An Accurate Detection and Location of Weld Surface Defect Based on Laser Vision

Abstract:

In order to effectively improve the efficiency of automatic detection and subsequent processing of welding defects in the construction field, this paper proposes a method for detecting and locating weld surface defects based on machine vision and laser vision. YOLOv5 is used for the initial detection and identification of weld hole defects to obtain the approximate location of the defect. Subsequently, the detailed features of the defect sites are extracted by scanning the approximate range of defect locations with a line laser 3D sensor based on the identification of weld defect holes. Finally, the defect location and depth are accurately located based on the extracted features. Experimental results show that the proposed method is capable of identifying weld surface hole defects with an accuracy rate of over 94%. Furthermore, the combination of the system with the line laser 3D sensor detection can significantly improve the accuracy compared to pure 2D visual inspection, while the manual measurement is neither convenient nor accurate. This indicates that the proposed system can be used for rapid and accurate feature information extraction of weld hole defects, making subsequent remedial welding in actual engineering more automatic and efficient.

• Periodical: Key Engineering Materials (Volume 963)
• Pages: 197-207
• DOI: https://doi.org/10.4028/p-vaqQo3
• Online since: October 2023
• Authors: Chao Chen, Shuai Li*, Y. Frank Chen
• Keywords: Automatic Detection, Laser Vision, Weld Surface Defect, YOLOv5

References

[1] J. Stavridis, A. Papacharalampopoulos, & P. Stavropoulos. (2018). Quality assessment in laser welding: a critical review. The International Journal of Advanced Manufacturing Technology, 94, 1825-1847.

DOI: 10.1007/s00170-017-0461-4

[2] T. W. Liao. (2009). Improving the accuracy of computer-aided radiographic weld inspection by feature selection. Ndt & E International, 42(4), 229-239.

DOI: 10.1016/j.ndteint.2008.11.002

[3] N. Nacereddine, A. B. Goumeidane & D. Ziou. (2019). Unsupervised weld defect classification in radiographic images using multivariate generalized Gaussian mixture model with exact computation of mean and shape parameters. Computers in Industry, 108, 132-149.

DOI: 10.1016/j.compind.2019.02.010

[4] X. Gao, N. Ma., & L. Du. (2018). Magneto-optical imaging characteristics of weld defects under alternating magnetic field excitation. Optics express, 26(8), 9972-9983.

DOI: 10.1364/oe.26.009972

[5] Z. Zhang, G. Wen., & S. Chen. (2017). Audible sound-based intelligent evaluation for aluminum alloy in robotic pulsed GTAW: mechanism, feature selection, and defect detection. IEEE Transactions on Industrial Informatics, 14(7), 2973-2983.

DOI: 10.1109/tii.2017.2775218

[6] Yusof. Kamaruzaman. M.F. M, M. A., M. Zubair, & M. Ishak. (2016). Detection of defects on weld bead through the wavelet analysis of the acquired arc sound signal. Journal of Mechanical Engineering and Sciences, 10(2), 2031-2042.

[7] N. Lv., Y. Xu., S. Li, X. Yu, & S. Chen. (2017). Automated control of welding penetration based on audio sensing technology. Journal of Materials Processing Technology, 250, 81-98.

DOI: 10.1016/j.jmatprotec.2017.07.005

[8] D. Naso, B. Turchiano, & P. Pantaleo. (2005). A fuzzy-logic based optical sensor for online weld defect-detection. IEEE transactions on Industrial Informatics, 1(4), 259-273.

DOI: 10.1109/tii.2005.857617

[9] J. Lin, N. Ma, Y. Lei, & H. Murakawa. (2017). Measurement of residual stress in arc welded lap joints by cosα X-ray diffraction method. Journal of Materials Processing Technology, 243, 387-394.

DOI: 10.1016/j.jmatprotec.2016.12.021

[10] R. B. Roy, A. Ghosh, S. Bhattacharyya, R. P. Mahto, K. Kumari, S. K. Pal, & S. Pal. (2018). Weld defect identification in friction stir welding through optimized wavelet transformation of signals and validation through X-ray micro-CT scan. International Journal of Advanced Manufacturing Technology, 99.

DOI: 10.1007/s00170-018-2519-3

[11] M. Malarvel, G. Sethumadhavan, P. C. R. Bhagi, S. Kar, T. Saravanan, & A. Krishnan. (2017). Anisotropic diffusion based denoising on X-radiography images to detect weld defects. Digital Signal Processing, 68, 112-126.

DOI: 10.1016/j.dsp.2017.05.014

[12] I. Valavanis, & D. Kosmopoulos. (2010). Multiclass defect detection and classification in weld radiographic images using geometric and texture features. Expert Systems with Applications, 37(12), 7606-7614.

DOI: 10.1016/j.eswa.2010.04.082

[13] N. Nacereddine, M. Zelmat, S. S. Belaifa, & M. Tridi. (2005). Weld defect detection in industrial radiography based digital image processing. Transactions on Engineering Computing and Technology, 2, 145-148.

[14] N. Boaretto, & T. M. Centeno. (2017). Automated detection of welding defects in pipelines from radiographic images DWDI. Ndt & E International, 86, 7-13.

DOI: 10.1016/j.ndteint.2016.11.003

[15] B. Chen, Z. Fang, Y. Xia, L. Zhang, Y. Huang, & L. Wang. (2018). Accurate defect detection via sparsity reconstruction for weld radiographs. NDT & E International, 94, 62-69.

DOI: 10.1016/j.ndteint.2017.11.006

[16] W. Hou, Y. Wei, Y. Jin, & C. Zhu. (2019). Deep features based on a DCNN model for classifying imbalanced weld flaw types. Measurement, 131, 482-489.

DOI: 10.1016/j.measurement.2018.09.011

[17] J. Sun, C. Li, X.J. Wu, V. Palade, & W. Fang. (2019). An effective method of weld defect detection and classification based on machine vision. IEEE Transactions on Industrial Informatics, 15(12), 6322-6333.

DOI: 10.1109/tii.2019.2896357

[18] C. Mera, M. Orozco-Alzate, J. Branch, & D. Mery. (2016). Automatic visual inspection: An approach with multi-instance learning. Computers in Industry, 83, 46-54.

DOI: 10.1016/j.compind.2016.09.002

[19] J. Muhammad, H. Altun, & E. Abo-Serie. (2017). Welding seam profiling techniques based on active vision sensing for intelligent robotic welding. The International Journal of Advanced Manufacturing Technology, 88, 127-145.

DOI: 10.1007/s00170-016-8707-0

[20] A. Vetrivel, M. Gerke, N. Kerle, F. Nex, & G. Vosselman. (2018). Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learning. ISPRS journal of photogrammetry and remote sensing, 140, 45-59.

DOI: 10.1016/j.isprsjprs.2017.03.001

[21] Y. Cheng, D. HongGui, & F. YuXin. (2020, June). Effects of faster region-based convolutional neural network on the detection efficiency of rail defects under machine vision. In 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC) (pp.1377-1380). IEEE.

DOI: 10.1109/itoec49072.2020.9141787

[22] L.H. Yin, S.B. Sun, X.U. Ye, & C. Zhang. (2019). Defect recognition of weld image based on improved multiscale sampling algorithm. Computer Engineering and Design.

[23] Z. Zhang, G. Wen, & S. Chen. (2019). Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding. Journal of Manufacturing Processes, 45, 208-216.

DOI: 10.1016/j.jmapro.2019.06.023

[24] Z. Zhang, G. Wen, & S. Chen. (2019). Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding. Journal of Manufacturing Processes, 45, 208-216.

DOI: 10.1016/j.jmapro.2019.06.023

[25] G. Ma, L. Yu, H. Yuan, W. Xiao, & Y. He. (2021). A vision-based method for lap weld defects monitoring of galvanized steel sheets using convolutional neural network. Journal of Manufacturing Processes, 64, 130-139.

DOI: 10.1016/j.jmapro.2020.12.067

[26] L. Yang, H. Wang, B. Huo, F. Li, & Y. Liu. (2021). An automatic welding defect location algorithm based on deep learning. Ndt & E International, 120, 102435.

DOI: 10.1016/j.ndteint.2021.102435

[27] C. Li, C. Guo, W. Ren, R. Cong, J. Hou, S. Kwong, & D. Tao. (2019). An underwater image enhancement benchmark dataset and beyond. IEEE Transactions on Image Processing, 29, 4376-4389.

DOI: 10.1109/tip.2019.2955241