Li Lin, Xin Liu, Junzhen Zhu, Fuzhou Feng. Research on vibrothermography detection and recognition method of metal fatigue cracks based on CNN[J]. Infrared and Laser Engineering, 2022, 51(3): 20210227
- Infrared and Laser Engineering
- Vol. 51, Issue 3, 20210227 (2022)
Fig. 1. Schematic diagram of ultrasonic infrared thermal imaging detection system
Fig. 2. Schematic diagram of test plate
Fig. 3. Data amplification
Fig. 4. Crack-free infrared thermal images
Fig. 5. Infrared thermal image with cracks
Fig. 6. Structure diagram of convolutional neural network designed in this article
Fig. 7. Curves of training results
Fig. 8. Classification results of testing samples
Fig. 9. t-SNE visualization of test set based on network model
Fig. 10. Prediction results of a crack
|
Table 1. Crack and optical measurement length of 15 kinds of metal specimens
|
Table 2. Description of network model parameters designed in this article
|
Table 3. Results of different batch size recognition rate
|
Table 4. Metal plate specimen and optical measurement of crack size
|
Table 5. Crack recognition and classification by different algorithms
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20