用于超声波焊接线束端子表面缺陷数据集的轻量级目标检测网络
DOI:
CSTR:
作者:
作者单位:

1.桂林理工大学广西高校先进制造与自动化技术重点实验室桂林541006;2.深圳职业技术大学深圳518055; 3.深圳大学深圳518060

作者简介:

通讯作者:

中图分类号:

TP391.4; TN911.73

基金项目:

广西创新发展重大项目(桂科AA22117006-1)、深职大广州制联时空智能感知与缺陷检测研发中心(6025310012PQ)项目资助


An ultrasound welding surface defect detection lightweight network
Author:
Affiliation:

1.Key Laboratory of Advanced Manufacturing and Automation Technology, Education Department of Guangxi Zhuang Autonomous Region, Guilin University of Technology, Guilin 541006,China; 2.Shenzhen Polytechnic University, Shenzhen 518055, China; 3.Shenzhen University, Shenzhen 518060, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    超声波焊接因其环保、高效等优点在高精度连接中得到广泛应用。超声波焊接表面缺陷尺寸跨度大、背景包含大量噪声,现阶段基于深度学习的工业表面缺陷检测网络在检测精度与计算 效率方面难以兼顾。针对上述问题,提出了一种用于超声波焊接线束端子表面缺陷的轻量级目标检测网络。首先,提出小波变换多尺度特征提取模块(multi-scale wavelet transform feature extraction module, MSWT);其次,提出高效多尺度特征提取模块(efficient multiscale residual block, EMR),利用残差结构和重参数化技术增强网络对多尺度特征信息的提取能力;最后,在网络中应用上下文和空间特征校准模块(context and spatial feature calibration model,CSFC)来进行上下文特征融合, 在增强小目标检测能力的同时提升网络对全局信息的识别能力。为验证网络的有效性,在实际生产环境中构建超声波焊接线束端子表面缺陷数据集(surface defect dataset of ultrasonic welded wire harness terminals, UWSD)。经过在UWSD数据集上的实验评估,UWSDLNet在参数量为2.24×106和模型大小为4.9×106的情况下,准确率达到93.6%,平均准确率(mean average precision, mAP)达到88.2%。此外,在公开数据集NEU-DET上的良好表现证明了UWSDLNet的泛化能力和稳定性,展现了在工业缺陷检测领域的广阔前景。

    Abstract:

    Ultrasonic welding is widely used in high-precision connections due to its environmentally friendly and high efficiency. However, surface defects in ultrasonic welding vary widely in size and contain significant background noise. Current deep learning-based industrial surface defect detection networks struggle to balance detection accuracy and computational efficiency. To address these challenges, this paper proposes a lightweight object detection network for ultrasonically welded wire harness terminal surface defects. First, a multi-scale feature extraction module (MSWT) using the wavelet transform is proposed. Second, an efficient multi-scale residual block (EMR) is proposed, leveraging residual structures and re-parameterization techniques to enhance multi-scale feature representation. Third, a contextual and spatial feature calibration module (CSFC)is applied to the network to fuse contextual features, enhancing the detection of small objects and the network’s ability to recognize global information. To verify the network’s effectiveness, a dataset of surface defects in ultrasonically welded wire harness terminals (UWSD) is constructed in a real-world production environment. Experimental evaluation on the UWSD dataset shows that UWSDLNet achieves an accuracy of 93.6% and a mean average precision (mAP) of 88.2% with a computational overhead of 2.24×106 and a model size of 4.9×106. In addition, the good performance on the public dataset NEU-DET demonstrates the generalization ability and stability of UWSDLNet, showing its broad prospects in the field of industrial defect detection.

    参考文献
    相似文献
    引证文献
引用本文

刘睿,沈中华,赵伦,王彦坤,任宇,苏延和.用于超声波焊接线束端子表面缺陷数据集的轻量级目标检测网络[J].电子测量与仪器学报,2026,40(9):233-242

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-11-13
  • 出版日期:
文章二维码
×
《电子测量与仪器学报》
关于防范虚假编辑部邮件的郑重公告