A Dataset of Pulsed Thermography for Automated Defect Depth Estimation
Source abstract
Abstract
Pulsed thermography is an established nondestructive evaluation technology that excels at detecting and characterizing subsurface defects within specimens. A critical challenge in this domain is the accurate estimation of defect depth. In this paper, a new publicly accessible pulsed infrared dataset for PVC specimens is introduced. It was enriched with 3D positional information to advance research in this area. To ensure the labeling quality, a comparative analysis of two distinct data labeling methods was conducted. The first method is based on human domain expertise, while the second method relies on 3D CAD images. The analysis showed that the CAD-based labeling method noticeably enhanced the precision of defect dimension quantification. Additionally, a sophisticated deep learning model was employed on the data, which were preprocessed by different methods to predict both the two-dimensional coordinates and the depth of the identified defects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Thermography and Photoacoustic Techniques · Industrial Vision Systems and Defect Detection · Integrated Circuits and Semiconductor Failure Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Science and Engineering, Department of Electrical and Computer Engineering, University Laval, Quebec City, QC G1V 0A6, Canada
School of Engineering, University of Applied Sciences in Saarbrücken, 66117 Saarbrücken, Germany
Fraunhofer Institute for Nondestructive Testing IZFP, 66123 Saarbrücken, Germany
Chair of Cognitive Sensor Systems, Saarland University, 66123 Saarbrücken, Germany
Funding
European Regional Development Fund · Fraunhofer IZFP institute
References (36)
Show source-provided references
1. Ciampa, F., Mahmoodi, P., Pinto, F., and Meo, M. (2018). Recent advances in active infrared thermography for non-destructive testing of aerospace components. Sensors, 18.10.3390/s18020609 ↗
2. Smith, R.A., Mukhopadhyay, S., Lawrie, A., and Hallett, S.R. (2013, January 13–15). Applications of ultrasonic NDT to aerospace composites. Proceedings of the 5th International Symposium on Aerospace NDT, Singapore.
3. Ley, O., and Godinez-Azcuaga, V. (2013, January 13–15). Line scanning thermography and its application inspecting aerospace composites. Proceedings of the 5th International Symposium on NDT in Aerospace, Singapore.
4. Infrared thermography for civil structural assessment: Demonstrations with laboratory and field studies10.1007/s13349-016-0180-9 ↗
5. Semantic segmentation of defects in infrared thermographic images of highly damaged concrete structures10.1061/(ASCE)CF.1943-5509.0001541 ↗
6. Blitz, J., and Simpson, G. (1995). Ultrasonic Methods of Non-Destructive Testing, Springer Science & Business Media.
7. Reliability considerations of NDT by probability of detection (POD) determination using ultrasound phased array10.1016/j.engfailanal.2013.06.008 ↗
8. Non-destructive techniques based on eddy current testing10.3390/s110302525 ↗
9. Heuer, H., Schulze, M., and Meyendorf, N. (2013). Non-Destructive Evaluation (NDE) of Polymer Matrix Composites, Elsevier.10.1533/9780857093554.1.33 ↗
10. Guided wave testing of rail
11. Ibarra-Castanedo, C., Genest, M., Piau, J.M., Guibert, S., Bendada, A., and Maldague, X.P. (2007). Ultrasonic and Advanced Methods for Nondestructive Testing and Material Characterization, World Scientific.
12. Characterisation of small embedded two-dimensional defects using multi-view Total Focusing Method imaging algorithm10.1016/j.ndteint.2021.102413 ↗
13. Fradkin, L., Uskuplu Altinbasak, S., and Darmon, M. (2021). Towards explainable augmented intelligence (AI) for crack characterization. Appl. Sci., 11.10.3390/app112210867 ↗
14. Automated defect detection in digital radiography of aerospace welds using deep learning10.1007/s40194-022-01257-w ↗
15. Fuchs, P., and Gondrom-Linke, S. (2022, January 24–27). Information Extraction from Industrial CT Scans Using 3D Deep Learning. Proceedings of the International Conference on NDE 4.0, Berlin, Germany.
16. Generative principal component thermography for enhanced defect detection and analysis
17. Wei, Z., Fernandes, H., Tarpani, J.R., Osman, A., and Maldague, X. (2021, January 21–23). Stacked denoising autoencoder for infrared thermography image enhancement. Proceedings of the 2021 IEEE 19th International Conference on Industrial Informatics (INDIN), Palma de Mallorca, Spain.10.1109/INDIN45523.2021.9557407 ↗
18. Wei, Z., Osman, A., Valeske, B., and Maldague, X. (2023). Pulsed Thermography Dataset for Training Deep Learning Models. Appl. Sci., 13.10.20944/preprints202301.0483.v1 ↗
19. Principal component thermography for flaw contrast enhancement and flaw depth characterisation in composite structures10.1016/S0263-8223(02)00161-7 ↗
20. Pulse phase infrared thermography10.1063/1.362662 ↗
21. Shepard, S.M. (2003). Temporal Noise Reduction, Compression and Analysis of Thermographic Image Data Sequences. (6,516,084), U.S. Patent.
22. Specified value based defect depth prediction using pulsed thermography10.1063/1.4737784 ↗
23. Determination of defect depth and size using virtual heat sources in pulsed infrared thermography10.1007/s11340-012-9670-9 ↗
24. Defect depth determination in laser infrared thermography based on LSTM-RNN10.1109/ACCESS.2020.3018116 ↗
25. Fang, Q., and Maldague, X. (2020). A method of defect depth estimation for simulated infrared thermography data with deep learning. Appl. Sci., 10.10.20944/preprints202008.0565.v1 ↗
26. Experimentally validated defect depth estimation using artificial neural network in pulsed thermography10.1016/j.infrared.2019.03.014 ↗
27. Jocher, G. (2023, November 21). YOLOv5 by Ultralytics. Available online: https://doi.org/10.5281/zenodo.3908559.
28. Real-time detection of particleboard surface defects based on improved YOLOV5 target detection10.1038/s41598-021-01084-x ↗
29. A domain adaptation YOLOv5 model for industrial defect inspection10.1016/j.measurement.2023.112725 ↗
30. An improved YOLOv5 crack detection method combined with transformer10.1109/JSEN.2022.3181003 ↗
31. Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H. (2020, January 14–19). CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
32. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–23). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
33. Xu, B., Wang, N., Chen, T., and Li, M. (2015). Empirical evaluation of rectified activations in convolutional network. arXiv.
34. Xu, R., Lin, H., Lu, K., Cao, L., and Liu, Y. (2021). A forest fire detection system based on ensemble learning. Forests, 12.10.3390/f12020217 ↗
35. Imagenet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
36. Davis, J., and Goadrich, M. (2006, January 25–29). The relationship between Precision-Recall and ROC curves. Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, USA.10.1145/1143844.1143874 ↗