计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (24): 243-245.DOI: 10.3778/j.issn.1002-8331.2010.24.070

• 工程与应用 • 上一篇    下一篇

焊点质量检测新方法

蔡 念,陈坚生,戴青云   

  1. 广东工业大学 信息工程学院,广州 510006
  • 收稿日期:2009-03-11 修回日期:2009-05-04 出版日期:2010-08-21 发布日期:2010-08-21
  • 通讯作者: 蔡 念

Novel inspecting method of solder joint

CAI Nian,CHEN Jian-sheng,DAI Qing-yun   

  1. School of Information Engineering,Guangdong University of Technology,Guangzhou 510006,China
  • Received:2009-03-11 Revised:2009-05-04 Online:2010-08-21 Published:2010-08-21
  • Contact: CAI Nian

摘要: 提出一种基于小波神经网络的焊点质量检测算法。首先对焊点图像进行预处理,然后提出采用形态因子和曲率作为焊点图像特征,最后建立焊点质量检测的小波神经网络模型。实验结果表明,提出的焊点质量检测算法具有较快的处理速度以及较高的准确率。

Abstract: A novel inspecting method of solder joint is proposed based on a wavelet neural network.Firstly,the images of solder joints are preprocessed.Then the morphological factor and the curvature are employed as features of the solder joint images.Finally,a wavelet neural network is established to inspect the quality of solder joints.The experimental results indicate that the proposed method for solder joint inspecting has the advantages of high speed and high accuracy.

中图分类号: