基于YOLOv7x的接触网吊弦缺陷检测方法
DOI:
作者:
作者单位:

1.华东交通大学电气与自动化工程学院,江西 南昌 330013 ;2.华东交通大学土木建筑学院,江西 南昌 330013

作者简介:

王晓明(1978—),男,副教授,硕士生导师,研究方向为人工智能,机器视觉,柔性传感器,物联网技术及应用。E-mail:2501@ecjtu.edu.cn。

通讯作者:

中图分类号:

U225.4

基金项目:

国家自然科学基金项目(52165069);江西省教育厅科技项目(GJJ2200621)


Detection Method of Catenary Hanging String Based on YOLOv7x
Author:
Affiliation:

1.School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013 , China ;2.School of Civil Engineering and Architecture, East China Jiaotong University, Nanchang 330013 , 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:

    目的】针对铁路运行时由于接触网吊弦缺陷造成的安全隐患问题,提出一种基于改进YOLOv7x的接触网吊弦缺陷识别方法。【方法】首先在主干特征提取层的末端引入Swin Transformer网络替换原有的扩展高效层聚合网络模块,提高网络掌握全局信息的能力,再引用SIoU(SCYLLA-IoU)损失函数替换原网络的损失函数,为预测框收敛过程添加方向惩罚机制,最后使用coordinate attention(CA)注意力机制融合颈部层中的扩展高效层聚合网络模块,增强颈部网络模块的全局感受野。【结果】 仿真结果表明,此改进算法训练出的模型精度达到95.9%,相较于原YOLOv7x算法检测精度提高了4.7%,检测速度也达到了 52 帧/s。【结论】改进算法解决了在吊弦缺陷识别领域检测效率低下的问题,在实际作业中能够提高接触网吊弦缺陷排查工作的效率。

    Abstract:

    Objective】Aiming at the potential risk caused by overhead contact wire defects during railway operation, an improved YOLOv7x method for overhead contact wire defect identification is proposed.【Method】Firstly, Swin Transformer network is introduced at the end of the backbone feature extraction layer to replace the original extended and efficient layer aggregation network module, so as to improve the ability of the network to grasp global information. Then the SIoU(SCYLLA-IoU) loss function is used to replace the original network loss function, and the direction penalty mechanism is added to the convergence process of the prediction frame. Finally, CA is integrated with the extended and efficient layer aggregation network module to enhance the global receptive field of the neck network module.【Result】Experimental simulation results show that the accuracy of the model trained with the improved algorithm reaches 95.9%, which is 4.7% higher than that of the original YOLOv7x algorithm, and the detection speed reaches 52 frames per second.【Conclusion】The improved algorithm solves the problem of low detection efficiency in hanging strings defect identification, which may improve the efficiency of detection of hanging strings defect in practice.

    参考文献
    相似文献
    引证文献
引用本文

王晓明,陈智宇,董文涛,姚道金,黄贻凤.基于YOLOv7x的接触网吊弦缺陷检测方法[J].华东交通大学学报,2024,41(3):65-73.
Wang Xiaoming, Chen Zhiyu, Dong Wentao, Yao Daojin, Huang Yifeng. Detection Method of Catenary Hanging String Based on YOLOv7x[J]. JOURNAL OF EAST CHINA JIAOTONG UNIVERSTTY,2024,41(3):65-73

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:2023-08-28
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-07-09
  • 出版日期:
关闭