铁氧体磁瓦表面典型缺陷检测方法

蒋红海; 李雪琴; 刘培勇; 殷国富

doi:10.3969/j.issn.0258-2724.2013.01.020

铁氧体磁瓦表面典型缺陷检测方法

doi: 10.3969/j.issn.0258-2724.2013.01.020

基金项目:

国家科技支撑计划资助项目(2006BAF01A07)

四川省高新技术产业重大关键技术项目(2010GZ0051)

详细信息

通讯作者:
殷国富(1956-),男,教授,博士生导师,研究方向为计算机辅助设计与制造(CAD/CAPP/CAM),E-mail:gfyin@scu.edu.cn

计量
- 文章访问数: 1107
- HTML全文浏览量: 58
- PDF下载量: 490
- 被引次数: 0
出版历程
- 收稿日期: 2012-03-19
- 刊出日期: 2013-02-25

Detection Method of Typical Defects in Arc Ferrite Magnet Surface

摘要

摘要: 为解决人工磁瓦表面缺陷检测质量不稳定的问题,提出了一种自动检测磁瓦表面缺陷的方法.首先利用磁瓦轮廓长度、面积等几何特征及轮廓匹配的相似度作为特征向量,采用支持向量机进行初次分类;然后再利用对凸凹缺陷的分析,得到缺陷数量和面积作为特征向量,采用最小均方误差分类器进行二次分类;最后对上述2步结果做与运算,得出最终判断.实验表明本方法可以达到正确识别率约为91.80%,错误接受率约为0.75%,正确拒绝率约为14.00%.
- 磁瓦 /
- 凸凹分类 /
- 支持向量机 /
- 缺陷检测
Abstract: An automatic detection approach was proposed to solve unstable accuracy problem of bare-eye inspection of surface defects on arc magnets. According to the geometry features such as the length and area of arc magnet contours, a primary classification of defects was implemented by the support vector machine (SVM), using contour matching similarity as the feature vector. Then, the minimum mean square error classifier was used for secondary classification based on the number and area of detects acquired from analysis of convex and concave defects. The final decision was made by performing the AND operation on the two classification results. The experiments show that the proposed method can achieve an overall accuracy rate of about 91.80%, a fault acceptance rate of about 0.75%, and a correct rejection rate of about 14.00%.
- arc magnet /
- convex and concave classification /
- support vector machine /
- defect detection

HTML全文

参考文献(15)

余永维,殷国富,蒋红海,等. 磁瓦表面图像的自适应形态学滤波缺陷提取方法[J]. 计算机辅助设计与图形学学报,2012,24(3): 351-356. YU Yongwei, YIN Guofu, JIANG Honghai, et al. Defect extraction method of arc magnet surface images based on adaptive morphological filtering[J]. Journal of Computer-Aided Design & Computer Graphics, 2012, 24(3): 351-356.

TSAI Duming, CHAO Shinmin. An anisotropic diffusion-based defect detection for sputtered surfaces with inhomogeneous textures[J]. Image and Vision Computing, 2005, 23(3): 325-338.

ZHANG Xiang, KUHLEN K, KUHLENKÖTTER B. Automatic classification of defects on the product surface in grinding and polishing[J]. International Journal of Machine Tools & Manufacture, 2006, 46(1): 59-69.

CHAPELLE O, HAFFNE P, VAPNIK V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks, 1999, 10(5): 1055-1064.

SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3): 293-300.

CHEUNG C F, HU K, JIANG X Q, et al. Characterization of surface defects in fast tool servo machining of microlens array using a pattern recognition and analysis method[J]. Measurement, 2010, 43(9): 1240-1249.

CHIOU Y C, LI Weichen. Flaw detection of cylindrical surfaces in PU-packing by using machine vision technique[J]. Measurement, 2009, 42(7), 989-1000.

ROSATI G, BOSCHETTI G, BIONDI A, et al. Real-time defect detection on highly reflective curved surfaces[J]. Optics and Lasers in Engineering, 2009, 47(3/4): 379-384.

DEINIS A, FRED M, CHIRISTOPHE D, et al. Vision system for defect imaging, detection, and characterization on a specular surface of a 3D object[J]. Image and Vision Computing, 2002, 20(8): 569-580.

FAN K C, CHEN S H, CHEN J Y, et al. Development of auto defect classification system on porosity powder metallurgy products[J]. NDT & E International, 2010, 43(6): 451-460.

SUN T H, TAENG C C, CHEN M S. Electric contacts inspection using machine vision[J]. Image and Vision Computing, 2010, 28(6): 890-901.

KULDEEP A, RAJIV S, ZHU Yijun, et al. Process knowledge based multi-class support vector classification (PK-MSVM) approach for surface defects in hot rolling[J]. Expert Systems with Applications, 2011, 38(6): 7251-7262.

HOMMA K, TAKENAKA E I. An image processing method for feature extraction of space-occupying lesions[J]. Journal of Nuclear Medicine,1985, 26(12): 1472-1477.

EMMANUEL J, CAND S, DEMANET L, et al. Fast discrete curvelet transforms[J]. Multiscale Modeling & Simulation, 2006, 5(3): 861-899.

CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1107
HTML全文浏览量: 58
PDF下载量: 490
被引次数: 0

铁氧体磁瓦表面典型缺陷检测方法

doi: 10.3969/j.issn.0258-2724.2013.01.020

通讯作者: 殷国富(1956-),男,教授,博士生导师,研究方向为计算机辅助设计与制造(CAD/CAPP/CAM),E-mail:gfyin@scu.edu.cn

计量

出版历程

Detection Method of Typical Defects in Arc Ferrite Magnet Surface

计量

出版历程

目录

通讯作者:
殷国富(1956-),男,教授,博士生导师,研究方向为计算机辅助设计与制造(CAD/CAPP/CAM),E-mail:gfyin@scu.edu.cn