电能表贴片电阻及焊点异常检测分析系统  被引量:1

Detection and analysis system of power meter patch resistance and welding spot abnormality

在线阅读下载全文

作  者:蒋超 陈圣泽 张智晶 李蕊 JIANG Chao;CHEN Shengze;ZHANG Zhijing;LI Rui(State Grid Shanghai Municipal Electric Power Company Marketing Service Center,Shanghai 200051,China)

机构地区:[1]国网上海市电力公司营销服务中心,上海200051

出  处:《现代电子技术》2023年第10期54-60,共7页Modern Electronics Technique

基  金:国家电网上海市电力公司科技项目(52090020007H)。

摘  要:针对当前电能表异常检测领域中更换贴片电阻与焊点异常的检测取证难度高、检测装置不便携等问题,文中基于机器视觉提出一种电阻与焊点异常检测算法,开发实现电能表异常检测现场分析系统。电阻异常检测算法首先将K⁃D树与Ransac相结合完成高效率电能表配准,然后通过差影法对电阻可疑异常区域进行检测,再根据分类网络对可疑异常区域识别到的电阻数值判断电阻异常情况。焊点异常检测算法通过显著性检测对图像进行特征增强,然后分割获取焊点目标信息,最后结合连通域分析判定焊点异常情况。实验结果表明:电能表异常检测现场分析系统贴片电阻异常检测正检率达到95.28%,检测时间约为1.52 s;焊点异常检测正检率达96.74%,检测时间约为0.74 s,说明该系统能够满足现场检测精度和速度的需求,具有较好的应用价值。In allusion to the problems in the current field of abnormality detection of power meters,such as the difficulty of obtaining evidence for replacing patch resistances and detecting welding spot abnormality,and the inportability of the detection device,a detection algorithm for resistance and welding spot abnormality is designed based on machine vision,and an on⁃site analysis system for power meter abnormality detection is developed and implemented.By the resistance abnormality detection algorithm,the K⁃D tree is combined with Ransac to complete the registration of high efficiency power meters.The suspected abnormal areas of resistance is detectsed by means of the different shading method.The abnormal resistance is judged based on the resistance values recognized in the suspected abnormal areas by the classification network.The welding spot abnormality detection algorithm can be used to enhance the image features by means of saliency detection,then obtain welding spot target information by segmentation,and finally determine welding spot abnormality by connected domain analysis.The experimental results show that the patch resistance abnormality detection rate of the on⁃site analysis system for abnormality detection of power meters can reach 95.28%,and the detection time is about 1.52 s;its positive detection rate of welding spot abnormality detection is 96.74%,and the detection time is about 0.74 s,indicating that the system can meet the requirements of on⁃site detection accuracy and speed,and has good application value.

关 键 词:电能表 贴片电阻 电阻异常判断 焊点异常检测 检测算法 系统设计 

分 类 号:TN911.23-34[电子电信—通信与信息系统] TP311[电子电信—信息与通信工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象