Laser & Optoelectronics Progress, Volume. 62, Issue 4, 0412005(2025)

Defect Detection Method for Vehicle Weld Porosity Based on Improved YOLOv5

Xiaolong Zhou* and Changjie Liu
Author Affiliations
  • National Key Laboratory of Precision Test Techniques and Instrument, Tianjin University, Tianjin 300072, China
  • show less
    References(16)

    [1] Xu R L, Zhu P C, Yu C Z et al. Present situation and development trends of welding technologies for B.I.W[J]. Electric Welding Machine, 40, 1-18(2010).

    [2] Zhang H, You G Q, Duan P A et al. Research progress of welding porosity detection technology[J]. Hot Working Technology, 46, 19-24(2017).

    [3] Gao H D. EMAT and its application in weld inspection[J]. Nondestructive Testing, 32, 850-853, 856(2010).

    [4] Chi D Z. Research on characterization of weld defect based on ultrasonic TOFD[D](2007).

    [5] Liu H, Guo R Y. Detection and identification of SAWH pipe weld defects based on X-ray image and CNN[J]. Chinese Journal of Scientific Instrument, 39, 247-256(2018).

    [6] Nacereddine N, Zelmat M, Belaïfa S S et al. Weld defect detection in industrial radiography based digital image processing[C], 1-10(2005).

    [7] Zhao S, Liang D Q, Wang X N et al. Weld seam tracking system based on dynamic mask match for spirally tubes[J]. Journal of Dalian Maritime University, 33, 27-29(2007).

    [9] Xiang K, Li S S, Luan M H et al. Aluminum product surface defect detection method based on improved Faster RCNN[J]. Chinese Journal of Scientific Instrument, 42, 191-198(2021).

    Tools

    Get Citation

    Copy Citation Text

    Xiaolong Zhou, Changjie Liu. Defect Detection Method for Vehicle Weld Porosity Based on Improved YOLOv5[J]. Laser & Optoelectronics Progress, 2025, 62(4): 0412005

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Instrumentation, Measurement and Metrology

    Received: Jun. 4, 2024

    Accepted: Jul. 9, 2024

    Published Online: Feb. 10, 2025

    The Author Email:

    DOI:10.3788/LOP241418

    CSTR:32186.14.LOP241418

    Topics