基于深度学习的航天密封圈表面缺陷检测
DOI:
CSTR:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP391. 4 TH878

基金项目:

国家自然科学基金(51575281)、中央高校基本科研业务费专项资金(30916011304)项目资助


Surface defect detection of aerospace sealing rings based on deep learning
Author:
Affiliation:

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:

    针对航天密封圈表面缺陷人工检测效率低、传统图像处理检测算法通用性差的问题,提出了两种基于深度学习的密封 圈表面缺陷检测算法。 首先,针对缺陷大部分为小目标的特点,选取对小目标较敏感的 RetinaNet 网络作为检测算法的基本架 构,通过在 RetinaNet 网络中引入轻量级网络 MoGaA 构建出 MoGaA-RetinaNet 算法。 然后,为了提高检测精度,在 MoGaARetinaNet 基础上,用分解卷积模块代替 MoGaA 骨干网络中的深度卷积构建了 newMoGaA 骨干网络,设计出 newMoGaARetinaNet 算法。 最后,在测试集上的实验结果表明,MoGaA-RetinaNet 算法比 RetinaNet 算法检测速度更快,但检测准确率略低; 而 newMoGaA-RetinaNet 算法实现了检测精度与检测速度的良好平衡,比 RetinaNet 算法准确率提升 4. 5% ,达到 92% ,检测速度提 升 55% ,达到 31 frame / s,网络参数量减少 50% 。 所设计的 newMoGaA-RetinaNet 算法可以实现密封圈表面缺陷的快速准确检测。

    Abstract:

    Aiming at the problems of low aerospace seal ring surface defect detection efficiency of manual inspection and poor versatility of traditional image processing detection algorithms, two kinds of deep learning based surface defect detection algorithms for aerospace sealing rings are proposed. Firstly, aiming at the characteristic that most of the defects are small targets, the RetinaNet network that is more sensitive to small targets is selected as the basic architecture of the defect detection algorithm, and the MoGaA-RetinaNet algorithm is constructed by introducing the lightweight network MoGaA into the RetinaNet network. Secondly, in order to improve the detection accuracy, on the basis of MoGaA-RetinaNet, the newMoGaA backbone network is constructed using the decomposition convolution module to replace the depthwise convolution in the MoGaA backbone network, and the newMoGaA-RetinaNet algorithm is designed. Finally, the experiment results on the test set show that the MoGaA-RetinaNet algorithm has faster detection speed but slightly lower detection accuracy compared with the RetinaNet algorithm; the newMoGaA-RetinaNet algorithm achieves a good balance of detection accuracy and detection speed, Compared with those of RetinaNet algorithm, the detection accuracy rate increases by 4. 5% , reaches to 92% ; the detection speed increases by 55% , reaches to 31 frame / s; and the number of network parameters is reduced by 50% . The newly designed newMoGaA-RetinaNet algorithm can achieve fast and accurate detection of the seal ring surface defects.

    参考文献
    相似文献
    引证文献
引用本文

陶晓天,何博侠,张鹏辉,田德旭.基于深度学习的航天密封圈表面缺陷检测[J].仪器仪表学报,2021,(1):199-206

复制
分享
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: 2023-06-28
  • 出版日期:
文章二维码