扁平漆包线表面缺陷在线检测研究

doi:10.16180/j.cnki.issn1007-7820.2021.05.013

摘要/Abstract

摘要：

为实现扁平漆包线表面缺陷的在线检测,文中设计了一种基于图像处理的检测系统。该系统采用帧间差分法分离扁平漆包线的背景,针对背景分离图像中的抖动干扰进行消抖处理,通过分析消抖处理结果判断当前图像是否存在缺陷。对于存在缺陷的图像,利用连通域分析和边界追踪算法提取了缺陷的位置、面积、周长等特征。实验结果表明,该系统检测缺陷的准确率达到95%,降低了缺陷特征提取的处理时间,可以满足在线检测的要求,具有较好的应用价值。

关键词: 扁平漆包线, 图像处理, 表面缺陷, 在线检测, 帧间差分法, 背景分离, 抖动干扰, 特征提取

Abstract:

In order to realize the on-line detection of flat enameled wire surface defects, a detection system based on image processing is designed in this study. The system uses a frame-to-frame difference method to separate the background of the flat enameled wire. In view of the jitter interference in the background-separated image, a debounce process is proposed. For images with defects, features such as the location, area, and perimeter of the defects are extracted using connected domain analysis and boundary tracking algorithms. The experimental results show that the accuracy of the system for detecting defects reaches 95%, which reduces the processing time of defect feature extraction, indicating that the system can meet the requirements of online detection and has good application value.

Key words: flat enameled wire, image processing, surface defects, online detection, frame difference method, background separation, jitter interference, feature extraction

中图分类号:

TP751.1

宋章明,贺慧勇,黄跃俊. 扁平漆包线表面缺陷在线检测研究[J]. 电子科技, 2021, 34(5): 72-78.

SONG Zhangming,HE Huiyong,HUANG Yuejun. Study on On-Line Detection of Surface Defects of Flat Enameled Wire[J]. Electronic Science and Technology, 2021, 34(5): 72-78.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

表2

表3

参考文献 17

[1]	李夫, 万文俊, 刘峰, 等. 漆包线漆的制备工艺及应用进展[J]. 绝缘材料, 2014(5):1-5.
	Li Fu, Wan Wenjun, Liu Feng, et al. Preparation technology and application progress of enameled wire paint[J]. Insulating Materials, 2014(5):1-5.
[2]	王湄. 漆包线外观缺陷的产生原因及改善分析[J]. 福建农机, 2017(2):46-48.
	Wang Mei. Analysis of the causes and improvement of appearance defects of enameled wire[J]. Fujian Agricultural Machinery, 2017(2):46-48.
[3]	周鹏毅. 漆包线漆膜连续性检测的相关检测技术[D]. 长沙:长沙理工大学, 2018.
	Zhou Pengyi. Relevantdetection technology of enameled wire film continuity detection[D]. Changsha:Changsha University of Science and Technology, 2018.
[4]	李智慧, 华云松. 表面缺陷检测中工件与光源相机位置关系研究[J]. 电子科技, 2018,31(5):66-68.
	Li Zhihui, Hua Yunsong. Research on the position relation between workpiece and light source camera in surface defect detection[J]. Electronic Science and Technology, 2018,31(5):66-68.
[5]	王海涛, 甄理, 杨春霞, 等. 基于计算机视觉的铁轨表面缺陷检测系统[J]. 无损检测, 2011,33(11):38-41.
	Wang Haitao, Zhen Li, Yang Chunxia, et al. Computer vision-based rail surface defect detection system[J]. Nondestructive Testing, 2011,33(11):38-41.
[6]	李秀超. 铜扁线表面缺陷识别的设计与实现[D]. 大连:大连交通大学, 2013.
	Li Xiuchao. Design and implementation of surface defect recognition on copper flat line[D]. Dalian:Dalian Jiaotong University, 2013.
[7]	赵柏山, 郑茂凯, 张帆. 基于帧差与背景差分的改进目标识别算法[J]. 通信技术, 2018(11):2733-2739.
	Zhao Baishan, Zheng Maokai, Zhang Fan. Improved target recognition algorithm based on frame difference and background difference[J]. Communications Technology, 2018(11):2733-2739.
[8]	徐骏升. 基于机器视觉的铜扁线表面缺陷检测系统的实现[D]. 大连:大连交通大学, 2015.
	Xu Junsheng. Implementation of surface defect detection system for copper flat wire based on machine vision[D]. Dalian:Dalian Jiaotong University, 2015.
[9]	朱妍妍, 左建华, 卢继平, 等. 基于图像处理的胶管缺陷在线检测系统开发[J]. 北京理工大学学报, 2017,37(9):937-941.
	Zhu Yanyan, Zuo Jianhua, Lu Jiping, et al. Development of an online detection system for hose defects based on image processing[J]. Journal of Beijing Institute of Technology, 2017,37(9):937-941.
[10]	肖昌炎, 贾康成, 王耀南. 线扫描铁轨表面缺陷成像与检测[J]. 湖南大学学报(自然科学版), 2013,40(11):64-69.
	Xiao Changyan, Jia Kangcheng, Wang Yaonan. Imaging and detection of surface defects in line scanning rails[J]. Journal of Hunan University(Natural Science), 2013,40(11):64-69.
[11]	唐湘娜, 王耀南. 铁轨表面缺陷的视觉检测与识别算法[J]. 计算机工程, 2013,39(3):25-30.
	Tang Xiangna, Wang Yaonan. Visual detection and recognition algorithm of rail surface defects[J]. Computer Engineering, 2013,39(3):25-30.
[12]	Carlos G S, Juan C, Gonzalo M A. Real-time image processing for edge inspection and defect detection in stainless steel production lines[C]. Penang:IEEE International Conference on Imaging Systems and Techniques, 2011.
[13]	Chu H, Wang Z, Luo X. Quality inspection algorithm based on machine vision for tube-sheet welding[C]. Shanghai:IEEE Workshop on Advanced Robotics and its Social Impacts, 2016.
[14]	刘蕴辉, 刘铁, 王权良, 等. 基于图像处理的铁轨表面缺陷检测算法[J]. 计算机工程, 2007(11):236-238.
	Liu Yunhui, Liu Tie, Wang Quanliang, et al. Defect detection algorithm for rail surface based on image processing[J]. Computer Engineering, 2007(11):236-238.
[15]	茅正冲, 邬锋. 基于图像传感器的铁轨表面缺陷视觉检测算法[J]. 传感器与微系统, 2015,34(9):141-144.
	Mao Zhengchong, Wu Feng. Image sensor based on visual detection of rail surface defects[J]. Transducer and Microsystem Technology, 2015,34(9):141-144.
[16]	左东祥, 陈晓荣. 基于HALCON的刹车片尺寸和表面缺陷检测系统[J]. 电子科技, 2016,29(11):78-80.
	Zuo Dongxiang, Chen Xiaorong. HALCON-based brake pad size and surface defect detection system[J]. Electronic Science and Technology, 2016,29(11):78-80.
[17]	Min Y, Xiao B, Dang J, et al. Real time detection system for rail surface defects based on machine vision[J]. EURASIP Journal on Image and Video Processing, 2018(1):3-16.

缺陷编号	质心	面积	实际面积 /mm²	周长	实际周长 /mm
1	[163,382]	75	0.067 5	32	0.96
2	[234,396]	897	0.807 3	216	6.48
3	[264,412]	12	0.010 8	10	0.30

扁平漆包线图像	张数	正确识别张数	正确率
存在缺陷	392	375	95.7%
不存在缺陷	300	293	97.7%

	图像总数	非缺陷图像数	非缺陷图像所占比例	处理时间 a/ms	处理时间 b/ms	处理时间下降
样本1	116	63	54.3%	934	689	26.2%
样本2	115	71	61.7%	826	567	31.4%
样本3	136	71	52.2%	1 086	839	22.7%