Advanced Search
DENG Zhichao, YAN Runming, YANG Huitong, CHEN Haolin, LAI Jinxiang, LEI Liang. Multiview solder joint defect detection based on improved ResNet[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2022, 43(3): 56-62. DOI: 10.12073/j.hjxb.20210928004
Citation: DENG Zhichao, YAN Runming, YANG Huitong, CHEN Haolin, LAI Jinxiang, LEI Liang. Multiview solder joint defect detection based on improved ResNet[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2022, 43(3): 56-62. DOI: 10.12073/j.hjxb.20210928004

Multiview solder joint defect detection based on improved ResNet

More Information
  • Received Date: September 27, 2021
  • Available Online: April 15, 2022
  • The single view detection based on convolutional neural network cannot effectively identify 3D shape defect targets. As a result, in practical applications, the low-precision detection requirements are often achieved by detecting only one of the most representative views or detecting each face in turn, which brings large time cost and use restrictions. To solve this problem, this paper proposes an improved residual network and applies it to 3D shape solder joint defect detection. The model can firstly obtain all view images of solder joints at one time, and then get detection results through feature aggregation and adaptive learning module. The multi-view solder joint data set was obtained from high frequency inductor element, and the identification accuracy of the proposed method reached 99.48%. The results show that the improved residual network can effectively improve the image identification accuracy under the same number of network layers. Compared with the single view detection, the multi-view detection structure can achieve greater accuracy with less time cost, and can effectively complete the detection task of 3D shape defect targets in actual industrial production.
  • Su S, Akkara F J, Thaper R, et al. A state-of-the-art review of fatigue life prediction models for solder joint[J]. Journal of Electronic Packaging, 2019, 141(4): 040802. doi: 10.1115/1.4043405
    Wang Q, Liu X, Liu W, et al. MetaSearch: incremental product search via deep meta-learning[J]. IEEE Transactions on Image Processing, 2020, 29: 7549-7564.
    He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, America, 2016: 770-778.
    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]. Journal of Manufacturing Processes, 2019, 45: 208 − 216.
    王中任, 王小刚, 刘德政, 等. 基于焊枪轮廓特征提取的焊接偏差测定方法[J]. 焊接学报, 2020, 41(7): 59 − 64. doi: 10.12073/j.hjxb.20191026002

    Wang Zhongren, Wang Xiaogang, Liu Dezheng, et al. Welding eviation measurement method based on welding torch contour feature extraction[J]. Transactions of the China Welding Institution, 2020, 41(7): 59 − 64. doi: 10.12073/j.hjxb.20191026002
    肖文波, 何银水, 袁海涛, 等. 镀锌钢GMAW焊缝成形特征与焊枪方向同步实时检测[J]. 焊接学报, 2021, 42(12): 78 − 82. doi: 10.12073/j.hjxb.20201021001

    Xiao Wenbo, He Yinshui, Yuan Haitao, et al. Synchronous real-time detection of weld bead geometry and the welding torch in galvanized steel GAMW[J]. Transactions of the China Welding Institution, 2021, 42(12): 78 − 82. doi: 10.12073/j.hjxb.20201021001
    Ding R, Dai L, Li G, et al. TDD-net: a tiny defect detection network for printed circuit boards[J]. CAAI Transactions on Intelligence Technology, 2019, 4(2): 110 − 116. doi: 10.1049/trit.2019.0019
    Chi Dazhao, Gang Tie. Defect detection method based on 2D entropy image segmentation[J]. China Welding, 2020, 29(1): 45 − 49.
    王睿, 胡云雷, 刘卫朋, 等. 基于边缘AI的焊缝X射线图像缺陷检测[J]. 焊接学报, 2022, 43(1): 79 − 84.

    Wang Rui, Hu Yunlei, Liu Weipeng, et al. Defect detection of weld X-ray image based on edge AI[J]. Transactions of the China Welding Institution, 2022, 43(1): 79 − 84.
    Veit A, Wilber M J, Belongie S. Residual networks behave like ensembles of relatively shallow networks[J]. Advances in Neural Information Processing Systems, 2016, 29: 550 − 558.
    Ma C, Guo Y, Yang J, et al. Learning multi-view representation with LSTM for 3D shape recognition and retrieval[J]. IEEE Transactions on Multimedia, 2018, 21(5): 1169 − 1182.
    迟大钊, 李孙珏, 孙昌立, 等. 基于双目视觉的缺陷深度测量方法[J]. 焊接学报, 2016, 37(11): 7 − 10.

    Chi Dazhao, Li Sunjue, Sun Changli, et al. Binocular visual based defect buried depth testing method[J]. Transactions of the China Welding Institution, 2016, 37(11): 7 − 10.
    Jiao Y, Jermsittiparsert K, Krasnopevtsev A Y, et al. Interaction of thermal cycling and electric current on reliability of solder joints in different solder balls[J]. Materials Research Express, 2019, 6(10): 106302. doi: 10.1088/2053-1591/ab366d
    Dai W, Mujeeb A, Erdt M, et al. Soldering defect detection in automatic optical inspection[J]. Advanced Engineering Informatics, 2020, 43: 101004. doi: 10.1016/j.aei.2019.101004
    Liu Z, Cao Y, Li Y, et al. Automatic diagnosis of fungal keratitis using data augmentation and image fusion with deep convolutional neural network[J]. Computer Methods and Programs in Biomedicine, 2020, 187: 105019. doi: 10.3390/info11020125
    He K, Fan H, Wu Y, et al. Momentum contrast for unsupervised visual representation learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Anchorage, Alaska, USA, 2020: 9729 − 9738.
    Yu F, Wang D, Shelhamer E, et al. Deep layer aggregation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, USA, 2018: 2403 − 2412.
    Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, USA, 2018: 7132 − 7141.
  • Related Articles

    [1]2022-7 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2022, 43(7): 1-8.
    [2]2021-11 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2021, 42(11): 1-6.
    [3]2020-12 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(12): 98-103.
    [4]2020-8 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(8): 97-102.
    [5]2020-5 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(5): 97-102.
    [6]2020-4 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(4): 97-102.
    [7]2020-3 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(3): 97-102.
    [8]2020-2 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(2): 97-102.
    [9]2020-1 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(1): 97-102.
    [10]2019-3 Abstract[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2019, 40(3): 161-168.
  • Cited by

    Periodical cited type(3)

    1. 陈文仕,何日恒,金礼,姚屏. 电流波形对2209双相不锈钢双丝增材制造的影响. 机电工程技术. 2025(04): 46-49+111 .
    2. 康国坡,朱强,黄建民,周铭伟,李中焕,王梓翰. 电弧增材制造技术与应用分析. 中国设备工程. 2024(18): 231-233 .
    3. 郭阳阳,李嘉诚,任凌宝,羿昌波,练政希,李进,刘章,郭居魁. 镁合金电弧增材制造研究进展及展望. 热加工工艺. 2024(20): 9-17 .

    Other cited types(0)

Catalog

    Article views (397) PDF downloads (64) Cited by(3)

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return