基于数字图像处理技术的接杆激光环焊焊缝视觉检测系统研究
|
摘要
联合汽车电子有限公司无锡厂现有汽车喷油嘴生产线的接杆激光环焊激光环焊焊缝可能存在焊缝不完整、表面凹痕、表面突起、表面飞溅等焊接缺陷,采用传统的涡流检测效果不理想,漏检率较高,为避免产品的品质隐患,现由操作工人利用放大镜进行检测,但是这难以完全避免人为误差,而且一定程度上降低了生产效率。
本研究利用现有工位工件的旋转功能,采用线阵CCD传感器配以辅助光源获取焊缝表面特征信息,通过去除焊缝背景、图像去噪、图像增强等方法对目标图像进行预处理,再结合改进的Otsu算法进行有效的图像分割,进而通过统计和比较判别,判断接杆焊缝是否合格。本研究中以中值滤波和图像增强为主要内容的焊缝图像预处理,有效地克服了亮度差异对图像识别带来的不良影响;分析比较基于区域图像分割算法(传统的Otsu和改进的Otsu方法)和基于边缘的图像分割算法(一次微分和二次微分)对焊缝图像分割得到的效果,发现基于边缘的分割算法不适用于本研究中焊缝的情况。而改进的Otsu法充分考虑了实际激光环焊焊缝图像的特征,即目标与背景分布有交叉的特点,相对于一般的Otsu法,具有分割准确且计算量相当的特点,是一种非常实用且有效的图像阈值分割方法。
通过这种实时图像处理软件完成焊缝完整性和焊缝表面缺陷的判别,完成检测系统和现有生产线的信息交流,极大地提高了处理效率,满足现有生产线的既有生产节拍。试验证明,该视觉检测系统Ⅰ类误判率(合格产品判为不合格产品)低于0.5%,Ⅱ类误判率(不合格产品判为合格产品)低于0.01%,在节约时间的基础上,本系统解决了传统的涡流检测精度不高的问题,建立起了针对工业生产中的基于机器视觉技术的激光环焊焊缝视觉检测系统。从采集图像到图像处理结束,把结果反馈到执行控制模块所用的时间有效控制在1.5秒之内,符合工业生产物流要求。
There are surface welding defects such as incomplete welding、surface hollow、surface heave and welding spatter in the inlet tube of laser welding in the Auto-mobile oil injection nozzle production line. The traditional eddy current testing results are not so ideal, the misjudging rate is relatively high. In order to avoid misjudging, workers will have a second time check, but such kind of operation can neither ensure the product quality nor decrease the production efficiency.
In this study, we acquire welding image by using the existing rotation function、line CCD sensor and lamp-house. Image preprocessing including wiping off the background in the welding、image denoise and image enhancement. After Image preprocessing, we use the Improved Otsu arithmetic to realise image segmentation. Finally, we judge the welding quality through statistics and comparison. The median filtering and image enhancement are two main functions in image preprocessing that are used to solve the problem of unstable impact which results from line CCD sensor; After comparing the results of regional image segmentation algorithm (traditional Otsu and improved Otsu Methods) and marginal image segmentation algorithm, we find that marginal image segmentation algorithm does not apply to the image with complicated margin and uneven lighting. The objectives and background cross-distributed in the image, improved Otsu applied this situation successfully. It is one of the practical and effective image thresholding segmentation methods.
Through this on line image processing software, we will identify product quality and finish the existing production line information exchanges. Through improving judging efficiency and meeting existing production rhythms, we control the time of image acquisition and image processing within 1.5 second / piece.
本研究利用现有工位工件的旋转功能,采用线阵CCD传感器配以辅助光源获取焊缝表面特征信息,通过去除焊缝背景、图像去噪、图像增强等方法对目标图像进行预处理,再结合改进的Otsu算法进行有效的图像分割,进而通过统计和比较判别,判断接杆焊缝是否合格。本研究中以中值滤波和图像增强为主要内容的焊缝图像预处理,有效地克服了亮度差异对图像识别带来的不良影响;分析比较基于区域图像分割算法(传统的Otsu和改进的Otsu方法)和基于边缘的图像分割算法(一次微分和二次微分)对焊缝图像分割得到的效果,发现基于边缘的分割算法不适用于本研究中焊缝的情况。而改进的Otsu法充分考虑了实际激光环焊焊缝图像的特征,即目标与背景分布有交叉的特点,相对于一般的Otsu法,具有分割准确且计算量相当的特点,是一种非常实用且有效的图像阈值分割方法。
通过这种实时图像处理软件完成焊缝完整性和焊缝表面缺陷的判别,完成检测系统和现有生产线的信息交流,极大地提高了处理效率,满足现有生产线的既有生产节拍。试验证明,该视觉检测系统Ⅰ类误判率(合格产品判为不合格产品)低于0.5%,Ⅱ类误判率(不合格产品判为合格产品)低于0.01%,在节约时间的基础上,本系统解决了传统的涡流检测精度不高的问题,建立起了针对工业生产中的基于机器视觉技术的激光环焊焊缝视觉检测系统。从采集图像到图像处理结束,把结果反馈到执行控制模块所用的时间有效控制在1.5秒之内,符合工业生产物流要求。
There are surface welding defects such as incomplete welding、surface hollow、surface heave and welding spatter in the inlet tube of laser welding in the Auto-mobile oil injection nozzle production line. The traditional eddy current testing results are not so ideal, the misjudging rate is relatively high. In order to avoid misjudging, workers will have a second time check, but such kind of operation can neither ensure the product quality nor decrease the production efficiency.
In this study, we acquire welding image by using the existing rotation function、line CCD sensor and lamp-house. Image preprocessing including wiping off the background in the welding、image denoise and image enhancement. After Image preprocessing, we use the Improved Otsu arithmetic to realise image segmentation. Finally, we judge the welding quality through statistics and comparison. The median filtering and image enhancement are two main functions in image preprocessing that are used to solve the problem of unstable impact which results from line CCD sensor; After comparing the results of regional image segmentation algorithm (traditional Otsu and improved Otsu Methods) and marginal image segmentation algorithm, we find that marginal image segmentation algorithm does not apply to the image with complicated margin and uneven lighting. The objectives and background cross-distributed in the image, improved Otsu applied this situation successfully. It is one of the practical and effective image thresholding segmentation methods.
Through this on line image processing software, we will identify product quality and finish the existing production line information exchanges. Through improving judging efficiency and meeting existing production rhythms, we control the time of image acquisition and image processing within 1.5 second / piece.
引文
[1] 娄琳,崔琪,国产微型车电喷系统常见故障及分析,汽车维修技师,2007 年,45 期
[2] 王新成,高级图像处理技术[M],北京:中国科学技术出版社,2001
[3] 贾云得.机器视觉[M].北京:科学出版社,2000
[4] 吴立德.计算机视觉需要更扎实更艰苦的工作.模式识别与人工智能.1992,5(4):261～265
[5] 李介谷.在应用中成长着的计算机视觉.模式识别与人工智能.1992,5(4):266～271
[6] 边肇琪.计算机视觉要更好地面向应用.模式识别与人工智能.1992,5(4):272～275
[7] D.H.Ballade,C.M.Brown.Principles of Animate Vision.CVGIP Image Understanding. 1992,56(1):3～21
[8] 唐四春,袁保宗,计算机视觉研究进展与展望.通讯学报.1993,14(4):55～62
[9] 阮秋琦.图像处理和计算机视觉技术在美国.北方交通大学学报.1992,16(3):8～14
[10] B.G.Batchelor,D.W.Braggins.Commercial vision systems in computervision.Theory and Industrial Applications.1992,405～452
[11] A.K.Elshennawy.The role of inspection in automated manufacturing. Computer Industrial Engineering.1989,17(1-4):327～331
[12] Michael C.Fairhurst.Computer Vision for Robotic Systems: An Introduction.The University Press.Cambridge,1988
[13] Ulrich RemBold,Christian blume,Ruediger Dillmann,田雨华等.计算机集成制造技术和系统[M].北京:兵器工业出版社,1995
[14] A.Rosenfeld.Computer Vision—Basic Principle.Proceeding of IEEE.1988,8:863～868
[15] Batchilor,B.G.Automated visual inspection in industry.The Industrial Robot.l978,5:174～l76
[16] Franci Lahajnar et al.Machine vision system for inspecting electric plates.Computer in Industry.2002,47:113～122
[17] Wu Wen-yen,Wang Mao-Jiun,Liu Chi-Ming.Automated inspection of printed circuit boards through machine vision.Computer In Industry.1996,28:103～111
[18] 谢图强,谢铁邦,唐良晶,李柱.热冷带钢表面缺陷在线检测系统.计量技术.1994,12:3～5
[19] 谢图强,唐良晶,王菊香,李柱.板坯端部优化剪切系统.工业仪表与自动化装置.1995,2:54～56
[20] N.Aleixos,J.Blasco,F.Navarron,E.Molto.Multispectral inspection of citrus in real-time using machine vision and digital signal processors.Computers and Electronics in Agriculture.2002,33:121～137
[21] 应义斌,饶秀勤,赵匀,蒋亦元.机器视觉技术在农产品品质自动识别中的应用研究进展.农业工程学报.2000,16(3):4～7
[22] 冯斌,汪懋华.基于计算机视觉的水果大小检测方法.农业机械学报.2003,34(1):73～75
[23] 李庆中,汪娥华.农业生物模式识别中的计算机视觉技术.中国图像图形学报.1999,4(7):610～616
[24] 刘禾,汪懋华.苹果自动分级中的图像分割.中国农业大学学报.1996,1(6):89～93
[25] K.Nakano.Application of Neural Networks to the Color Grading of Apples Computers and Electronics in Agriculture.1997,18:105-116
[26] 赵学增,杨延竹,王伟杰,吴羡.计算机技术在苗木自动分级中的应用发展概况.林业科学.2004,40(3):162～166
[27] 张勇斌,王执泉.HT在玻管检测中的应用.工业计量.2003,1:43～45
[28] 陈元琰,姜颖军,王强.玻璃瓶口裂纹检测的简易判断法.广西师范大学学报(自然科学版).2001,19(3):19～21
[29] 张建荣,姜昱明.CCD 成像在线测量玻璃棒直径的方法研究.应用光学.2004,25(3):53～56
[30] 张红娜,王祁.图像测量技术及其应用.电测与仪表.2003,40(7):19～21
[31] 潘洪达,陈熔,苏建,詹东华.图像测量技术在汽车轴距差检测中的应用研究.中国公路学报.2003,16(2):112～114
[32] Manbir S,Sodhi and KHALIL.Surface roughness monitoring using computer vision.Machine Tools Manufacture.1995,36(7):817～828
[33] Franci Lahajnar et al.Machine vision system for inspecting electric plates.Computer in Industry.2002,47:113～122
[34] L.Angrisani,P.Daponte,A.Pietrosanto,C.Liguori.An image-based measurement system for the characterisation of automotive gaskets. Measurement 1999,25:169～181
[35] TIMOTHYS.NEWAN and ANILK.JAIN.A system for 3d cad-based inspection using range images.Pattern Recognition.1995,28(10):1555～1574
[36] Schmidberger,E.J.and Ahlers,R.J.Quality control with a robot-guided electro-optical sensor.Ibid:27～36
[37] C.SANBY,L.NORTON-WAYNE and R.HARWOOD.The automated inspection of lace using machine vision.Mechatronics.1995,5(2/3):215～23
[38] 马强,唐文彦,陈金存,王庆.自由环状零件尺寸图像测量系统研究.航天制造技术.2004,1:27～31
[39] 高向东,严向文,杨雪荣,陈章兰.新型轮对参数自动测量装置.中国铁路.2004,8:33～34
[40] 卞晓东,张为公,郭占军.利用视觉伺服技术进行车辆尺寸测量的方法.汽车工程.2004,26(3):341～344
[41] 杨丽凤,韩冀皖,李元宗.面阵高精度测量技术的应用.太原理工大学学报.2001,32(5):455～458
[42] 刘兴占,巩马理,李伦.CCD 扫描法检测模具表面缺陷的研究.光学技术.2000,26(4):337～338
[43] 邢希东,王淑君,韩进宏,王好臣,杨文彩.建筑装饰材料尺寸偏差的计算机视觉检测系统.成组技术与生产现代化.2000,19(2):49～51
[44] 吕文阁,刘建群等,应用机器视觉的工件表面质量检测,机床与液压,2006,vol.14
[45] 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
[46] Chin T.R,Harlow C.A.Automated visual inspection:A Survey,IEEE Trans.on Pattern Analysis and Machine Intelligence.1982,PAMI-4:557～573.
[47] 段峰,王耀南,雷晓峰等,机器视觉技术及其应用综述[J]. 自动化博览,2002,(3):59-62
[48] 王其隆.弧焊过程质量实时传感与控制[M].北京:机械工业出版社,2000
[49] 叶佳.中文 Visual Basic 6.0 编程实用指南[M].北京:中国水利出版社,1999
[50] 王敏 电阻焊在汽车工业中的应用[J] 电焊机 2003.33(1):1-6
[51] 周昀,蒋金鹏,颜国正,楼松年,焊缝的主动红外线成像检测技术,电焊机,2004(4),49-51
[52] 黄凤岗,宋克欧. 模式识别. 哈尔滨:哈尔滨工程大学出版社,1998
[53] 王伟;王承训. 焊接缺陷自动识别系统的研究和应用. 焊接学报,1992,13(1):45~50
[54] 李月景. 图像识别技术及其应用. 北京:机械工业出版社,1985
[55] 夏正良,数字图像处理,东南大学出版社,1999.
[56] Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing, Second Edition.北京:电子工业出版社. 2004:94-97.
[57] Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing, Second Edition.北京:电子工业出版社. 2004:117-169.
[58] 钟玉琢,乔秉新,李树青.机器人视觉技术[M].北京:国防工业出版社,1994
[2] 王新成,高级图像处理技术[M],北京:中国科学技术出版社,2001
[3] 贾云得.机器视觉[M].北京:科学出版社,2000
[4] 吴立德.计算机视觉需要更扎实更艰苦的工作.模式识别与人工智能.1992,5(4):261～265
[5] 李介谷.在应用中成长着的计算机视觉.模式识别与人工智能.1992,5(4):266～271
[6] 边肇琪.计算机视觉要更好地面向应用.模式识别与人工智能.1992,5(4):272～275
[7] D.H.Ballade,C.M.Brown.Principles of Animate Vision.CVGIP Image Understanding. 1992,56(1):3～21
[8] 唐四春,袁保宗,计算机视觉研究进展与展望.通讯学报.1993,14(4):55～62
[9] 阮秋琦.图像处理和计算机视觉技术在美国.北方交通大学学报.1992,16(3):8～14
[10] B.G.Batchelor,D.W.Braggins.Commercial vision systems in computervision.Theory and Industrial Applications.1992,405～452
[11] A.K.Elshennawy.The role of inspection in automated manufacturing. Computer Industrial Engineering.1989,17(1-4):327～331
[12] Michael C.Fairhurst.Computer Vision for Robotic Systems: An Introduction.The University Press.Cambridge,1988
[13] Ulrich RemBold,Christian blume,Ruediger Dillmann,田雨华等.计算机集成制造技术和系统[M].北京:兵器工业出版社,1995
[14] A.Rosenfeld.Computer Vision—Basic Principle.Proceeding of IEEE.1988,8:863～868
[15] Batchilor,B.G.Automated visual inspection in industry.The Industrial Robot.l978,5:174～l76
[16] Franci Lahajnar et al.Machine vision system for inspecting electric plates.Computer in Industry.2002,47:113～122
[17] Wu Wen-yen,Wang Mao-Jiun,Liu Chi-Ming.Automated inspection of printed circuit boards through machine vision.Computer In Industry.1996,28:103～111
[18] 谢图强,谢铁邦,唐良晶,李柱.热冷带钢表面缺陷在线检测系统.计量技术.1994,12:3～5
[19] 谢图强,唐良晶,王菊香,李柱.板坯端部优化剪切系统.工业仪表与自动化装置.1995,2:54～56
[20] N.Aleixos,J.Blasco,F.Navarron,E.Molto.Multispectral inspection of citrus in real-time using machine vision and digital signal processors.Computers and Electronics in Agriculture.2002,33:121～137
[21] 应义斌,饶秀勤,赵匀,蒋亦元.机器视觉技术在农产品品质自动识别中的应用研究进展.农业工程学报.2000,16(3):4～7
[22] 冯斌,汪懋华.基于计算机视觉的水果大小检测方法.农业机械学报.2003,34(1):73～75
[23] 李庆中,汪娥华.农业生物模式识别中的计算机视觉技术.中国图像图形学报.1999,4(7):610～616
[24] 刘禾,汪懋华.苹果自动分级中的图像分割.中国农业大学学报.1996,1(6):89～93
[25] K.Nakano.Application of Neural Networks to the Color Grading of Apples Computers and Electronics in Agriculture.1997,18:105-116
[26] 赵学增,杨延竹,王伟杰,吴羡.计算机技术在苗木自动分级中的应用发展概况.林业科学.2004,40(3):162～166
[27] 张勇斌,王执泉.HT在玻管检测中的应用.工业计量.2003,1:43～45
[28] 陈元琰,姜颖军,王强.玻璃瓶口裂纹检测的简易判断法.广西师范大学学报(自然科学版).2001,19(3):19～21
[29] 张建荣,姜昱明.CCD 成像在线测量玻璃棒直径的方法研究.应用光学.2004,25(3):53～56
[30] 张红娜,王祁.图像测量技术及其应用.电测与仪表.2003,40(7):19～21
[31] 潘洪达,陈熔,苏建,詹东华.图像测量技术在汽车轴距差检测中的应用研究.中国公路学报.2003,16(2):112～114
[32] Manbir S,Sodhi and KHALIL.Surface roughness monitoring using computer vision.Machine Tools Manufacture.1995,36(7):817～828
[33] Franci Lahajnar et al.Machine vision system for inspecting electric plates.Computer in Industry.2002,47:113～122
[34] L.Angrisani,P.Daponte,A.Pietrosanto,C.Liguori.An image-based measurement system for the characterisation of automotive gaskets. Measurement 1999,25:169～181
[35] TIMOTHYS.NEWAN and ANILK.JAIN.A system for 3d cad-based inspection using range images.Pattern Recognition.1995,28(10):1555～1574
[36] Schmidberger,E.J.and Ahlers,R.J.Quality control with a robot-guided electro-optical sensor.Ibid:27～36
[37] C.SANBY,L.NORTON-WAYNE and R.HARWOOD.The automated inspection of lace using machine vision.Mechatronics.1995,5(2/3):215～23
[38] 马强,唐文彦,陈金存,王庆.自由环状零件尺寸图像测量系统研究.航天制造技术.2004,1:27～31
[39] 高向东,严向文,杨雪荣,陈章兰.新型轮对参数自动测量装置.中国铁路.2004,8:33～34
[40] 卞晓东,张为公,郭占军.利用视觉伺服技术进行车辆尺寸测量的方法.汽车工程.2004,26(3):341～344
[41] 杨丽凤,韩冀皖,李元宗.面阵高精度测量技术的应用.太原理工大学学报.2001,32(5):455～458
[42] 刘兴占,巩马理,李伦.CCD 扫描法检测模具表面缺陷的研究.光学技术.2000,26(4):337～338
[43] 邢希东,王淑君,韩进宏,王好臣,杨文彩.建筑装饰材料尺寸偏差的计算机视觉检测系统.成组技术与生产现代化.2000,19(2):49～51
[44] 吕文阁,刘建群等,应用机器视觉的工件表面质量检测,机床与液压,2006,vol.14
[45] 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
[46] Chin T.R,Harlow C.A.Automated visual inspection:A Survey,IEEE Trans.on Pattern Analysis and Machine Intelligence.1982,PAMI-4:557～573.
[47] 段峰,王耀南,雷晓峰等,机器视觉技术及其应用综述[J]. 自动化博览,2002,(3):59-62
[48] 王其隆.弧焊过程质量实时传感与控制[M].北京:机械工业出版社,2000
[49] 叶佳.中文 Visual Basic 6.0 编程实用指南[M].北京:中国水利出版社,1999
[50] 王敏 电阻焊在汽车工业中的应用[J] 电焊机 2003.33(1):1-6
[51] 周昀,蒋金鹏,颜国正,楼松年,焊缝的主动红外线成像检测技术,电焊机,2004(4),49-51
[52] 黄凤岗,宋克欧. 模式识别. 哈尔滨:哈尔滨工程大学出版社,1998
[53] 王伟;王承训. 焊接缺陷自动识别系统的研究和应用. 焊接学报,1992,13(1):45~50
[54] 李月景. 图像识别技术及其应用. 北京:机械工业出版社,1985
[55] 夏正良,数字图像处理,东南大学出版社,1999.
[56] Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing, Second Edition.北京:电子工业出版社. 2004:94-97.
[57] Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing, Second Edition.北京:电子工业出版社. 2004:117-169.
[58] 钟玉琢,乔秉新,李树青.机器人视觉技术[M].北京:国防工业出版社,1994