基于机器视觉的管道焊接跟踪技术研究
|
摘要
针对爬行焊接机器人在管道自动焊接中对典型的V形坡口焊缝的定位与中心线的提取,设计了一种基于激光视觉检测的自动焊缝跟踪系统。提出了一种基于激光条纹图像特征的两步定位方法:第一步,建立模板匹配,利用模板匹配方式获取激光条纹位置区域;第二步,采用阈值分割和中心法提取激光条纹中心线,然后采用Shi-Tomasi算法对中心线进行角点检测,经过拟合直线求交点和逐列扫描对比得到焊缝坡口的4个拐点信息,并确定焊缝中心。通过对实际的焊接过程进行测试,结果表明:跟踪系统的平均纠偏误差在2像素以内,平均处理纠偏时间在120 ms以内,具有较高的精度和实时性。
Aiming at the positioning and centerline of typical V-groove welds in the automatic welding of the crawler welding robot,an automatic welding seam tracking system based on laser vision detection was designed.A two-step positioning method based on the characteristics of laser fringe image was presented.The first step is to establish template matching and use template matching to obtain the laser stripe location.Secondly,the center line of laser stripe was extracted by threshold segmentation algorithm and center value method.Then the Shi-Tomasi algorithm was used to detect the corner points of the center line,and the four inflection points of the weld groove were obtained by fitting the straight line intersection and contrast by scanning column,then the weld center was determined.Through testing the process of real welding tracking,the results show that the average error correction error of the tracking system was within 2 pixels and the average processing time was within 120 ms,which has high accuracy and instantaneity.
Aiming at the positioning and centerline of typical V-groove welds in the automatic welding of the crawler welding robot,an automatic welding seam tracking system based on laser vision detection was designed.A two-step positioning method based on the characteristics of laser fringe image was presented.The first step is to establish template matching and use template matching to obtain the laser stripe location.Secondly,the center line of laser stripe was extracted by threshold segmentation algorithm and center value method.Then the Shi-Tomasi algorithm was used to detect the corner points of the center line,and the four inflection points of the weld groove were obtained by fitting the straight line intersection and contrast by scanning column,then the weld center was determined.Through testing the process of real welding tracking,the results show that the average error correction error of the tracking system was within 2 pixels and the average processing time was within 120 ms,which has high accuracy and instantaneity.
引文
[1] XU Y L,LV N,FANG G,et al.Welding Seam Tracking in Robotic Gas Metal Arc Welding[J].Journal of Materials Processing Technology,2017,248:18-30.
[2] 顾帆,陈华斌,何银水,等.基于激光视觉的多层多道焊接坡口特征点提取方法[J].上海交通大学学报,2016,50(S1):62-65.GU F,CHEN H B,HE Y S,et al.Method for Extracting Multi-Pass Welding Groove Feature Point Based on Laser Vision[J].Journal of Shanghai Jiaotong University,2016,50(S1):62-65.
[3] WEI H,RADOVAN K.Development of a Real-time Laser-based Machine Vision System to Monitor and Control Welding Processes[J].International Journal of Advanced Manufacturing Technology,2012,63(1/2/3/4):235-248.
[4] GU W P,XIONG Z Y,WAN W.Autonomous Seam Acquisition and Tracking System for Multi-pass Welding Based on Vision Sensor[J].International Journal of Advanced Manufacturing Technology,2013,69(1/2/3/4):451-460.
[5] XU Y L,YU H W,ZHONG J Y,et al.Real-time Seam Tracking Control Technology During Welding Robot GTAW Process Based on Passive Vision Sensor[J].Journal of Materials Processing Technology,2012,212(8):1654-1662.
[6] HE Y S,XU Y L,CHEN Y X,et al.Weld Seam Profile Detection and Feature Point Extraction for Multi-pass Route Planning Based on Visual Attention Model[J].Robotics and Computer-Integrated Manufacturing,2015,37:251-261.
[7] 于保军,曹晓燕.汽车传感器引脚焊接质量视觉检测系统研究[J].机床与液压,2011,39(21):46-49.YU B J,CAO X Y.Research on Vision Detection System Applied to the Pin Welding Quality of Automobile Sensor[J].Machine Tool & Hydraulics,2011,39(21):46-49.
[8] DINHAM M,FANG G.Autonomous Weld Seam Identification and Localisation Using Eye-in-hand Stereo Vision for Robotic Arc Welding[J].Robotics and Computer-Integrated Manufacturing,2013,29(5):288-301.
[9] 吴迪.不锈钢薄板TIG焊熔池图像处理及视觉特征计算[D].上海:上海交通大学,2010.
[10] ZHANG Y X,GAO X D.Analysis of Characteristics of Molten Pool Using Cast Shadow During High-power Disk Laser Welding[J].International Journal of Advanced Manufacturing Technology,2014,70(9/10/11/12):1978-1988.
[11] 杨雪君,许燕玲,黄色吉,等.一种基于结构光的V型坡口焊缝特征点识别算法[J].上海交通大学学报,2016,50(10):1573-1576.YANG X J,XU Y L,HUANG S J,et al.A Recognition Algorithm for Feature Points of V-Groove Wleds Based on Structured Light[J].Journal of Shanghai Jiaotong Univerity,2016,50(10):1573-1576.
[12] BROWN L G.A Survey of Image Registration Techniques[J].ACM Computing Surveys,1992,24(4):325-376.
[13] ZHU Z Y,LIN T,PIAO Y J,et al.Recognition of the Initial Position of Weld Based on the Image Pattern Match Technology for Welding Robot[J].International Journal of Advanced Manufacturing Technology,2005,26(7):784-788.
[14] RAVISANKAR A,VELAGA S K,RAJPUT G,et al.Influence of Welding Speed and Power on Residual Stress During Gas Tungsten Arc Welding(GTAW)of Thin Sections with Constant Heat Input:A Study Using Numerical Simulation and Experimental Validation[J].Journal of Manufacturing Processes,2014,16(2):200-211.
[2] 顾帆,陈华斌,何银水,等.基于激光视觉的多层多道焊接坡口特征点提取方法[J].上海交通大学学报,2016,50(S1):62-65.GU F,CHEN H B,HE Y S,et al.Method for Extracting Multi-Pass Welding Groove Feature Point Based on Laser Vision[J].Journal of Shanghai Jiaotong University,2016,50(S1):62-65.
[3] WEI H,RADOVAN K.Development of a Real-time Laser-based Machine Vision System to Monitor and Control Welding Processes[J].International Journal of Advanced Manufacturing Technology,2012,63(1/2/3/4):235-248.
[4] GU W P,XIONG Z Y,WAN W.Autonomous Seam Acquisition and Tracking System for Multi-pass Welding Based on Vision Sensor[J].International Journal of Advanced Manufacturing Technology,2013,69(1/2/3/4):451-460.
[5] XU Y L,YU H W,ZHONG J Y,et al.Real-time Seam Tracking Control Technology During Welding Robot GTAW Process Based on Passive Vision Sensor[J].Journal of Materials Processing Technology,2012,212(8):1654-1662.
[6] HE Y S,XU Y L,CHEN Y X,et al.Weld Seam Profile Detection and Feature Point Extraction for Multi-pass Route Planning Based on Visual Attention Model[J].Robotics and Computer-Integrated Manufacturing,2015,37:251-261.
[7] 于保军,曹晓燕.汽车传感器引脚焊接质量视觉检测系统研究[J].机床与液压,2011,39(21):46-49.YU B J,CAO X Y.Research on Vision Detection System Applied to the Pin Welding Quality of Automobile Sensor[J].Machine Tool & Hydraulics,2011,39(21):46-49.
[8] DINHAM M,FANG G.Autonomous Weld Seam Identification and Localisation Using Eye-in-hand Stereo Vision for Robotic Arc Welding[J].Robotics and Computer-Integrated Manufacturing,2013,29(5):288-301.
[9] 吴迪.不锈钢薄板TIG焊熔池图像处理及视觉特征计算[D].上海:上海交通大学,2010.
[10] ZHANG Y X,GAO X D.Analysis of Characteristics of Molten Pool Using Cast Shadow During High-power Disk Laser Welding[J].International Journal of Advanced Manufacturing Technology,2014,70(9/10/11/12):1978-1988.
[11] 杨雪君,许燕玲,黄色吉,等.一种基于结构光的V型坡口焊缝特征点识别算法[J].上海交通大学学报,2016,50(10):1573-1576.YANG X J,XU Y L,HUANG S J,et al.A Recognition Algorithm for Feature Points of V-Groove Wleds Based on Structured Light[J].Journal of Shanghai Jiaotong Univerity,2016,50(10):1573-1576.
[12] BROWN L G.A Survey of Image Registration Techniques[J].ACM Computing Surveys,1992,24(4):325-376.
[13] ZHU Z Y,LIN T,PIAO Y J,et al.Recognition of the Initial Position of Weld Based on the Image Pattern Match Technology for Welding Robot[J].International Journal of Advanced Manufacturing Technology,2005,26(7):784-788.
[14] RAVISANKAR A,VELAGA S K,RAJPUT G,et al.Influence of Welding Speed and Power on Residual Stress During Gas Tungsten Arc Welding(GTAW)of Thin Sections with Constant Heat Input:A Study Using Numerical Simulation and Experimental Validation[J].Journal of Manufacturing Processes,2014,16(2):200-211.