Abstract
This study is aimed to analyze the characteristics of different kinds of time-of-flight diffraction (TOFD) images for welding seam defects. Combined with the image recognition technology of artificial intelligence, a deep learning neural network program based on TensorFlow was developed and applied to the training and recognition of welding seam defects in ultrasonic TOFD images. The results showed that, after training, the program could identify typical welding seam defects such as stoma, crackle, slag inclusion, lack of fusion, and incomplete penetration in TOFD images of the welding seam, and the recognition confidence was more than 0.8. This proved that the program developed in this study provided an effective reference for determining typical welding seam defects in TOFD images of the welding seam.
Similar content being viewed by others
REFERENCES
Zhen, N., Influence of weld defect on construction quality of steel structure, Steel Struct., 2013, vol. 28, no. 3, pp. 66–71.
Vilar, R., Zapata, J., and Ruiz, R., An automatic system of classification of weld defects in radiographic images, NDT E Int., 2009, vol. 42, no. 5, pp. 467–476. https://doi.org/10.1016/j.ndteint.2009.02.004
Schmidhuber, J., Deep learning in neural networks: An overview, Neural Networks, 2015, vol. 61, pp. 85–117. https://doi.org/10.1016/j.neunet.2014.09.003
Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., and Lew, M.S., Deep learning for visual understanding: A review, Neurocomputing, 2016, vol. 187, pp. 27–48. https://doi.org/10.1016/j.neucom.2015.09.116
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D.G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., and Zheng, X., TensorFlow: A system for large-scale machine learning, Proc. 12th USENIX Conf. on Operating Systems Design and Implementation, Savannah, Ga., 2016, Berkely, Calif.: USENIX Association, 2016, pp. 265–283.
Chen, Y., Wang, H., and Han, Z., Design and implementation of a multi-scale object detection algorithm on TensorFlow, J. Phys.: Conf. Ser., 2020, vol. 1576, p. 012031. https://doi.org/10.1088/1742-6596/1576/1/012031
Sudharshan, D.P. and Raj, S., Object recognition in images using convolutional neural network, 2nd Int. Conf. on Inventive Systems and Control (ICISC), Coimbatore, India, 2018, IEEE, 2018, pp. 718–722. https://doi.org/10.1109/ICISC.2018.8398893
Hayat, S., Kun, S., Tengtao, Z., Yu, Y., Tu, T., and Du, Y., A deep learning framework using convolutional neural network for multi-class object recognition, IEEE 3rd Int. Conf. on Image, Vision and Computing (ICIVC), Chongqung, China, 2018, IEEE, 2018, pp. 194–198. https://doi.org/10.1109/ICIVC.2018.8492777
Al-Ataby, A., Al-Nuaimy, W., Brett, C.R., and Zahran, O., Automatic detection and classification of weld flaws in TOFD data using wavelet transform and support vector machines, Insight Non-Destruct. Test. Cond. Monit., 2010, vol. 52, no. 11, pp. 597–602. https://doi.org/10.1784/insi.2010.52.11.597
Barceló, F.R., del Hierro, P.J., Llario, F.R., and Herráiz, J.R., Development of an ultrasonic weld inspection system based on image processing and neural networks, Nondestruct. Test. Eval., 2018, vol. 33, no. 2, pp. 229–236. https://doi.org/10.1080/10589759.2017.1376056
Lin, N., Yang, X., Tang, X., and Zhu, Z., Defect recognition of TOFD image based on Gabor wavelet, J. Mech. Electr. Eng., 2013, vol. 30, no. 12, pp. 1450–1454.
Liu, J., Xu, G.C., Ren, L., Qian, Z., and Ren, L., Defect intelligent recognition in resistance spot welding ultrasonic detection based on wavelet packet and neural network, Int. J. Adv. Manuf. Technol., 2017, vol. 90, pp. 2581–2588. https://doi.org/10.1007/s00170-016-9588-y
Yi, X., Discussion on the basic principle and application of TOFD detection technology, Petrochem. Appl., 2008, no. 3, pp. 29–31.
Zhu, S., Lu, D., Hu, L., Wu, C., and Shao, J., Application of time-of-flight diffraction technique on the site welding pressure vessels, Petrochem. Equipment, 2012, vol. 41, no. 6, pp. 74–78.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
About this article
Cite this article
Shuohui Chen, Teng, X., Sang, X. et al. Automatic Recognition of Welding Seam Defects in TOFD Images Based on TensorFlow. Aut. Control Comp. Sci. 56, 58–66 (2022). https://doi.org/10.3103/S0146411622010035
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411622010035