 （in Chinese）.
29	韩淞宇，邵海东，姜洪开，等. 基于提升卷积神经网络的航空发动机高速轴承智能故障诊断［J］. 航空学报， 2022， 43（9）： 625479.
	HAN S Y， SHAO H D， JIANG H K， et al. Intelligent fault diagnosis of aero-engine high-speed bearings using enhanced CNN［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（9）： 625479 （in Chinese）.
30	李红光，于若男，丁文锐. 基于深度学习的小目标检测研究进展［J］. 航空学报， 2021， 42（7）： 024691.
	LI H G， YU R N， DING W R. Research development of small object traching based on deep learning［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（7）： 024691 （in Chinese）.
31	ZHAO G， HU J Y， XIAO W L， et al. A mask R-CNN based method for inspecting cable brackets in aircraft［J］. Chinese Journal of Aeronautics， 2021， 34（12）： 214-226.
32	LI Y B， DU X Q， WAN F Y， et al. Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging［J］. Chinese Journal of Aeronautics， 2020， 33（2）： 427-438.
33	ZHOU D， XIAO Z， ZUO H. A hybrid deep neural network based on multi-time window convolutional bidirectional LSTM for civil aircraft APU hazard identification［J］. Chinese Journal of Aeronautics，2022，35（4）：344-361.
34	RADFORD A， METZ L， CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks［DB/OL］. arXiv preprint：1511.06434，2015.
35	卫奥尼，秦成兵，董帅，等. 超分辨荧光显微成像的若干研究进展［J］. 激光与光电子学进展， 2023， 60（11）： 1106012.
	WEI A N， QIN C B， DONG S， et al. Research progress of super-resolution fluorescence microscopy［J］. Laser & Optoelectronics Progress， 2023， 60（11）：1106012. （in Chinese）.
36	GLOROT X， BORDES A， BENGIO Y. Deep sparse rectifier neural networks［J］.Journal of Machine Learning Research， 2011，15： 315-323.
37	IOFFE S， SZEGEDY C. Batch normalization： Accelerating deep network training by reducing internal covariate shift［C］∥ Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37. New York： ACM， 2015： 448-456.
38	MAAS A L， HANNUN A Y， NG A Y. Rectifier nonlinearities improve neural network acoustic models［C］∥ International Conference on Machine Learning （ICML），2013.
39	DAVIES F， COLLIER C G， PEARSON G N， et al. Doppler lidar measurements of turbulent structure function over an urban area［J］. Journal of Atmospheric and Oceanic Technology， 2004， 21（5）： 753-761.
40	HEUSEL M， RAMSAUER H， UNTERTHINER T， et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium［C］∥ Proceedings of the 31st International Conference on Neural Information Processing Systems. New York： ACM， 2017： 6629-6640.

参数	数值
扫描距离间隔/m	50
数据刷新率/s	约3
扫描角度间隔/（°）	5
俯仰角/（°）	3
最大扫描高度/m	128
5 km内数据获取率	≥85%

$E D R 1 / 3$ /（ $m 2 / 3 · s - 1$ ）	湍流强度
$≤ 0.1$	无
$(0.1,0.4]$	轻度
$(0.4,0.7]$	中度
> $0.7$	重度

对比方法	原始样本集识别准确率/%	增广样本集识别准确率/%
TD	91.11	99.68
CNN	84.56	99.37
UD	82.86	97.78

[1]	ZHANG Shengfei, LI Tianmei, HU Changhua, DU Dangbo, SI Xiaosheng. Missing data generation method and its application in remaining useful life prediction based on deep convolutional generative adversarial network [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 225708-225708.
[2]	QI Farui, ZHANG Tisheng, LI Zhuo, TANG Hailiang. A FFT frequency discriminator for improving the dynamic tracking performance of GNSS weak signal [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2018, 39(8): 321932-321932.
[3]	ZHANG Wei;SHEN Shi-tuan;LI Yi-hua;SUN Bao-jiang. A Decision Tree Implementation Approach on the Optimal Fault Discernment Effect Presented with Test Nodes and Specifications for Analog Circuit [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2004, 25(3): 293-296.

Clear⁃air turbulence recognition by Doppler⁃wind⁃lidar in terminal area based on DCGAN

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 40

Related Articles 3

Recommended Articles 0

Metrics

Comments