基于卷积神经网络的GFRP/NOMEX蜂窝夹层结构缺陷红外热成像检测

doi:10.3964/j.issn.1000-0593(2025)02-0542-09

Abstract
References
Related Citation (15)

Download: PDF (11318 KB)
Export: BibTeX | EndNote (RIS)

Abstract Honeycomb sandwich structure is one of the important structural forms in the field of composite materials. Due to its complex preparation process and harsh service environment, it is easy to produce delamination, debonding, and other defects, which seriously affect the service life of materials. To ensure the performance and quality safety of related components, it is necessary to carry out regular quality monitoring and flaw detection of the honeycomb sandwich structure through appropriate non-destructive testing technology. Therefore, quantitatively detecting defects is the fundamental way to prevent and solve such problems. Based on infrared thermal imaging technology to GFRP/NOMEX honeycomb sandwich structure specimens containing prefabricated delamination and debonding defects as the object of study for pulsed infrared thermal wave nondestructive testing experimental research, the acquisition of several frames of the specimen surface temperature distribution thermograms, take several defective areas and the healthy region of the pixel temperature signals to construct a sample dataset, and randomly divided into a training set and a validation set, take the fourth row of defective The center horizontal line area is taken as the test set data. Combined with convolutional neural network technology, GFRP/NOMEX honeycomb sandwich structure defect detection and depth prediction is completed. Analyze the -one-dimensional convolutional neural network structure, introduce multi-scale dilated convolution, residual module, and attention mechanism to build a one-dimensional convolutional neural network prediction model, and use the constructed temperature signal data set to train the network model. The training results show that the Loss and RMSE trends of the validation and training sets are consistent. The final Loss of the validation set is 1.67×10^-5, the RMSE is 0.005 8, and there is no over-fitting problem. The test set data is input into the trained network. The results show that the constructed network can effectively identify the defects and the depth prediction error at the defect center is controlled within 2%. It can be seen that the combination of convolutional neural network and infrared thermal imaging detection technology can realize the reliable detection of GFRP/NOMEX honeycomb sandwich structure defects and the stable prediction of defect burial depth and also provide a reference for the identification and quantitative detection of defects in other composite materials.

Key words：Honeycomb sandwich structure; Depth prediction; Convolutional neural network; Infrared thermal imaging

Received: 2024-02-24 Accepted: 2024-09-29

ZTFLH:

TN219

Cite this article:

TANG Qing-ju,GU Zhuo-yan,BU Hong-ru, et al. Infrared Thermography Detection of GFRP/NOMEX Honeycomb Sandwich Structure Defects Based on Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(02): 542-550.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)02-0542-09 OR https://www.gpxygpfx.com/EN/Y2025/V45/I02/542

[1] Tang Q J, Fan W M, Ji J, et al. Thermal Science, 2021, 25(6 Part B): 4611.
[2] LIU Ying-tao, GUO Guang-ping, WEN Lei, et al(刘颖韬, 郭广平, 温磊, 等). Nondestructive Testing(无损检测), 2011, 33(12): 81.
[3] Hu C, Duan Y, Liu S, et al. Infrared Physics & Technology, 2019, 102: 103032.
[4] Almond D P, Angioni S L, Pickering S G. NDT & E International, 2017, 87: 7.
[5] WEI Jia-cheng, LIU Jun-yan, HE Lin, et al(魏嘉呈, 刘俊岩, 何林, 等). Journal of Harbin University of Science and Technology(哈尔滨理工大学学报), 2020, 25(2): 64.
[6] WANG Yong-mao, GUO Xing-wang, LI Ri-hua(王永茂, 郭兴旺, 李日华). Laser & Infrared(激光与红外), 2002，(6): 404.
[7] Tang Q, Dai J, Liu J, et al. Infrared Physics & Technology, 2016, 77: 144.
[8] Saeed N, Abdulrahman Y, Amer S, et al. Infrared Physics & Technology, 2019, 98: 192.
[9] Wang Z, Wan L, Zhu J, et al. NDT & E International, 2022, 129: 102658.
[10] ZHOU Fei-yan, JIN Lin-peng, DONG Jun(周飞燕, 金林鹏, 董军). Chinese Journal of Computers(计算机学报), 2017, 40(6): 1229.
[11] MOU Xin-ying, HE Yun-ze, WANG Hong-jin, et al(牟欣颖, 何赟泽, 王洪金, 等). Journal of Electronic Measurement and Instrumentation(电子测量与仪器学报), 2021, 35(4): 211.
[12] CAI Jian-rong, HUANG Chu-jun, MA Li-xin, et al(蔡健荣, 黄楚钧, 马立鑫, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(9): 2792.
[13] CHEN Wei, WANG Fu-song, GUO Jing, et al(陈伟, 王复淞, 郭婧, 等). Journal of Mechanical & Electrical Engineering(机电工程), 2023, 40(5): 644.
[14] GUO Chen, JIAN Tao, XU Cong-an, et al(郭晨, 简涛, 徐从安, 等). Journal of Electronics & Information Technology(电子与信息学报), 2019, 41(6): 1302.
[15] Yu J, Zhang C, Wang S. Neural Computing and Applications, 2020, 33(8): 1.
[16] JIN Yu-feng, YAO Mei-chang, LIU Xiao-feng, et al(金余丰, 姚美常, 刘晓锋, 等). Mechanical Science and Technology for Aerospace Engineering(机械科学与技术), 2020, 39(6): 919.
[17] Peng D, Liu Z, Wang H, et al. IEEE Access, 2019, 710278.
[18] WANG Yi-ding, YAO Yi, LI Yao-li, et al(王一丁, 姚毅, 李耀利, 等). Application Research of Computers(计算机应用研究), 2021, 38(9): 2861.