基于视觉识别的电缆保护管热收缩检测  

Heat Shrinkage Detection of Cable Protection Tube Based on Visual Recognition

作　　者：史会轩[1] 白张 李原 王韬[1] 孔凡胜[1] 陈永强[1] 乐文静[1] 徐征 秦威 赵云涛 熊雅婷 Shi Huixuan;Bai Zhang;Li Yuan;Wang Tao;Kong Fansheng;Chen Yongqiang;Le Wenjing;Xu Zheng;Qin Wei;Zhao Yuntao;Xiong Yating(Wuhan NARI Limited Liability Company of State Grid Electric Power Research Institute,Wuhan 430000,China;College of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]国网电力科学研究院武汉南瑞有限责任公司,武汉430000 [2]武汉科技大学信息科学与工程学院,武汉430081

出　　处：《科技通报》2022年第11期33-36,共4页Bulletin of Science and Technology

基　　金：国家自然科学基金面上项目-融合工业大数据与冶金机理的微合金钢性能预报模型研究(51774219)。

摘　　要：针对电缆保护管热收缩实验,标识线采用人工测量费时耗力问题,本文提出基于视觉识别的电缆保护管热收缩检测方法。将线阵相机用于电缆保护管热收缩检测,使用亚像素提取法在特征提取基础上对边缘像素精细提取,最终实现标识线高精度检测。通过实验验证,标识线间距测量为±0.5 mm以内,能够满足热收缩实验精度要求。At the heat shrinkage experiment of the cable protection tube, the manual measurement of the identification line is time-consuming and labor-intensive.This paper proposes a method for detecting heat shrinkage of cable protection tubes based on visual recognition.The line array camera is used to photograph the identification line of the cable protection tube, and the sub-pixel extraction method is used to finely extract the edge pixels based on the feature extraction, and finally the high-precision detection of the identification line is realized.Through experimental verification, the distance between the identification lines is measured within ±0.5 mm by visual recognition, which meets the accuracy requirements of the heat shrinkage experiment.

关 键 词：电缆保护管 热收缩实验 线阵相机 视觉 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]