摘要
针对中小型企业在焊接缺陷检测领域中存在人工成本高、检测精度低、实时性差等问题,提出了基于机器视觉的焊接缺陷检测系统,在生产线上安装多套图像采集装置。根据现场情况,设计了多套打光方案,实现连锡、焊点偏位、芯线断开等缺陷的高清成像;基于HALCON软件,采用图像定位、图像预处理、图像分割、形态学处理及焊接缺陷识别算法,完成了USB接口缺陷的精确检测,并将结果显示在上位机界面。测试生产线上实际采集的402幅缺陷图像,结果表明,系统成功检出率达86%,基本满足实际生产需要。该检测系统用于中小型企业生产,有利于大幅度提高检测效率和缺陷检测智能化水平,同时降低检测成本。
Aiming at the problems of high labor cost,low detection accuracy and poor real-time in the field of weld-ing defect detection in small and medium-sized enterprises,a welding defect detection system based on machine vision is proposed,and multiple sets of image acquisition devices are installed in the production line.According to the on-site situation,several sets of polishing schemes are designed to achieve high-definition imaging of defects including the tin connection,solder joint offset,core wire disconnection,and etc.Based on HALCON software,the precise detection of USB interface defects is completed by using image positioning,image preprocessing,image segmentation,morphological processing and welding defect recognition algorithm.Results are displayed on the upper computer interface.402 defect images collected on the production line are tested.Results show that the system has a successful detection rate of 86%,which basically meets the requirement of actual production.The detection system is used in the production of small and medium-sized enterprises,which is conducive to greatly improving the detection efficiency and the intelligent level of defect detection,while reducing the detection cost.
作者
易欢
汪志成
YI Huan;WANG Zhicheng(School of Mechanical and Electronic Engineering,East China Institute of Technology,Nanchang 330013,China)
出处
《仪表技术》
2023年第3期55-58,共4页
Instrumentation Technology
关键词
机器视觉
缺陷检测
图像识别
机器视觉软件
machine vision
defect detection
image recognition
machine vision software
