Utilizing improved YOLOv8 based on SPD-BRSA-AFPN for ultrasonic phased array non-destructive testing

被引:3
作者
Chen, Hongyu [1 ]
Tao, Jianfeng [1 ]
机构
[1] Shanghai Jiao Tong Univ, State Key Lab Mech Syst & Vibrat, Shanghai, Peoples R China
关键词
Phased array ultrasound; Non-destructive testing; Convolutional neural networks; Defect detection; YOLOv8;
D O I
10.1016/j.ultras.2024.107382
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Non-destructive testing (NDT) is a technique for inspecting materials and their defects without causing damage to the tested components. Phased array ultrasonic testing (PAUT) has emerged as a hot topic in industrial NDT applications. Currently, the collection of ultrasound data is mostly automated, while the analysis of the data is still predominantly carried out manually. Manual analysis of scan image defects is inefficient and prone to instability, prompting the need for computer-based solutions. Deep learning-based object detection methods have shown promise in addressing such challenges recently. This approach typically demands a substantial amount of high-resolution, well-annotated training data, which is challenging to obtain in NDT. Consequently, it becomes difficult to detect low-resolution images and defects with varying positional sizes. This work proposes improvements based on the state-of-the-art YOLOv8 algorithm to enhance the accuracy and efficiency of defect detection in phased-array ultrasonic testing. The space-to-depth convolution (SPD-Conv) is imported to replace strided convolution, mitigating information loss during convolution operations and improving detection performance on low-resolution images. Additionally, this paper constructs and incorporates the bi-level routing and spatial attention module (BRSA) into the backbone, generating multiscale feature maps with richer details. In the neck section, the original structure is replaced by the asymptotic feature pyramid network (AFPN) to reduce model parameters and computational complexity. After testing on public datasets, in comparison to YOLOv8 (the baseline), this algorithm achieves high-quality detection of flat bottom holes (FBH) and aluminium blocks on the simulated dataset. More importantly, for the challenging-to-detect defect side-drilled holes (SDH), it achieves F1 scores (weighted average of precision and recall) of 82.50% and intersection over union (IOU) of 65.96%, representing an improvement of 17.56% and 0.43%. On the experimental dataset, the F1 score and IOU for FBH reach 75.68% (an increase of 9.01%) and 83.79%, respectively. Simultaneously, the proposed algorithm demonstrates robust performance in the presence of external noise, while maintaining exceptionally high computational efficiency and inference speed. These experimental results validate the high detection performance of the proposed intelligent defect detection algorithm for ultrasonic images, which contributes to the advancement of the smart industry.
引用
收藏
页数:13
相关论文
共 34 条
  • [1] [Anonymous], 2020, arXiv
  • [2] Carion N., 2020, EUROPEAN C COMPUTER, P213, DOI 10.1007/978-3-030-58452-813
  • [3] Cheepu M.M., 2019, Mater. Sci. Forum, V969, P613, DOI DOI 10.4028/WWW.SCIENTIFIC.NET/MSF.969.613
  • [4] Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
  • [5] Ge Z., 2021, ARXIV, DOI 10.48550/ARXIV.2107.08430
  • [6] Fast R-CNN
    Girshick, Ross
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 1440 - 1448
  • [7] Rich feature hierarchies for accurate object detection and semantic segmentation
    Girshick, Ross
    Donahue, Jeff
    Darrell, Trevor
    Malik, Jitendra
    [J]. 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 580 - 587
  • [8] He KM, 2017, IEEE I CONF COMP VIS, P2980, DOI [10.1109/ICCV.2017.322, 10.1109/TPAMI.2018.2844175]
  • [9] Relation Networks for Object Detection
    Hu, Han
    Gu, Jiayuan
    Zhang, Zheng
    Dai, Jifeng
    Wei, Yichen
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 3588 - 3597
  • [10] Towards using convolutional neural network to locate, identify and size defects in phased array ultrasonic testing
    Latete, Thibault
    Gauthier, Baptiste
    Belanger, Pierre
    [J]. ULTRASONICS, 2021, 115