锻压技术

拉深件缺陷在线检测系统设计

英文标题：Design of on-line detection system for drawing defects

作者：徐信肖小亭温锡昌谢家静

单位：广东工业大学

分类号：

出版年,卷(期):页码：2016,41(7):97-101

摘要：

针对拉深缺陷人工检测的不足问题，提出了一种生产线上表面缺陷检测系统的设计方案。通过Halcon和VC++的联合开发，实现图像处理流程以及检测结果输出，包括摄像机标定、对图像进行平滑处理、利用动态阀值分割表面缺陷特征，通过形态学处理识别破裂缺陷，并对破裂缺陷分类和测量以及输出破裂缺陷外形和尺寸等,实现冲压生产线拉深件表面缺陷的自动检测功能。其中在相机标定过程中，采用Halcon的相机标定方法，快速获取图像坐标与世界三维坐标的对应关系，并实现缺陷特征的准确测量。此方案具有一定的稳定性，可提高检测效率。

For the problem of manual detection drawing defects, the design scheme of an on-line automatic detection system was put forward on the stamping production line. In the scheme, the image processing and the output of detection were achieved through the joint development of Halcon and VC++ including camera calibration，image smooth processing，the segment of surface defects with dynamic threshold. Furthermore, the auto-detection function on surface defects of drawing parts in stamping production line was achieved by identification of crack defects with morphology processing，classification and measurement of crack defects and output of the length and the shape of the crack defects etc. During the camera calibration, camera calibration method based on Halcon was carried out, and the transformation between image coordinate and three-dimensional coordinates of the world could be obtained to achieve automatic measurement of defect features accurately. This scheme is of good stability, and the detection efficiency is improved.

基金项目：

广东省战略性新兴产业发展专项（2012A090100014）；广东工业大学2015年大学生创新项目(yj201511845110)

徐信（1990-），男，硕士研究生

参考文献：

[1]彭向前.产品表面缺陷在线检测方法研究及系统实现[D].武汉：华中科技大学,2008.

Peng X Q, Online Defects Inspection Theory and Algorithms for Product Surface based on Distribution Machine Vision [D]. Wuhan: Huazhong University of Science and Technology, 2008.

[2]王震宇.基于机器视觉钢板表面缺陷检测技术研究[J].计算机与现代化,2013,（7）:130-134.

Wang Z Y. Research on steel plate surface defects detection method based on machine vision [J]. Computer and Modernization, 2013, (7):130-134.

[3]聂振宇.金属部件表面缺陷视觉检测系统研究[D].长沙：中南大学,2013.

Nie Z Y. Research on Metal Parts Surface Defect Visual Inspection System [D]. Changsha:Central South University, 2013.

[4]贾丹.摄像机现场标定算法研究[D].哈尔滨：哈尔滨工程大学,2007.

Jia D. Researches on Site Camera Calibration Methods [D]. Harbin: Harbin Engineering University, 2007.

[5]罗珍茜,薛雷,孙峰杰,等,基于HALCON的摄像机标定[J].电视技术,2010,34(4):100-102.

Luo Z Q, Xue L, Sun F J,et al. Camera calibration based on HALCON [J]. Video Engineering, 2010, 34(4):100-102.

[6]Noguchi R, Hayashi J I. A method for character and photograph segmentation using dynamic thresholding[A]. The Workshop on Frontiers of Computer Vision. IEEE[C]. Mokpo,2015.

[7]李大成，梁晋，胡浩，等. 数字图像相关法用于金属薄板成形性能研究[J]. 锻压技术，2014，39（5）：23-28.

Li D C，Liang J，Hu H，et al. Digital image correlation measurement for forming properties of sheet metal [J]. Forging & Stamping Technology，2014，39（5）：23-28.

[8]斯蒂格,尤里奇,威德曼.机器视觉算法与应用[M].杨少荣，译.北京：清华大学出版社,2008．

Steger C, Ulrich M, Wiedemann C. Machine Vision Algorithms and Applications [M]. Translated by Yang S R. Beijing: Tsinghua University Press,2008.

[9]潘武,张莉彦,徐俊成,等.基于机器视觉的工件的在线检测[J].组合机床与自动化加工技术,2012,(7):75-78.

Pan W, Zhang L Y, Xu J C, et al. The research about on-line detection of work piece based on machine vision [J]. Combined Machine Tool and Automatic Machining Technology, 2012, (7):75-78.

[10]黄柳倩.基于机器视觉的冲压件缺陷检测系统研究[D].广州：广东工业大学,2012.

Huang L Q. Research of Stamping Defect Detection System based on Machine Vision[D]. Guangzhou: Guangdong University of Technology,2012.

服务与反馈：

【本网站尚未开通全文下载服务】【加入收藏】