基于机器视觉的微小型组件精密测量与装配
|
摘要
微机电系统高度集成化的需求不断增加,但其整合过程还依赖于熟练装配人员的个人经验来完成,零件装配的稳定性和精度指标远远不能达到要求,极大地限制了微产品产业化的进程。机器视觉辅助的微小型组件装配系统借助于视觉系统的特点不断地被应用于实际生产过程中,显著提高零件装配精度和稳定性,越来越得到研究人员的重视,成为工业现代化进程中的重要技术革新内容之一
基于机器视觉的微装配技术关键在于机器视觉识别定位的精度以及装配系统协调动作的一致性。待装配零件往往存在表面质量差、尺寸跨度大、形状不规则等问题,不仅会影响零件特征识别的真实度,而且对装配系统设计的通用性也有较高的高求。此外,独立功能模块之间相对运动产生的位置不确定度也是微小型零件装配系统架构中需要重点考虑的问题。
为解决上述微装配技术难题,针对跨尺度多零件精密装配任务,本文架构了基于双摄像机的自动装配系统。双摄像机架构解决了视场局限性的问题；机械、吸附混合式夹持机构保证了多形状易碎零件的柔性夹持；实时监控反馈的装配策略防止误装配引起零件和系统的损坏。
在保证合适的照明和图像预处理的前提下,图像高级处理采用canny算法、边界全局逐点扫描算法、动态空间矩定位扫描算法进行目标边界的提取。针对不同零件的空间定位区别情况,采用局部图像的拼接定位法、基于最小包围矩形的质心定位法、特征圆和直线的优化最小二乘拟合定位法、基于Radon变换的零件角度定位算法进行零件图像拼接和定位,获取图像坐标位置信息。然后将实验获取的摄像机和系统参数标定值引入坐标变换矩阵,将图像坐标信息转换为装配模块对准时的平移量和转角量,引导其对准装配动作。针对个别零件无法直接视觉定位的问题,本文设计了间接视觉测量辅助的装配策略实现其装配作业。
装配实验结果表明,本系统很好的实现装配精度要求,极大地提高装配作业效率和稳定性,实际生产成品率表现突出。
The demand for highly-integrated micro electromechanical systems is increasing dramatically, but their integration process still depends on the experience of professional workers, which makes the assembly stability and accuracy not highly met and the process of micro products industrialization slow down. Due to the advantage of machine vision technology, the computer vision based assembly system for miniature components is widely put into industrial manufacturing use. As a result, the assembly stability and accuracy are greatly improved while the working intensity is effectively controlled. So computer vision based assembly technology is attracting more and more researchers'attention and becoming very important technology innovation aspect of industry modernization.
The key issue for machine vision based assembly technology lies in the achieved recognition and position accuracy of machine vision system and the consistency of whole working platform. The parts to be assembled always have the problem of poor surface condition, wide range of dimensional span and varied manufacturing shapes. They can not only influence the parts edge detection accuracy but also raise high demand on the generality of assembly system. In addition, the position uncertainty caused by movement of relevant functional subsystem is also a very essential problem that needs to be further discussed during system construction.
In order to solve the micro assembly difficulties mentioned above, a double camera auto-assembly system for multiple parts is constructed and put into use. Double camera is applied to meet the different demand of detection vision field. Multi-functional manipulating mechanism, which includes both mechanical gripper and vacuum pad, is designed to ensure the flexible clamping of different fragile assembly parts. The real-time monitoring strategy is carried out, which uses the feedback to control system's next motion.
After proper illumination and image preprocessing is implemented, the advanced image process is used to extract the target contour. It includes canny detection algorithm, global points scanning method and dynamic centroid position scanning method. Afterwards different kinds of algorithms are carried out to fulfill image matching and positioning, which is consisted of image mosaic positioning method, Minimum bounding rectangle algorithm positioning method, least square fitting method for line and circle and randon angle detection method. Frame transformation, the parameters of which are obtained through camera calibration and system calibration experiments, is applied to calculate the displacement for aligning and assembling task later. Besides, an indirect vision measuring strategy is developed to fulfill the assembly of certain parts which can not acquire real-time image detection and position.
The experiment results demonstrate that high assembly accuracy is achieved while assembly efficiency and stability is improved. Consequently, this promises a much higher yielding rate and economic profits.
基于机器视觉的微装配技术关键在于机器视觉识别定位的精度以及装配系统协调动作的一致性。待装配零件往往存在表面质量差、尺寸跨度大、形状不规则等问题,不仅会影响零件特征识别的真实度,而且对装配系统设计的通用性也有较高的高求。此外,独立功能模块之间相对运动产生的位置不确定度也是微小型零件装配系统架构中需要重点考虑的问题。
为解决上述微装配技术难题,针对跨尺度多零件精密装配任务,本文架构了基于双摄像机的自动装配系统。双摄像机架构解决了视场局限性的问题；机械、吸附混合式夹持机构保证了多形状易碎零件的柔性夹持；实时监控反馈的装配策略防止误装配引起零件和系统的损坏。
在保证合适的照明和图像预处理的前提下,图像高级处理采用canny算法、边界全局逐点扫描算法、动态空间矩定位扫描算法进行目标边界的提取。针对不同零件的空间定位区别情况,采用局部图像的拼接定位法、基于最小包围矩形的质心定位法、特征圆和直线的优化最小二乘拟合定位法、基于Radon变换的零件角度定位算法进行零件图像拼接和定位,获取图像坐标位置信息。然后将实验获取的摄像机和系统参数标定值引入坐标变换矩阵,将图像坐标信息转换为装配模块对准时的平移量和转角量,引导其对准装配动作。针对个别零件无法直接视觉定位的问题,本文设计了间接视觉测量辅助的装配策略实现其装配作业。
装配实验结果表明,本系统很好的实现装配精度要求,极大地提高装配作业效率和稳定性,实际生产成品率表现突出。
The demand for highly-integrated micro electromechanical systems is increasing dramatically, but their integration process still depends on the experience of professional workers, which makes the assembly stability and accuracy not highly met and the process of micro products industrialization slow down. Due to the advantage of machine vision technology, the computer vision based assembly system for miniature components is widely put into industrial manufacturing use. As a result, the assembly stability and accuracy are greatly improved while the working intensity is effectively controlled. So computer vision based assembly technology is attracting more and more researchers'attention and becoming very important technology innovation aspect of industry modernization.
The key issue for machine vision based assembly technology lies in the achieved recognition and position accuracy of machine vision system and the consistency of whole working platform. The parts to be assembled always have the problem of poor surface condition, wide range of dimensional span and varied manufacturing shapes. They can not only influence the parts edge detection accuracy but also raise high demand on the generality of assembly system. In addition, the position uncertainty caused by movement of relevant functional subsystem is also a very essential problem that needs to be further discussed during system construction.
In order to solve the micro assembly difficulties mentioned above, a double camera auto-assembly system for multiple parts is constructed and put into use. Double camera is applied to meet the different demand of detection vision field. Multi-functional manipulating mechanism, which includes both mechanical gripper and vacuum pad, is designed to ensure the flexible clamping of different fragile assembly parts. The real-time monitoring strategy is carried out, which uses the feedback to control system's next motion.
After proper illumination and image preprocessing is implemented, the advanced image process is used to extract the target contour. It includes canny detection algorithm, global points scanning method and dynamic centroid position scanning method. Afterwards different kinds of algorithms are carried out to fulfill image matching and positioning, which is consisted of image mosaic positioning method, Minimum bounding rectangle algorithm positioning method, least square fitting method for line and circle and randon angle detection method. Frame transformation, the parameters of which are obtained through camera calibration and system calibration experiments, is applied to calculate the displacement for aligning and assembling task later. Besides, an indirect vision measuring strategy is developed to fulfill the assembly of certain parts which can not acquire real-time image detection and position.
The experiment results demonstrate that high assembly accuracy is achieved while assembly efficiency and stability is improved. Consequently, this promises a much higher yielding rate and economic profits.
引文
[1]韩卫军,丁富强,赵锡芳,机器人装配系统产品装配质量影响因素研究[J].制造业自动化.2002,24(9)：14-18.
[2]张德荣.科研产品的装配工艺及工艺管理.机电设备.2007,(7)：1-3.
[3]包丽雅.微装配技术及其在引信中的应用.黑龙江科技信息.2008,31：27.
[4]席文明,吴洪涛,朱剑英.微装配技术的发展现状.机械科学与技术.2002,11(21)：861-865.
[5]Song Yu, Li Mantian, Sun Lining, et al. Global Visual Servoing of Miniature Mobile Robot inside a Micro-Assembly Station. Proceedings of the IEEE International Conference on Mechatronics & Automation.2005:1586-1591.
[6]Wang Lin, Wang Xiaodong, Zhang Xiwen.Micro-stress assembly of fragile miniature parts. The second International Conference of CSMNT.2010.
[7]廖万辉,李琳.基于机器视觉的工业机器人定位系统.机器人技术.2009,25(32)：242-244.
[8]GRACIAS. D. H, TIEN. J, BREEN T. L. Forming electrical network in three dimensions by self-assembly. Science.2000,289(18):1170-1172.
[9]贾云得.机器视觉[M].北京：科学出版社,2000.
[10]SNYDER W E, QI H R. Machine Vision[M]. Landon:Cambridge University Press,2005.
[11]L.Roberts. Machine perception of three-dimensional solidsIn:Tippertt J. Optical and Electron-Optical Information Processing. Cambridge, MA:MIT Press.1965,159-197.
[12]D. Marr. Vision[M].W.H. Freeman and Company,1982.
[13]D G Lowe. Three-dimensional object recognition from single two-dimensional images, AI.1987,37:355-395.
[14]J Aloimonos,I Weiss, A Bandopadhay. Active vision, IJCV.1988,1:333-356.
[15]王力.基于机器视觉的贴片元件定位系统的研究与开发[D].苏州：苏州大学,2009.
[16]岳晓峰.计算机视觉技术及其在工业中应用的研究.吉林：吉林大学,2006.
[17]王崇涛.基于机器视觉的表面缺陷检测仪在冷轧生产的应用.河南冶金金.2007,15(9)：57-60.
[18]鲍官军,荀一,戚利勇.机器视觉在黄瓜采摘机器人中的应用研究.浙江工业大学学报.2010,38(1)：114-118.
[19]刘长红,徐杜,蒋永平.基于机器视觉的心脏医学图像处理研究.计算机与应用化学.2010,7(27)：997-1000.
[20]李超,李运华.基于机器视觉的高精度顶桥施工位姿测量系统.北京航空航天大学学报.2007,3(33)：322-326.
[21]王丽英.需求带来市场-机器视觉迎来发展的春天[J].今日电子,2008,(6)：67.
[22]尹周平,熊有伦.微装配技术的研究进展及其展望.半导体技术.2004,29(5)：6-9.
[23]S. Fatikow, R. Munassypov, U. Rembold. Assembly Planning and Plan Decomposition in an Automated Microrobot-Based Microassembly Desktop Station. Journal of Intelligent Manufacturing(1998)9,73-92, Chapman & Hall, London.
[24]Stephen J. Ralis, Barmeshwar Vikramaditya, and Bradley J. Nelson. Micropositioning of a Weakly Calibrated Microassembly System Using Coarse-to-Fine Visual Servoing Strategies. IEEE Transactions on Electronics Packaging Manufacturing.2000,23(2):123-131.
[25]Driesen, W., Varidel, T., Mazerolle,S.,et al. Flexible micromanipulation platform based on tethered cm3-sized mobile micro robots[C],IEEE International Conference on Robotics and Biomimetics, Hong Kong,2005:145-150.
[26]GIOUROUDI I, HOTZENDORFER H, KOSEL J, et al. Development of a microgripping system for handling of microcomponents[J]. Precision Engineering,2008, (32):148-152.
[27]SONG Y, LI M T, SUN L N, et al. Global Visual Servo of Miniature Mobile Robot inside a Micro-Assembly Station[C]. Proceedings of the IEEE International Conference on Mechatronics & Automation,2005:1586-1591.
[28]刘超.基于机器视觉的微小型零件自动测量与装配.大连：大连理工大学,2009.
[29]段瑞玲,段惠波,李庆祥.基于图像处理的微装配自动调焦系统.光学精密工程.2006,6(14)：468-472.
[30]张建忠.孔-轴装配机器人视觉制导关键技术研究[D].南京：东南大学,2005.
[31]刘景泰,吴水华,孙雷.基于视觉的遥操作机器人精密装配系统.机器人.2005,3(27)：178-182
[32]黄桂平,李云,王保丰,etal.单目视觉测量技术研究.计量学报.2004,25(4)：314-317.
[33]周婷.基于OpenCV的移动靶面图像识别算法研究[D].大连：大连海事大学,2008.
[34]丁哲.机器视觉硬件选型基础[EB/OL]. http://www.visiondragon.com,2007.
[35]吴淑梅,霍彦明.LED光源的应用及前景[J].灯与照明,2008,32(3)：24-26.
[36]席文明,姚斌.微装配与微操作[M].北京：国防工业出版社,2006.
[37]王晓东,宋洪侠,J. HESSELBACH.德国微装配技术研究的几个方向[J].机械制造,2002,(09)：13-15.
[38]张毓晋.图像处理与分析.北京：清华大学出版社,1999.
[39]王朝晖.基于计算机视觉反馈微装配系统及其关键技术研究[D].西安：西安交通大学,2002.
[40]SONKA M,HLAVAC V,BOYLE R.图像处理、分析与机器视觉[M].北京：人民邮电出版社,2003.09.
[41]贾永红.数字图像处理[M].武汉：武汉大学出版社,2003.
[42]陈天华.数字图像处理[M].北京：清华大学出版社,2007.
[43]卫保国.一种改进的自适应中值滤波方法.计算机应用.2008,28(7)：1732-1734.
[44]李久芳.基于二值化的边缘图像滤波方法.电子工业专用设备.2010,181：25-27.
[45]孙光灵,周庆松,方传刚.基于最小类内方差的快速闽值分割算法.安徽理工大学学报(自然科学版).2005,25(1)：39-42.
[46]张津,万振凯.基于数学形态学的图像二值化算法.仪器仪表用户.2008,15(2)：80-81.
[47]徐艳蕾,赵继印,焦玉斌.噪声图像边缘检测方法的研究[J].计算机应用研究.2009,26(1)：387-389.
[48]周晓明,马秋禾,肖蓉.基于Canny算子的改进的图像边缘检测方法[J].影像技术,2008,20(4)：17-20.
[49]薛丽霞,李涛,王佐成.一种自适应的Canny边缘检测算法.计算机应用研究.2010,27(9)：3588-3590.
[50]于起峰,陆宏伟,刘肖琳.基于图像的精密测量与运动测量[M].北京：科学出版社,2002.
[51]查英,刘铁根,杜东.图像识别技术在零件装配自动识别中的应用.Computer Engineering.2006,32(10):178-185.
[52]CHEN Y H. Determining parting direction based on minimum bounding box and fuzzy logics. Int. J. Mach. Tools Manufact.1997,37(9):1189-1199.
[53]张雷涛,胡玉霞,曹秀鸽.注塑件最小包围矩形算法的研究.甘肃高师学报.2005,10(2)：16-18.
[54]孔兵,王昭,谭玉山.基于圆拟合的激光光斑中心检测算法.红外与激光工程.2002,31(3)：275-279.
[55]张起贵,张魁.基于最小二乘直线拟合的小目标检测.电子设计工程.2010,18(7)：176-180.
[56]孙东卫,朱程辉.基于Radon变换的倾斜车牌图像角度检测与校正.微计算机应用.2008,29(2)：18-21.
[57]刘瑞祯,于仕琪.OpenCV教程--基础篇.北京航空航天大学出版社,2007.
[58]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述[J].自动化学报,2000,26(1)：43-55.
[59]刘国瑛,薛月菊,邹湘军.基于图像残差的摄像机标定精度比较.农机化研究.2010,10：118-121.
[60]郑国威,高满屯,董巧英.基于平面镜的摄像机内参数线性标定方法.计算机工程与应用.2006,28：86-88.
[61]艾丽敏,郑平,杨忠根.两种多视图线性摄像机自标定算法研究.信息技术.2010,8：105-111.
[62]姚德馨.基于构件的多层复用工控软件研究[D].合肥：合肥工业大学,2006.
[2]张德荣.科研产品的装配工艺及工艺管理.机电设备.2007,(7)：1-3.
[3]包丽雅.微装配技术及其在引信中的应用.黑龙江科技信息.2008,31：27.
[4]席文明,吴洪涛,朱剑英.微装配技术的发展现状.机械科学与技术.2002,11(21)：861-865.
[5]Song Yu, Li Mantian, Sun Lining, et al. Global Visual Servoing of Miniature Mobile Robot inside a Micro-Assembly Station. Proceedings of the IEEE International Conference on Mechatronics & Automation.2005:1586-1591.
[6]Wang Lin, Wang Xiaodong, Zhang Xiwen.Micro-stress assembly of fragile miniature parts. The second International Conference of CSMNT.2010.
[7]廖万辉,李琳.基于机器视觉的工业机器人定位系统.机器人技术.2009,25(32)：242-244.
[8]GRACIAS. D. H, TIEN. J, BREEN T. L. Forming electrical network in three dimensions by self-assembly. Science.2000,289(18):1170-1172.
[9]贾云得.机器视觉[M].北京：科学出版社,2000.
[10]SNYDER W E, QI H R. Machine Vision[M]. Landon:Cambridge University Press,2005.
[11]L.Roberts. Machine perception of three-dimensional solidsIn:Tippertt J. Optical and Electron-Optical Information Processing. Cambridge, MA:MIT Press.1965,159-197.
[12]D. Marr. Vision[M].W.H. Freeman and Company,1982.
[13]D G Lowe. Three-dimensional object recognition from single two-dimensional images, AI.1987,37:355-395.
[14]J Aloimonos,I Weiss, A Bandopadhay. Active vision, IJCV.1988,1:333-356.
[15]王力.基于机器视觉的贴片元件定位系统的研究与开发[D].苏州：苏州大学,2009.
[16]岳晓峰.计算机视觉技术及其在工业中应用的研究.吉林：吉林大学,2006.
[17]王崇涛.基于机器视觉的表面缺陷检测仪在冷轧生产的应用.河南冶金金.2007,15(9)：57-60.
[18]鲍官军,荀一,戚利勇.机器视觉在黄瓜采摘机器人中的应用研究.浙江工业大学学报.2010,38(1)：114-118.
[19]刘长红,徐杜,蒋永平.基于机器视觉的心脏医学图像处理研究.计算机与应用化学.2010,7(27)：997-1000.
[20]李超,李运华.基于机器视觉的高精度顶桥施工位姿测量系统.北京航空航天大学学报.2007,3(33)：322-326.
[21]王丽英.需求带来市场-机器视觉迎来发展的春天[J].今日电子,2008,(6)：67.
[22]尹周平,熊有伦.微装配技术的研究进展及其展望.半导体技术.2004,29(5)：6-9.
[23]S. Fatikow, R. Munassypov, U. Rembold. Assembly Planning and Plan Decomposition in an Automated Microrobot-Based Microassembly Desktop Station. Journal of Intelligent Manufacturing(1998)9,73-92, Chapman & Hall, London.
[24]Stephen J. Ralis, Barmeshwar Vikramaditya, and Bradley J. Nelson. Micropositioning of a Weakly Calibrated Microassembly System Using Coarse-to-Fine Visual Servoing Strategies. IEEE Transactions on Electronics Packaging Manufacturing.2000,23(2):123-131.
[25]Driesen, W., Varidel, T., Mazerolle,S.,et al. Flexible micromanipulation platform based on tethered cm3-sized mobile micro robots[C],IEEE International Conference on Robotics and Biomimetics, Hong Kong,2005:145-150.
[26]GIOUROUDI I, HOTZENDORFER H, KOSEL J, et al. Development of a microgripping system for handling of microcomponents[J]. Precision Engineering,2008, (32):148-152.
[27]SONG Y, LI M T, SUN L N, et al. Global Visual Servo of Miniature Mobile Robot inside a Micro-Assembly Station[C]. Proceedings of the IEEE International Conference on Mechatronics & Automation,2005:1586-1591.
[28]刘超.基于机器视觉的微小型零件自动测量与装配.大连：大连理工大学,2009.
[29]段瑞玲,段惠波,李庆祥.基于图像处理的微装配自动调焦系统.光学精密工程.2006,6(14)：468-472.
[30]张建忠.孔-轴装配机器人视觉制导关键技术研究[D].南京：东南大学,2005.
[31]刘景泰,吴水华,孙雷.基于视觉的遥操作机器人精密装配系统.机器人.2005,3(27)：178-182
[32]黄桂平,李云,王保丰,etal.单目视觉测量技术研究.计量学报.2004,25(4)：314-317.
[33]周婷.基于OpenCV的移动靶面图像识别算法研究[D].大连：大连海事大学,2008.
[34]丁哲.机器视觉硬件选型基础[EB/OL]. http://www.visiondragon.com,2007.
[35]吴淑梅,霍彦明.LED光源的应用及前景[J].灯与照明,2008,32(3)：24-26.
[36]席文明,姚斌.微装配与微操作[M].北京：国防工业出版社,2006.
[37]王晓东,宋洪侠,J. HESSELBACH.德国微装配技术研究的几个方向[J].机械制造,2002,(09)：13-15.
[38]张毓晋.图像处理与分析.北京：清华大学出版社,1999.
[39]王朝晖.基于计算机视觉反馈微装配系统及其关键技术研究[D].西安：西安交通大学,2002.
[40]SONKA M,HLAVAC V,BOYLE R.图像处理、分析与机器视觉[M].北京：人民邮电出版社,2003.09.
[41]贾永红.数字图像处理[M].武汉：武汉大学出版社,2003.
[42]陈天华.数字图像处理[M].北京：清华大学出版社,2007.
[43]卫保国.一种改进的自适应中值滤波方法.计算机应用.2008,28(7)：1732-1734.
[44]李久芳.基于二值化的边缘图像滤波方法.电子工业专用设备.2010,181：25-27.
[45]孙光灵,周庆松,方传刚.基于最小类内方差的快速闽值分割算法.安徽理工大学学报(自然科学版).2005,25(1)：39-42.
[46]张津,万振凯.基于数学形态学的图像二值化算法.仪器仪表用户.2008,15(2)：80-81.
[47]徐艳蕾,赵继印,焦玉斌.噪声图像边缘检测方法的研究[J].计算机应用研究.2009,26(1)：387-389.
[48]周晓明,马秋禾,肖蓉.基于Canny算子的改进的图像边缘检测方法[J].影像技术,2008,20(4)：17-20.
[49]薛丽霞,李涛,王佐成.一种自适应的Canny边缘检测算法.计算机应用研究.2010,27(9)：3588-3590.
[50]于起峰,陆宏伟,刘肖琳.基于图像的精密测量与运动测量[M].北京：科学出版社,2002.
[51]查英,刘铁根,杜东.图像识别技术在零件装配自动识别中的应用.Computer Engineering.2006,32(10):178-185.
[52]CHEN Y H. Determining parting direction based on minimum bounding box and fuzzy logics. Int. J. Mach. Tools Manufact.1997,37(9):1189-1199.
[53]张雷涛,胡玉霞,曹秀鸽.注塑件最小包围矩形算法的研究.甘肃高师学报.2005,10(2)：16-18.
[54]孔兵,王昭,谭玉山.基于圆拟合的激光光斑中心检测算法.红外与激光工程.2002,31(3)：275-279.
[55]张起贵,张魁.基于最小二乘直线拟合的小目标检测.电子设计工程.2010,18(7)：176-180.
[56]孙东卫,朱程辉.基于Radon变换的倾斜车牌图像角度检测与校正.微计算机应用.2008,29(2)：18-21.
[57]刘瑞祯,于仕琪.OpenCV教程--基础篇.北京航空航天大学出版社,2007.
[58]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述[J].自动化学报,2000,26(1)：43-55.
[59]刘国瑛,薛月菊,邹湘军.基于图像残差的摄像机标定精度比较.农机化研究.2010,10：118-121.
[60]郑国威,高满屯,董巧英.基于平面镜的摄像机内参数线性标定方法.计算机工程与应用.2006,28：86-88.
[61]艾丽敏,郑平,杨忠根.两种多视图线性摄像机自标定算法研究.信息技术.2010,8：105-111.
[62]姚德馨.基于构件的多层复用工控软件研究[D].合肥：合肥工业大学,2006.