Infrared and Laser Engineering, Volume. 53, Issue 3, 20230631(2024)
Infrared thermal imaging detection and defect classification of honeycomb sandwich structure defects
Figures & Tables(14)
Fig. 1. Pulsed infrared thermal wave nondestructive testing principle
Fig. 2. The process of heat transfer at different types of defects. (a) Specimen without defects; (b) Specimen containing thermal insulation defects; (c) Specimens containing thermal conductivity defects
Fig. 3. The schematic diagram of surface temperature change curve corresponding to different types of defects
Fig. 9. Transfer learning model training process. (a) Training set Accuracy; (b) Training set Loss; (c) Validation set Accuracy; (d) Validation set Loss
Table 1. Defects type of specimen
View tableView in ArticleTable 1. Defects type of specimen
Column test specimen The first column The second column The third column The fourth column #A1 Water accumulation defects Plugging glue defects Plugging glue defects Plugging glue defects #A2 Water accumulation defects Plugging glue defects Bonding defects 1 - #A3 Water accumulation defects Bonding defects 2 Bonding defects 1 -
Table 2. The number of samples of different types of defects in the infrared image data set
View tableView in ArticleTable 2. The number of samples of different types of defects in the infrared image data set
Types of defects Plugging glue defects Water accumulation defects Bonding defects 1 Bonding defects 2 Health Sample size 2457 2079 1512 756 1260 Proportion 30.5% 25.8% 18.8% 9.4% 15.6%
Table 3. Performance comparison of different classification models of transfer learning
View tableView in ArticleTable 3. Performance comparison of different classification models of transfer learning
Deep learning model Learning rate Iteration cycle Training time/s VGG-16-1 0.00005 50 12500 VGG-16-2 0.00005 50 12515 ResNet50 0.00005 50 4160 Densenet201 0.00005 50 15437 MobileNetV2 0.00005 50 3765 InceptionV3 0.00005 50 6689
Table 4. The
\begin{document}$ \varphi $\end{document} accuracy of each transfer learning model for each defectView tableView in ArticleTable 4. The
\begin{document}$ \varphi $\end{document} accuracy of each transfer learning model for each defectTransfer learning model $ \varphi $ Predictive Accuracy Plugging glue defects Water accumulation defects Bonding defects 1 Bonding defects 2 Health VGG-16-1 99.80% 99.90% 100% 100% 100% 99.94% VGG-16-2 100% 99.79% 99.88% 97.72% 95.53% 99.10% ResNet50 99.20% 99.29% 99.40% 98.51% 96.99% 98.95% DenseNet201 98.61% 99.39% 99.52% 96.88% 93.96% 98.33% MobileNetV2 97.64% 98.48% 98.30% 97.83% 95.45% 98.01% InceptionV3 94.32% 96.58% 98.18% 93.29% 83.09% 94.85%
Tools
Get Citation
Copy Citation Text
Qingju Tang, Zhuoyan Gu, Hongru Bu, Guipeng Xu. Infrared thermal imaging detection and defect classification of honeycomb sandwich structure defects[J]. Infrared and Laser Engineering, 2024, 53(3): 20230631
Paper Information
Category:
Received: Nov. 13, 2023
Accepted: --
Published Online: Jun. 21, 2024
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20