摘要
针对传统检测设备对金属板材凹凸表面、边缘面等特殊部位缺陷检测困难、识别率低等问题,课题组提出并设计了金属板材表面缺陷自动检测系统。通过CCD相机获取待检测部位图片,使用以Inception-V3模型为主的迁移学习算法实现对缺陷的检测。实验结果表明该系统能够准确、高效地检测出金属板材一般及特殊表面缺陷,能够满足工业生产需求。
Aiming at the problems that the traditional detection equipment has low recognition rate of defects in special parts such as uneven surface and edge of sheet metal,an automatic intelligent detection device for surface defects of metal sheets was proposed and designed.The CCD camera was used to obtain the image of the part to be detected,and the transfer learning algorithm based on the improved Inception-V3 model was adopted to detect the defect.The experimental results show that the device can accurately and efficiently detect the general and special surface defects of metal sheets,which can meet the requirements of industrial production.
作者
蔡汉明
刘明
CAI Hanming;LIU Ming(College of Electromechanical Engineering,Qingdao University of Science&Technology,Qingdao,Shandong 266100,China)
出处
《轻工机械》
CAS
2020年第1期71-74,共4页
Light Industry Machinery
