Data line welding defect detection based on machine vision
摘 要
数据线的虚焊是数据线焊接过程的常见缺陷,严重影响数据线的验收与后续使用。目前针对该类缺陷多采用目视检测方式进行判断,工作效率低下,漏检率较高。已有的机器视觉算法多针对金属表面的焊缝、孔洞等缺陷进行检测,很少有算法专门对数据线的焊接质量进行检测。据此,设计了一种基于机器视觉的数据线焊接质量检测方法,首先通过角点检测分割原始图像得到待检测区域图像,再利用彩色图像局部二值模式(LBPC)分割待检测区域;然后利用轮廓检测和形态学运算获取各区域轮廓,根据轮廓特征对焊接缺陷进行分类;最后利用支持向量机(SVM)进行分类统计。试验结果表明,所提检测方法缺陷分类准确率为96%,针对性强,操作简单,具有较高的实用性。
Abstract
False welding of data lines is a common defect in the welding process of data lines, which seriously affects the acceptance and subsequent use of data lines. At present, visual inspection is often used to judge such defects, which results in low work efficiency and high missed detection rate. Existing algorithms were mostly used to detect defects such as welds and holes on metal surfaces. However, there are few specialized methods for detecting the welding quality of data lines. According to this, a method of data line welding quality detection based on machine vision was designed. First, the original image was segmented to obtain the image of the area to be detected by corner detection, and then the area to be detected was segmented by color image local binary patterns (LBP). Then, contour detection and morphological operations were used to obtain the contours of each region, and welding defects were classified based on contour features. Finally, support vector machine (SVM) was used for classification and statistics. The experimental results showed that the proposed detection method had a defect classification accuracy of 96%, strong pertinence, simple operation, and high practicality.
中图分类号 TP391.41 TG115.28 DOI 10.11973/wsjc202308013
所属栏目 试验研究
基金项目
收稿日期 2023/2/18
修改稿日期
网络出版日期
作者单位点击查看
备注税法典(1998-),男,硕士研究生,主要研究方向为数据分析和图像处理
引用该论文: SHUI Fadian,CHEN Shiqiang. Data line welding defect detection based on machine vision[J]. Nondestructive Testing, 2023, 45(8): 67~72
税法典,陈世强. 基于机器视觉的数据线焊接缺陷检测[J]. 无损检测, 2023, 45(8): 67~72
共有人对该论文发表了看法,其中:
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】杨征, 霍卫华, 秦松梅. 常见焊接缺陷原因分析及检验方法[C]//第十二届河南省汽车工程科技学术研讨会论文集.焦作:河南省汽车工程学会、焦作市科协,2015.
【2】苏俊峰.X射线探伤图像的焊缝缺陷检测系统的设计与实现[D].北京:北京邮电大学,2021.
【3】陈亮,张天江,吴员.钢悬链线立管焊缝的自动超声检测[J].无损检测,2021,43(7):45-49.
【4】彭丹.荧光磁粉探伤中裂纹自动检测方法研究[D].南京:南京邮电大学,2017.
【5】陈滔,张庆国,刘澳.基于灰度共生矩阵的图形纹理检测及焊接缺陷的SVM分类实现[J].洛阳理工学院学报(自然科学版),2022,32(1):53-61,67.
【6】高向东,谢溢龙,陈子琴,等.高强钢焊接缺陷磁光成像分形特征检测[J].焊接学报,2017,38(7):1-4,129.
【7】高堂盼.基于机器视觉的锂电池极耳焊接缺陷检测技术研究与分析[J].机电工程技术,2021,50(7):187-190.
【8】蔡文龙,李旺平,刘安阳,等.航空插头焊接异常检测技术[J].兵器装备工程学报,2022,43(2):249-253.
【9】李文静,张虎山,焦键.基于HALCON的贴片IC焊接缺陷检测算法研究[J].兵器装备工程学报,2020,41(8):244-248.
【10】刘铃,陈立峰,彭向前.基于角点检测的倾斜文档校正[J].机电信息,2019(27):136-137,139.
【11】OJALA T,PIETIKÄINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
【12】郭策锋.基于中高级视觉机理的轮廓检测方法研究[D].成都:电子科技大学,2016.
【2】苏俊峰.X射线探伤图像的焊缝缺陷检测系统的设计与实现[D].北京:北京邮电大学,2021.
【3】陈亮,张天江,吴员.钢悬链线立管焊缝的自动超声检测[J].无损检测,2021,43(7):45-49.
【4】彭丹.荧光磁粉探伤中裂纹自动检测方法研究[D].南京:南京邮电大学,2017.
【5】陈滔,张庆国,刘澳.基于灰度共生矩阵的图形纹理检测及焊接缺陷的SVM分类实现[J].洛阳理工学院学报(自然科学版),2022,32(1):53-61,67.
【6】高向东,谢溢龙,陈子琴,等.高强钢焊接缺陷磁光成像分形特征检测[J].焊接学报,2017,38(7):1-4,129.
【7】高堂盼.基于机器视觉的锂电池极耳焊接缺陷检测技术研究与分析[J].机电工程技术,2021,50(7):187-190.
【8】蔡文龙,李旺平,刘安阳,等.航空插头焊接异常检测技术[J].兵器装备工程学报,2022,43(2):249-253.
【9】李文静,张虎山,焦键.基于HALCON的贴片IC焊接缺陷检测算法研究[J].兵器装备工程学报,2020,41(8):244-248.
【10】刘铃,陈立峰,彭向前.基于角点检测的倾斜文档校正[J].机电信息,2019(27):136-137,139.
【11】OJALA T,PIETIKÄINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
【12】郭策锋.基于中高级视觉机理的轮廓检测方法研究[D].成都:电子科技大学,2016.
相关信息