Deep learning-based defect detection in pulsed thermography
DOI:
https://doi.org/10.58368/MTT.23.9-10.2024.1-9Keywords:
Pulse Thermography, Pulse Phase Thermography, Artificial Intelligence, Deep Learning, YOLOv8, Object Detection, Semantic SegmentationAbstract
The current era emphasizes system productivity to meet global demand. The productivity index is closely tied to the reliability of the manufacturing process. To keep up with today’s manufacturing demands, inspection systems on the production line must prioritize both speed and quality. However, a key challenge in automated inspection is achieving a balance between high defect detection accuracy and minimizing false positives and false negatives. To address this, this study investigates the effectiveness of deep learning-based models for defect detection in Pulsed Thermography (PT) using a publicly available dataset of PVC specimens. Pulsed Phase Thermography (PPT) was applied to the raw thermograms to generate phase images and evaluate the performance of conventional methods. Two models were trained and evaluated for defect detection: a pre-trained YOLOv8 object detection model and a semantic segmentation model from Halcon. The YOLOv8 model demonstrated a high precision of 97.1%, but with a recall of 82%, indicating that it accurately detected defects but missed some. In contrast, the Halcon model achieved perfect recall (100%) but lower precision (78.2%), suggesting that it detected all defects but also introduced a significant number of false positives. The results highlight the trade-offs between precision and recall in these models, with YOLOv8 focusing on accuracy and Halcon on comprehensive defect detection. This study demonstrates the potential of deep learning techniques in enhancing defect detection performance in Pulsed Thermography applications.
Metrics
References
Almond, D. P. & Lau, S. K. (1994). Defect sizing by transient thermography. I. An analytical treatment. Journal of Physics D: Applied Physics, 27(5). http://iopscience.iop.org/0022- 3727/27/5/027
Ciampa, F., Mahmoodi, P., Pinto, F., & Meo, M. (2018). Recent advances in active infrared thermography for non-destructive testing of aerospace components. Sensors, 18(2), 609. MDPI AG. https://doi.org/10.3390/s18020609
Follmann, P., Böttger, T., Härtinger, P., König, R., & Ulrich, M. (2018). MVTec D2S: Densely segmented supermarket dataset. Proceedings of the European Conference on Computer Vision (ECCV), (pp. 569-585)
Gao, C., Zhang, Q., Tan, Z., Zhao, G., Gao, S., Kim, E., & Shen, T. (2024). Applying optimized YOLOv8 for heritage conservation: enhanced object detection in Jiangnan traditional private gardens. Heritage Science, 12(1). https://doi. org/10.1186/s40494-024-01144-1
Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems (2nd ed.). O’Reilly Media.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna Z., Song Y., Guadarrama S., Murphy K. (2017). Speed/ accuracy trade-offs for modern convolutional object detectors. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3296-3297. https://doi. org/10.1109/CVPR.2017.351
Liu, Y., Wu, J. Y., Liu, K., Wen, H. L., Yao, Y., Sfarra, S., & Zhao, C. (2019). Independent component thermography for non-destructive testing of defects in polymer composites. Measurement Science and Technology, 30(4). https://doi. org/10.1088/1361-6501/ab02db
Maldague, X., & Marinetti, S. (1996). Pulse phase infrared thermography. Journal of Applied Physics, 79(5), 2694–2698. https://doi. org/10.1063/1.362662
Rajic, N. (2002). Principal component thermo-graphy for flaw contrast enhancement and flaw depth characterisation in composite structures. www.elsevier.com/locate/compstruct
Redmon, J., & Farhadi, A. (n.d.). YOLO9000: Better, Faster, Stronger. http://pjreddie.com/yolo9000/
Shelhamer, E., Long, J., & Darrell, T. (2017). Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 640-651.
Skalski, P. (2019). Make sense. GitHub. https:// github.com/SkalskiP/make-sense/
Ultralytics. (2023). YOLOv8. GitHub. https://github. com/ultralytics/yolov8
Vavilov, V. P., & Burleigh, D. D. (2015). Review of pulsed thermal NDT: Physical principles, theory and data processing. NDT and E International, 73, 28-52. https://doi.org/10.1016/j.ndteint. 2015.03.003
Wei, Z., Osman, A., Valeske, B., & Maldague, X. (2023). A dataset of pulsed thermography for automated defect depth estimation. Applied Sciences (Switzerland), 13(24). https://doi. org/10.3390/app132413093
Wu, J. Y., Sfarra, S., & Yao, Y. (2018). Sparse Principal component thermography for structural health monitoring of composite structures. IFAC-PapersOnLine, 51(24), 855-860. https://doi. org/10.1016/j.ifacol.2018.09.675
Downloads
Published
How to Cite
Issue
Section
License
All the articles published in Manufacturing Technology Today (MTT) Journal are held by the Publisher. Central Manufacturing Technology Institute (CMTI) as a publisher requires its authors to transfer the copyright prior to publication. This will permit CMTI to reproduce, publish, distribute, and archive the article in print and electronic form and also to defend against any improper use of the article.
