Detection of surface defection of solder on flexible printed circuit

HUANG Jie-xian; LI Di; YE Feng; Zhang Wu-jie

doi:10.3788/OPE.20101811.2443

您当前的位置：

首页 >

文章列表页 >

Detection of surface defection of solder on flexible printed circuit

Article | 更新时间：2020-08-12

- Detection of surface defection of solder on flexible printed circuit
- Optics and Precision Engineering Vol. 18, Issue 11, Pages: 2443-2453(2010)
- 作者机构：
  
  华南理工大学机械与汽车学院,广东广州,510640
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20101811.2443
  CLC： TN710;TP391.4
- Received：24 February 2010，
  
  Revised：24 March 2010，
  
  Published Online：25 November 2010，
  
  Published：25 November 2010
- 稿件说明：
移动端阅览
黄杰贤, 李迪, 叶峰, 张舞杰. 挠性印制电路板焊盘表面缺陷的检测[J]. 光学精密工程, 2010,18(11): 2443-2453

HUANG Jie-xian, LI Di, YE Feng, Zhang Wu-jie. Detection of surface defection of solder on flexible printed circuit[J]. Editorial Office of Optics and Precision Engineering, 2010,18(11): 2443-2453
黄杰贤, 李迪, 叶峰, 张舞杰. 挠性印制电路板焊盘表面缺陷的检测[J]. 光学精密工程, 2010,18(11): 2443-2453 DOI： 10.3788/OPE.20101811.2443.

HUANG Jie-xian, LI Di, YE Feng, Zhang Wu-jie. Detection of surface defection of solder on flexible printed circuit[J]. Editorial Office of Optics and Precision Engineering, 2010,18(11): 2443-2453 DOI： 10.3788/OPE.20101811.2443.

摘要

针对挠性印制电路板(FPC)上的焊盘表面缺陷

提出一种基于图像处理技术的智能检测方法。首先

根据缺陷的表现形式对焊盘缺陷进行归纳与分类

采用最大熵值法量化提取焊盘的颜色特征和面积特征;然后

通过评估灰度共生矩阵(GLCM)对纹理颜色变化特征与纹理结构特征量化的有效性

将其应用于焊盘纹理特征的量化与提取。实验分析显示

缺陷焊盘与非缺陷焊盘在某个或多个特征上存在着明显的差异。基于该特点

建立了BP神经网络

以焊盘的颜色、面积、纹理结构、纹理颜色变化特征值作为神经网络的输入

通过学习大量样本

获取最佳权值参数

最终实现对FPC焊盘表面缺陷的检测

检测准确率高达94.6%

50个焊盘的检测时间为300 ms。实验结果表明:本文提出的检测方法不仅能够有效地对焊盘表面缺陷进行识别

而且能够满足在线检测对速度的要求。

Abstract

In order to detect the surface defect on the solder of a Flexible Printed Circuit(FPC)

an inspecting technology based on image processing was presented. Firstly

all the defects on the FPC were classified into several defection sorts according to their defection characters. Then

the maximum entropy was used to locate the solder and extract the square and color characters. After estimating the effectness of the Grey Level Co-occurrence Matrix(GLCM) on the quantification for color and structure characters

it was introduced to quantify and extract colorific and structural textures for solders. An analysis on experiments indicates that the defective solder is obviously different from the non-defective solder in several kinds of quantified charaters. On the basis of the result obove

the BP neural network was established and four kinds of characters were selected as the input of neural network. After all neural network weight parameters were adjusted to the optimization through sample training

the performance of the proposed defect detection algorithm was finally evaluated in an on-line testing. Test shows that 50 inspecting targets cost 300 ms

and the inspecting accuracy can reach 94.6%. The experimental result demonstrates that proposed method can detect accurately the solder defect with low false alarms

and the efficiency can satisfy the requirement of defect inspection in online and real time.

关键词

Keywords

references

<td valign='top'>[1]AYOUB G. Real-time SPC with AOI [J]. Surface Mount Technology Magazine, 2001,15(6):36 - 38.<td valign='top'>[2]WANG Q X, LI D, ZHANG W J. Detecting defects in golden surfaces of flexible printed circuits using optimal gabor filters . Intelligent Information Technology Application,2008, IITA '08. Second International Symposium on Volume 1,Dec.2008:321-325.<td valign='top'>[3]CHEN CH H, WANG C C, LIN CH Y, et al.. Realization of defect automatic inspection system for flexible printed circuit (FPC) . Proceedings of the 35th International MATADOR Conference, 2007:225-228.<td valign='top'>[4]TSAI D M,LIN B T. Defect detection of gold-plated surfaces on PCBs using entropy measures[J].The International Journal of Advanced Mannufacturing Technology</em.2002,20(6):420-428<a href='http://dx.doi.org/10.1007/s001700200172' target='_blank'><img src='../../images/crossref.gif' width='41' height='15' border='0' /><td valign='top'>[5]KAPUR J N,SAHOO P K,WONG A K C.A new method for grey-level picture thresholding using the entropy of the histogram[J]. Computer Vision,Graphics and Image Processing, 1980,3(2):223-237.<td valign='top'>[6]ABUTALEB A S.Automatic thresholding of gray-level picture using two-dimensional entropies[J].Pattern Recognition,1989,47(1):22-32.<td valign='top'>[7]HARALICK R M,SHANMUGAM K,DINSTEIN I. Textural features for image classification[J].IEEE Trans. SMC, 1973,3:610-621.<td valign='top'>[8]WALKER R F,JACKWAY P T,LONGSTAFF D. Genetic algorithm optimization of adaptive multi-scale GLCM features[J].International Journal of Pattern Recognition and Artificial Intelligence, 2003,17(1):17-39.<td valign='top'>[9]DESOKY A H,HALL S A. Entropy measures for texture analysis based on Hadamard transform[J]. Proceedings of the IEEE Southeastcon Conference, 1990(2):467-470.<td valign='top'>[10]DAWSON B R P,PARSONS A J. Texture measures for the identification and monitoring of urban derelict land[J].International Journal of Remote Sensing.1994,15(6):1259-1271<a href='http://dx.doi.org/10.1080/01431169408954159' target='_blank'><img src='../../images/crossref.gif' width='41' height='15' border='0' /><td valign='top'>[11]马立,于瀛洁,程维明,等. BP神经网络补偿并联机器人定位误差[J]. 光学精密工程,2008,16(5):878-883. MA L,YU Y J,CHENG W M,et al..Positioning error compensation for a parallel robot based on BP neural networks[J].Opt.Precision Eng.,2008,16(5):878-883.(in Chinese)<td valign='top'>[12]王自强,李银妹,楼立人,等. BP神经网络用于光镊力的非线性修正[J]. 光学精密工程,2008,16(1):6-10. WANG Z Q,LI Y M,LOU L R,et al..Application of BP neural network to nonlinearity correction of optical tweezer force[J].Opt. Precision Eng.,2008,16(1):6-10.(in Chinese)<td valign='top'>[13]沈铖武,王志乾,刘畅,等. BP神经网络在多位置捷联寻北系统中的应用[J]. 光学精密工程,2009,17(18):1890-1895. SHEN CH W,WANG ZH Q,LIU CH,et al..Application of BP neural network to multi-position strap-down north seeking system[J].Opt.Precision Eng.,2009,17(8):1890-1895.(in Chinese)<td valign='top'>[14]LOH H H, LU M S. Printed circuit board inspection using image analysis [J]. IEEE Transactions on Industry App lications, 1999,35:4262432.

Views

578

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Full-stokes photodetector based on neural networks

Detection of conductive multi-particles based on circular convolutional neural network

Partial optimal transport-based domain adaptation for hyperspectral image classification

Thermal error prediction for grinding machine spindle based on heat conduction and convolutional neural network

Stiffness prediction-neural network based error compensation for attitude adjustment platform

Related Author

WANG Shoutong

ZHANG Ran

CHU Jinkui

MENG Hailong

CAI Dehao

LUO Chen

ZHOU Yijun

JIA Lei

Related Institution

Ningbo Research Institute， Dalian University of Technology

Liaoning Provincial Key Laboratory of Micro Nanosystems， Dalian University of Technology

College of Mechanical Engineering， Southeast University

Wuxi Shangshi-finevision Technology Co.， Ltd

College of Computer Science and Technology， Jilin University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰