第19卷
第3期
2011年3月
文章编号
1004-924X(2011)03-0567-06
光学精密工程
Optics and Precision Engineering
基于侧向连接Sanger算法实现
微钻头棱边投影的拟合
葛动元1.2，姚锡凡1，向文江2
（1.华南理工大学机械与汽车工程学院，广东广州510640
2.邵阳学院机械与能源工程系，邵阳湖南422004）
Vol.19
No.3 Mar, 2011
摘要：针对微钻头的圆角、外径等的检测，研究了微钻头棱边投影的拟合方法。首先，采用印刷电路板（PCB)微钻头高精度自动化检测系统采集图像。在对微钻头棱边投影的椭圆方程进行拟合时，以采样点坐标的组合失量坐标到超平面距离的平方和为目标函数。然后，根据求解目标，设计一个有侧向连接的Sanger网络，以采样点坐标组成的矢量坐标为 Sanger网络的输人。最后，采用自适应次分量的提取方法，以自相关矩阵的最小特征值所对应的特征向量为超平面的拟合系数，即椭圆方程拟合系数，得到微钻头的圆角、外径等技术指标。这种自适应Sanger网络在工件形状误差检测中的应用方法能满足微钻头检测的精度要求。
调：微钻头；几何参数；视检测；Sanger神经网络
键关
中图分类号：TB92;TP391
文献标识码：A
doi;10,3788/OPE, 20111903. 0567
Fittingmarginprojectionofmicro-drillbasedon
Sangeralgorithmwithlateralconnection GE Dong-yuan'-2,YAO Xi-fan',XIANG Wen-Jiang
(1.School of Mechanical &AutomotiveEngineering,SouthChina
University of Technology,Guangzhou 510640,Chind; 2.Department of Mechanical and
EnergyEngineering，ShaoyangUniversity，Shaoyang422004，China)
Abstract: To measure the rounded corner and diameter of a micro-drill, the fitting of the elliptical e-quation for margin projection of the micro-drill was researched. Firstly,the margin projective image
tion of margin projection of micro-drill was fitted, the sum of square distance from the sample points" vector coordinates to the hyperplane determined by the elliptical coefficients was taken as an objective function. Then, a Sanger neural network with lateral connection was designed, in which the input sig nal were vector coordinates composed of sample points, Finally,on the basis of an adaptive minor com-ponent extracting method, the eigenvector of minimum eigen values was taken as the fitted coefficients of the hyperplane, i, e. , fitted elliptical coefficients, and the rounded corner and diameter of the mi
收稿日期：2010-05-05；修订日期：2010-06-28.
基金项目：国家863高技术研究发展计划资助项目（No,2007AA04Z111)，湖南省教育厅重点资助项目（No.07A062)，湖南
省自然科学基金资助项目(No.09J6092)，潮南省教育厅资助科研项目(No,09B092)