计算机与现代化 ›› 2022, Vol. 0 ›› Issue (07): 15-20.

• 图像处理 • 上一篇    下一篇

基于双模型的输电线绝缘子自爆检测算法

  

  1. (1.国网安徽省电力有限公司信息通信分公司,安徽合肥230002;2.安徽大学电子信息工程学院,安徽合肥230601;
    3.安徽南瑞继远电网技术有限公司,安徽合肥230094)

  • 出版日期:2022-07-25 发布日期:2022-07-25
  • 作者简介:林航(1975—),男,江苏海密人,高级工程师,研究方向:电网智能巡检,E-mail: linh_752005@hotmail.com。
  • 基金资助:
    国家自然科学基金资助项目(61672032)

An Insulator Self-detonation Detection Algorithm on Transmission Line Based on Double Modules

  1. (1. Anhui State Grid Information & Telecommunication Co. Ltd., Heifei 230002, China; 
    2. School of Electronic and Information Engineering, Anhui University, Heifei 230601, China; 
    3. Anhui Nanrui Jiyuan Power Grid Technology Co. Ltd., Heifei 230094, China)
  • Online:2022-07-25 Published:2022-07-25

摘要: 针对输电线路无人机巡检图像中绝缘子自爆缺陷目标小而难以精准检测的问题,提出一种基于Faster R-CNN和改进的YOLO v3级联双模型的绝缘子自爆缺陷检测算法。首先,利用无人机巡检图像构建绝缘子串缺陷数据集,并对训练图像样本进行翻转预处理,增加样本数量,提高模型泛化能力,避免过拟合;然后,利用Faster R-CNN检测图像中的绝缘子串,再将检测到的绝缘子串图像送入改进的YOLO v3网络进行自爆缺陷的定位。改进的YOLO v3网络是在YOLO v3基础上借鉴FPN的思想,增加特征提取层并进行特征融合,充分利用深层特征和浅层特征;同时采用CIoU Loss函数作为损失函数,以解决边界框宽高比尺度信息。实验结果表明,本文算法在所构建的绝缘子缺陷数据集上的检测准确率达到91.2%,相比Faster R-CNN或YOLO v3等单模型检测算法提升了3.31个百分点以上,能有效实现无人机巡检中绝缘子自爆缺陷的检测,为输电线路智能化巡检故障诊断提供方法支持。

关键词: 绝缘子自爆, 目标检测, Faster R-CNN, YOLO v3, CIoU Loss

Abstract: Aiming at the problem that it is difficult to accurately detect  the small defects targets of insulator self-detonation in transmission line UAV inspection images, this paper proposes an insulator self-detonation defect detection algorithm based on Faster R-CNN and the improved YOLO v3 cascaded dual model. Firstly, the insulator string defect dataset is constructed using UAV inspection images, and the training image samples are pre-processed by flipping to increase the number of samples and improve the generalization ability of the model and avoid over fitting; then the Faster R-CNN is used to detect the insulator strings in the images, and then the detected insulator string images are fed into the improved YOLO v3 network for locating the self-exploding defects. The improved YOLO v3 network is based on YOLO v3 by borrowing the idea of FPN, adding feature extraction layer and performing feature fusion to make full use of deep and shallow features; meanwhile, the CIoU Loss function is used as the loss function to solve the boundary frame aspect ratio scale information. The experimental results show that the detection accuracy of the proposed algorithm reaches 91.2% on the constructed insulator defect dataset, which is more than 3.31 percentage points higher than that of single-model detection algorithms such as Faster R-CNN or YOLO v3, and can effectively realize the detection of insulator self-detonation defects in UAV inspection, which provides methodological support for intelligent inspection fault diagnosis of transmission lines.

Key words: insulator self-detonation, target detection, Faster R-CNN, YOLO v3, CIoU Loss