Abstract
The human visual inspection to find defects from welding joints is very tough. The examiners have to inspect many bend test fragments carefully. The present study aims to build an automatic detection system capable of finding cracks from bend test fragments. This paper describes the automatic detection method employing Faster R-CNN to detect crack regions. First, we introduce our achievement and explain the focused issue. Second, the structure of the proposed Faster R-CNN is explained, and then the present paper shows the experiment of automatic detection using web-camera working in real-time. Finally, conclusions and future works are discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asai, S., Ogawa, T., Takebayashi, H.: Visualization and digitation of welder skill for education and training. Weld. World 56, 26–34 (2012)
Byrd, A.P., Stone, R.T., Anderson, R.G., Woltjer, K.: The use of virtual welding simulators to evaluate experimental welders. Weld. J. 94(12), 389–395 (2015)
Hino, T., et al.: Visualization of gas tungsten arc welding skill using brightness map of backside weld pool. Trans. Mat. Res. Soc. Jpn. 44(5), 181–186 (2019)
Niles, R.W., Jackson, C.E.: Weld thermal efficiency of the GTAW process. Weld. J. 54, 25–32 (1975)
Kato, S., Hino, T., Yoshikawa, N.: Fundamental study on evaluation system of beginner’s welding using CNN. In: Barolli, L., Hellinckx, P., Natwichai, J. (eds.) 3PGCIC 2019. LNNS, vol. 96, pp. 821–827. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-33509-0_77
Kato, S., Hino, T., Kumeno, H., Kagawa, T., Nobuhara, H.: Automatic detection of beginner’s welding joint. In: Proceedings of 2020 Joint 11th International Conference on Soft Computing and Intelligent Systems and 21st International Symposium on Advanced Intelligent Systems, pp. 465–467 (2020)
Kato, S., et al.: Evaluation for angular distortion of welding plate. In: Arai, K. (eds.) IntelliSys 2021. LNNS, vol. 294, pp. 344–354. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-82193-7_23
The Japanese Welding Engineering Society. http://www.jwes.or.jp/en/qualification.html. Accessed 3 Sept 2021
Wan, Y., Jiang, W., Li, H.: Cold bending effect on residual stress, microstructure and mechanical properties of Type 316L stainless steel welded joint. Eng. Fail. Anal. 117, 104825 (2020)
Kato, S., Hino, T., Kume, S., Nobuhara, H.: Crack detection from weld bend test images using R-CNN. In: Barolli, L., (eds.) 3PGCIC 2021. LNNS, vol. 343, pp. 289–298. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-89899-1_31
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR 2014 Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)
Park, J.-K., , An, W.-H., Kang, D.-J.: Convolutional neural network based surface inspection system for non-patterned welding defects. Int. J. Precis. Eng. Manuf. 20(3), 363–374 (2019)
Dung, C.V., Sekiya, H., Hirano, S., Okatani, T., Miki, C.: A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks. Autom. Constr. 102, 217–229 (2019)
Zhang, Z., Wen, G., Chen, S.: Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding. J. Manuf. Process. 45, 208–216 (2019)
Dai, W., et al.: Deep learning assisted vision inspection of resistance spot welds. J. Manuf. Process. 62, 262–274 (2021)
Abdelkader, R., Ramou, N., Khorchef, M., Chetih, N., Boutiche, Y.: Segmentation of x-ray image for welding defects detection using an improved Chan-Vese model. Mater. Today Proc. 42, Part 5, 2963–2967 (2021)
Zhu, H., Ge, W., Liu, Z.: Deep learning-based classification of weld surface defects. Appl. Sci. 9(16), 3312 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
MathWorks: https://jp.mathworks.com/help/deeplearning/ug/investigate-network-predictions-using-class-activation-mapping.html?lang=en. Accessed 8 Sept 2021
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: IEEE International Conference on Computer Vision (ICCV), pp. 618–626 (2017)
Acknowledgments
The authors would like to thank Crimson Interactive Pvt. Ltd. (Ulatus) - www.ulatus.jp for their assistance in manuscript translation and editing, and Ueno in MathWorks for technical advice. This work was supported by a Grant-in-Aid from JWES (The Japan Welding Engineering Society).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kato, S., Hino, T., Kumeno, H., Kume, S., Kagawa, T., Nobuhara, H. (2022). Fault Detection from Bend Test Images of Welding Using Faster R-CNN. In: Barolli, L., Kulla, E., Ikeda, M. (eds) Advances in Internet, Data & Web Technologies. EIDWT 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 118. Springer, Cham. https://doi.org/10.1007/978-3-030-95903-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-95903-6_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95902-9
Online ISBN: 978-3-030-95903-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)