航空学报 > 2024, Vol. 45 Issue (1): 428624-428624   doi: 10.7527/S1000-6893.2023.28624

基于虚拟样本生成的铺丝表面缺陷检测

甘纪强, 王小平()   

  1. 南京航空航天大学 机电学院,南京 210016
  • 收稿日期:2023-02-27 修回日期:2023-03-29 接受日期:2023-09-22 出版日期:2024-01-15 发布日期:2023-11-07
  • 通讯作者: 王小平 E-mail:levine@nuaa.edu.cn
  • 基金资助:
    国家自然科学基金(51575266)

Surface defect detection of fiber placement based on virtual sample generation

Jiqiang GAN, Xiaoping WANG()   

  1. College of Mechanical & Electrical Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
  • Received:2023-02-27 Revised:2023-03-29 Accepted:2023-09-22 Online:2024-01-15 Published:2023-11-07
  • Contact: Xiaoping WANG E-mail:levine@nuaa.edu.cn
  • Supported by:
    National Natural Science Foundation of China(51575266)

摘要:

自动铺丝构件在实际生产过程中会受到环境和工艺等因素的影响,从而导致缺陷的产生并对铺丝构件以及装配整体带来严重危害。由于自动铺丝成型技术的保密性以及制造工艺昂贵和耗时等因素,有关缺陷图像的样本数据集难以获取,造成了小样本学习的问题。提出通过虚拟样本生成的方法来扩容数据集并将其作为目标检测网络的输入训练样本。针对铺丝缺陷特点,在YOLOv5s中添加坐标注意力机制来优化设计,得到最终的目标检测网络模型并命名为Place-YOLO,其精度值为0.941,平均精度均值mAP为0.833,与原始YOLOv5s相比提升了1.8%。

关键词: 自动铺丝, 生成对抗网络, 虚拟样本生成, 目标检测, 注意力机制

Abstract:

Automated Fiber Placement (AFP) components are affected by environmental and technological factors in the actual production process, leading to the generation of defects and posing serious harm to the fiber placement components and the overall assembly. Due to the confidentiality of AFP and forming technology, as well as the expensive and time-consuming manufacturing process, it is difficult to obtain sample datasets related to defect images, resulting in the problem of small sample learning. This article proposes a method of expanding the dataset through virtual sample generation and using it as input training samples for the target detection network. In response to the characteristics of fiber placement defects, a coordinate attention mechanism was added to YOLOv5s to optimize the design. The final target detection network model was named Place YOLO, with an accuracy value of 0.941 and a mean Average Precision (mAP) of 0.833, which is 1.8% higher than that of the original YOLOv5s.

Key words: automated fiber placement, generative adversarial network, virtual sample generation, object detection, attention mechanism

中图分类号: