摘要
现代制造业对小型断路器(MCB)生产过程的效率和精度要求都在不断提高,传统的人工装配效率低且装配质量参差不齐,而传统基于振动盘上料的自动装配技术限制了制造的柔性化水平;针对上述问题以及未来的市场需求,提出了一种基于机器视觉的小型断路器柔性装配系统,该系统搭建专用的视觉识别模块,通过VGG-16架构的深度学习分类器和特征模板匹配方法,对小型断路器零件的种类、位置坐标、当前姿态进行识别,并将识别结果发送给工业机器人控制器,指导工业机器人对不同型号产品的不同零件类型通过机器人夹爪的灵活切换来完成不同的装配任务;实验表明,该系统对零件种类识别准确率为99.8%,坐标偏差在±0.3mm以内,旋转角度偏差在±0.8°以内,达到了MCB装配的精度要求,符合柔性化制造的需求。
High efficiency and precision are the key requirements of modern miniature circuit breaker(MCB)manufacturing.Traditional manual assembly is inefficient and the quality is uneven.Conventional automatic assembling techniques with vibrating plate loading limit the flexibility in manufacturing.To solve the problems above and to meet future market demand,a flexible system using machine vision for miniature circuit breaker assembly is proposed.The system builds a visual recognition module that identifies the category,position and posture of an MCB component by the VGG-16 deep learning classifier and feature-template matching,and sends the recognition result to the industrial robot.which is guided to flexibly switch the corresponding robot jaw and perform different assembly motions.The experimental result shows that the visual system has an accuracy rate of 99.8%for category recognition,the coordinate deviation is within± 0.3 mm,and the rotation angle deviation is within±0.8°,which meets the precision requirement of flexible MCB assembly.
作者
闫俊涛
吴自然
陈宪帅
吴桂初
舒亮
Yan Juntao;Wu Ziran;Chen Xianshuai;Wu Guichu;Shu Liang(Wenzhou University,Wenzhou 325000,China)
出处
《计算机测量与控制》
2020年第7期192-198,共7页
Computer Measurement &Control
基金
浙江省重点研发计划项目(2017C01008)
温州市重大科技专项项目(2018ZG020)。
关键词
机器视觉
深度学习
姿态识别
柔性装配
machine vision
deep learning
posture recognition
flexible assembly