基于机器视觉的直插式网络变压器PIN脚平整度检测  

PIN Flatness Detection Method of Direct Plug-inNetwork Transformer Based on Machine Vision

在线阅读下载全文

作  者:杨杨 黄菊[1] YANG Yang;HUANG Ju(Department of Electrical and Electronic Engineering,Sichuan Vocational and Technical College,Suining 629000,China)

机构地区:[1]四川职业技术学院电子工程学院,四川遂宁629000

出  处:《四川职业技术学院学报》2023年第6期152-157,共6页Journal of Sichuan Vocational and Technical College

摘  要:针对直插式网络变压器PIN脚人工视检存在误差大、效率低和人工成本高等问题,提出一种基于机器视觉的网络变压器PIN脚平整度检测方法.首先采用图像预处理,通过空间滤波进行图像去噪,并对网络变压器图像灰度直方图进行阈值分割,得到信息保存完整的二值图像;接着进行K值计算(物理长度与像素长度之比)和PIN脚间距计算(图像水平校正、垂直投影以及波谷检测得到间距的像素长度).最后与网络变压器设计图纸的间距长度对比得到误差,设置误差阈值,检测网络变压器PIN脚平整度是否符合要求.实验表明,文章方法的PIN脚间距测量结果平均绝对误差为0.09mm,平均相对误差为4.6%,该方法可以快速、准确地对网络变压器PIN脚平整度进行检测,研究结果可为网络变压器自动化检测提供理论依据.Aiming at the problems of high error,low efficiency and high labor cost in the manual inspection of PIN Flatness of Direct Plug-in Network Transformer,a PIN flatness detection method based on machine vision is proposed.In the image preprocessing,image denoising by spatial filtering and threshold segmentation according to the gray histogram characteristics of network transformer image,we can get the binary image with complete information.k value(ratio of physical length to pixel length)calculating,which is obtained by vertical projection of binary image combined with conveyor speed.To calculate PIN spacing,horizontal image correction,vertical(horizontal)projection,and wave valley detection are used.Finally,the error is obtained by comparing the distance length with the design drawing of the network transformer.By setting the error threshold,the flatness of the PIN of the network transformer is detected.The experimental results show that the average absolute error of the PIN spacing measurement is 0.09 mm,and the average relative error is 4.6%.And this method can quickly and accurately detect the PIN flatness of network transformers,and the research results can provide relevant theoretical reference for automatic detection of network transformers.

关 键 词:网络变压器 PIN脚间距 垂直投影 波谷检测 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

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