Page 77 - 无损检测2024年第八期

试验研究
试验研究

DOI：10.11973/wsjc202408008

基于 RetinaNet 算法的输电线路耐张线夹压接

缺陷图像检测方法

周 飞，高 伟，李鑫博
（国网甘肃省电力公司金昌供电公司，金昌 737100）

摘 要：对输电线路耐张线夹进行射线检测时，图像特征投影过程忽略了图像清晰度对检测结
果的影响，会导致检测结果AP值较低。因此，提出基于RetinaNet算法的输电线路耐张线夹压接缺
陷图像检测方法。该方法通过判别耐张线夹压接图像的灰度值等级，计算最优分割阈值并保留检
测目标轮廓，补偿该轮廓的倾角差值以提高其清晰度，然后通过二维傅里叶逆变换重构缺陷图像，
引入RetinaNet算法融合提取图像特征，解构耐张线夹压接部位，计算缺陷特征比例得出缺陷检测
结果。试验结果表明，所提方法得出的缺陷检测结果的AP值较高，检测精度较高，满足了输电线
路耐张线夹压接质量检测的需求。
关键词：输电线路；RetinaNet算法；耐张线夹压接；缺陷检测；图像检测；输电线路缺陷
中图分类号：TP391；TG115.28 文献标志码：A 文章编号：1000-6656(2024)08-0043-05

Image detection method for compression defects in tension line clamps of

transmission lines based on RetinaNet algorithm

ZHOU Fei, GAO Wei, LI Xinbo
（State Grid Gansu Electric Power Company Jinchang Power Supply Company, Jinchang 737100, China）
Abstract: When conducting radiographic testing on tension clamps of transmission lines, the projection process of image
features ignores the impact of image clarity on the detection results, which can lead to lower AP values in the detection results.
Therefore, a method for detecting compression defects in tension line clamps of transmission lines based on RetinaNet algorithm
was proposed. This method determined the grayscale level of the compressed image of the tension wire clamp, calculated the
optimal segmentation threshold to retain the detection target contour, compensated for the difference in inclination angle of
the contour to improve its clarity, and reconstructed the defect image through two-dimensional inverse Fourier transform. The
RetinaNet algorithm was introduced to fuse and extract image features, deconstructed the compressed part of the tension wire
clamp, and calculated the proportion of defect features to obtain the defect detection result. The experimental results showed that
the defect detection results obtained by applying the proposed method had a high AP value and detection accuracy, which met the
practical needs of quality inspection for tension line clamps in transmission lines.
Key words: transmission line; RetinaNet algorithm; strain resistant wire clamp crimping; defect detection; image
detection; defect in transmission line

输电线路在电力系统中发挥着不可或缺的重要 而一旦这些金属附件出现了问题，输电线路将出现
作用。在输电线路中，存在着诸如耐张线夹等金具， 掉线等故障 。因此有必要对输电线路中的缺陷进
[1]
行检测，很多研究人员亦提示出了输电线路中的金
收稿日期：2024-01-11
具缺陷图像检测方法。
作者简介：周 飞（1976—），男，本科，高级工程师，主要研究方向
吴刘宸等 针对输电线路中螺栓缺陷的检测方
[2]
为输电线路运维、检修管理等
通信作者：周 飞，shitangmi0eg@163.com 法进行了研究，将输电线路中的螺栓元件部位设置
43
2024 年 第 46 卷 第 8 期
无损检测