（2D）2LDA和支持向量机在PCB焊点检测中的应用  

Application of（2D）2LDA and support vector machine in PCB solder joint inspection

作　　者：贺海浪 龙绪明[1] 刘明晓[1] 罗爱玲[1] 

机构地区：[1]西南交通大学电气工程学院,四川成都610031

出　　处：《现代电子技术》2015年第2期100-103,共4页Modern Electronics Technique

摘　　要：在现代印刷电路板生产过程中,焊点质量检测是其中的一个重要组成部分。然而随着电子元器件封装的不断小型化,焊点质量检测也变得越来越具有挑战性,传统的依靠人工检测的方式已经越来越不能满足实际生产的需要,同时,基于图像处理与人工智能的自动光学检测技术在焊点质量检测中得到越来越广泛的应用。在此提出一种将双方向二维线性判别分析和支持向量机相结合的焊点质量自动光学检测方法。实验结果表明,该方法能够取得良好的识别效果。During the production of printed circuit board,quality detection of welding spot is an important component. How-ever,with the miniaturization of electron components’package,quality detection of welding spot becomes more and more chal-lenging and traditional detection methods based on artificial detection can’t satisfy needs of practical production. Meanwhile,au-tomatic optic inspection based on image processing and artificial intelligence technology has been used in quality detection of welding spot more and more extensively. A kind of automatic optic inspection method combined with two directional two-dimen-sion linear discriminant analysis and support vector machine in quality detection of welding spot is put forward in this paper. The experimental results indicate that this method is helpful in recognization.

关 键 词：焊点检测 双方向二维线性判别分析 支持向量机 印刷电路板生产 

分 类 号：TN911-34[电子电信—通信与信息系统] TP391.4[电子电信—信息与通信工程]