电弧焊焊缝偏差测量的视觉模型理论与试验研究
|
摘要
焊缝跟踪技术是自动电弧焊接的一个重要研究领域，实现精确的焊缝跟踪对于提高焊接质量具有非常重要的作用。而要实现精确的焊缝跟踪，焊缝偏差(即焊缝中心与电弧的偏差)检测技术是一个关键。目前国内外应用于自动焊接的传感器有许多种，其中机器视觉型传感器因其特有的优点成为最有应用前景的传感器。
视觉传感式焊缝跟踪的一般方法是利用CCD(Charge Couple Device)传感器实时获取焊接图像，再利用图像处理技术提取熔池中心与熔池前端的焊缝位置信息，两者之间的差值就反映了当前时刻电弧与焊缝的偏差情况。本论文不同于传统的通过图像处理技术来直接获取焊缝偏差信息，而是选取熔池图像处理区域(包括了熔池前端与熔池前端部份焊缝)，并将熔池图像质心作为分析焊缝偏差的特性参量，研究利用熔池特性参数来建立焊缝偏差测量视觉模型的新方法。
论文的研究基于一套焊缝跟踪实验系统，该系统主要包括CCD传感器、工作台、步进驱动与控制系统等装置。首先研究了焊前图像的焊缝识别技术，应用数学形态学较好地提取焊前图像的焊缝信息，为实现焊前示教型的焊缝跟踪提供依据。
其次，针对焊前示教型焊缝跟踪系统的不足，研究实现实时焊缝跟踪的新方法。进行了不同工艺条件下的焊接试验，分析熔池前端区域质心差值与焊缝偏差之间的关系，并应用一元线性回归分析建立了熔池图像质心差值与焊缝偏差之间的关系模型，并对该模型进行了显著性与通用性检验。
最后，进一步分析其它因素对焊缝偏差的影响，分析比较并抽取熔池图像的三个特性参数(熔池图像质心差值、质心位移、质心移动速度)作为输入变量，研究并应用神经网络建模技术建立了它们与焊缝偏差间的关系模型，对模型进行了精确性与通用性检验，该方法具有较好的理论与现实意义。
Seam tracking technology is one of the important research issues in the field of theautomation of arc welding process, and accurate seam tracking can improve the weld quality.The technology of seam deviation detection, which is the deviation between the seam center andthe arc, is one of the key to realize accurate seam tracking. Nowadays there are many sensorsapplied in weld automation, and the machine vision sensor has become the most prospectivesensor for its special advantage.
The traditional method of seam tracking based on machine vision is to catch weld imagereal time by CCD (Charge Couple Device) vision, and the information between the weld poolcenter and the seam has been acquired through image processing, whose dispersion reflects thedeviation between the arc and the seam at the moment. The thesis, which is different from thetraditional method getting the seam deviation information only by image processing, chooses aweld pool process region which includes the foreside of weld pool and the seam in front of thepool. Then the centroid of weld pool image is made as the characteristic parameter to analyze theseam deviation. And the new method is researched on how to set up the seam deviationmeasurement visual model by the pool characteristic parameters.
The thesis has been researched by a set of seam tracking experiment apparatus, whichincludes the CCD sensor, the working platform, and the step drive control system and so on.Firstly the thesis researches the seam recognition technology of welding images. And theposition of the seam has been acquired by the morphology, which can supply the bases to realizethe demonstration welding.
However, there are some disadvantages in the demonstration weld seam tracking system.So the thesis researches new methods to realize the real time seam tracking. Several experimentsunder different welding conditions have been undertaken in order to analyze the relation betweenthe centroid's dispersion of the process region and seam deviation. The relation model betweenthem has been set up using the linear regression analysis. And the model's salience andgenerality have been tested.
In order to analyze other factors' influence to seam deviation, the weld pool characteristic parameters, which are the dispersion of pool centroid, the centroid's displacement and thecentroid's speed, have been chosen as input data. And the visual model between the seamdeviation and weld pool characteristic parameters has been set up using the neural networktechnology. Finally, the visual measurement model's accuracy and generality have been tested,and the result shows that the method has the signification of the theory and the realism.
视觉传感式焊缝跟踪的一般方法是利用CCD(Charge Couple Device)传感器实时获取焊接图像，再利用图像处理技术提取熔池中心与熔池前端的焊缝位置信息，两者之间的差值就反映了当前时刻电弧与焊缝的偏差情况。本论文不同于传统的通过图像处理技术来直接获取焊缝偏差信息，而是选取熔池图像处理区域(包括了熔池前端与熔池前端部份焊缝)，并将熔池图像质心作为分析焊缝偏差的特性参量，研究利用熔池特性参数来建立焊缝偏差测量视觉模型的新方法。
论文的研究基于一套焊缝跟踪实验系统，该系统主要包括CCD传感器、工作台、步进驱动与控制系统等装置。首先研究了焊前图像的焊缝识别技术，应用数学形态学较好地提取焊前图像的焊缝信息，为实现焊前示教型的焊缝跟踪提供依据。
其次，针对焊前示教型焊缝跟踪系统的不足，研究实现实时焊缝跟踪的新方法。进行了不同工艺条件下的焊接试验，分析熔池前端区域质心差值与焊缝偏差之间的关系，并应用一元线性回归分析建立了熔池图像质心差值与焊缝偏差之间的关系模型，并对该模型进行了显著性与通用性检验。
最后，进一步分析其它因素对焊缝偏差的影响，分析比较并抽取熔池图像的三个特性参数(熔池图像质心差值、质心位移、质心移动速度)作为输入变量，研究并应用神经网络建模技术建立了它们与焊缝偏差间的关系模型，对模型进行了精确性与通用性检验，该方法具有较好的理论与现实意义。
Seam tracking technology is one of the important research issues in the field of theautomation of arc welding process, and accurate seam tracking can improve the weld quality.The technology of seam deviation detection, which is the deviation between the seam center andthe arc, is one of the key to realize accurate seam tracking. Nowadays there are many sensorsapplied in weld automation, and the machine vision sensor has become the most prospectivesensor for its special advantage.
The traditional method of seam tracking based on machine vision is to catch weld imagereal time by CCD (Charge Couple Device) vision, and the information between the weld poolcenter and the seam has been acquired through image processing, whose dispersion reflects thedeviation between the arc and the seam at the moment. The thesis, which is different from thetraditional method getting the seam deviation information only by image processing, chooses aweld pool process region which includes the foreside of weld pool and the seam in front of thepool. Then the centroid of weld pool image is made as the characteristic parameter to analyze theseam deviation. And the new method is researched on how to set up the seam deviationmeasurement visual model by the pool characteristic parameters.
The thesis has been researched by a set of seam tracking experiment apparatus, whichincludes the CCD sensor, the working platform, and the step drive control system and so on.Firstly the thesis researches the seam recognition technology of welding images. And theposition of the seam has been acquired by the morphology, which can supply the bases to realizethe demonstration welding.
However, there are some disadvantages in the demonstration weld seam tracking system.So the thesis researches new methods to realize the real time seam tracking. Several experimentsunder different welding conditions have been undertaken in order to analyze the relation betweenthe centroid's dispersion of the process region and seam deviation. The relation model betweenthem has been set up using the linear regression analysis. And the model's salience andgenerality have been tested.
In order to analyze other factors' influence to seam deviation, the weld pool characteristic parameters, which are the dispersion of pool centroid, the centroid's displacement and thecentroid's speed, have been chosen as input data. And the visual model between the seamdeviation and weld pool characteristic parameters has been set up using the neural networktechnology. Finally, the visual measurement model's accuracy and generality have been tested,and the result shows that the method has the signification of the theory and the realism.
引文
[1] 林尚扬，关桥．我国制造业焊接生产现状与发展战略研究[M]．北京：机械工业出版社，2003年．
[2] 吴林，陈善本．智能化焊接技术[M]．北京：国防工业出版社，2000．
[3] Yu Xue,I.S.Kim, J.S.Son, et al. Fuzzy regression method for prediction and control the bead width in the robotic arc-welding[J]. Journal of Material Process,2005(164):1134～1139.
[4] K.-Y.Bae, T.-H.Lee, K.-C.Ahn, et al. An optical sensing system for seam tracking and weld pool control in gas metal arc welding of steel pipe[J].Joumal of Material Processing Technology,2002(120):458～465.
[5] M.Vasudevan, B.P.C.Rao, B.Venkatraman, et al. Artificial neural network modeling for evaluating austenitic stainless steel and Zircaloy-2 welding[J]. Journal of Material Processing Technology,2005(169): 396～400.
[6] Cook, George E, Smartt, et al. Controlling robotic friction stir welding[J].Welding Journal,2003,82(6): 28～34.
[7] Adolfo Bauchspiecs, Sadek C.Absi Alfaro, Leszek A.Dobrzenski. Prediction sensor guided robotic manipulator in automated welding cells[J]. Journal of Material Processing Technology,2001 (109): 13～19.
[8] I.S.Kim, J.S.Son, C.E.Park, et al. A study on prediction of bead height in robotic arc welding using a neural network[J]. Journal of Material Processing Technology, 2002(130):229～234.
[9] 丁坤，于洽，丘华等．摆动跟踪传感器在全位置焊接中的应用[J]．焊接，2004(5)：29～31．
[10] 熊震宇，张华，潘际銮．电弧传感器的发展状况及应用前景[J]．焊接技术，2001，30(5)：2～5．
[11] 贾剑平，张华，徐健宁．电弧传感器的研究现状与展望[J]．焊接，2005(11)：14～18．
[12] 廖宝剑，吴世德，潘际銮．电弧传感器理论模型及信息处理[J]．焊接学报，1996，17(4)：263～270．
[13] 李顺华，胡绳荪．超生波传感器在焊缝跟踪中的应用[J]．焊接技术，2000，29(5)：33～34．
[14] 鲍加铭，胡绳荪，王玉龙．超声传感焊缝自动跟踪的研究[J]．焊接技术，2000，29(增 刊)：18～19．
[15] 胡绳荪，李顺华，孙栋等．CO_2焊接超声传感焊缝跟踪控制规则与参数[J]．焊接学报，2003，24(2)：22～26．
[16] 尹懿，洪波，张晨曙等．光电传感器式焊缝自动跟踪系统[J]．焊接学报，2006，27(9)：93～98．
[17] 李安强，洪波，屈岳波等．基于ACFM技术的焊缝跟踪传感器设计与实现[J]．电焊机，2006，36(10)：13～16．
[18] Kang-Yul Bae, Jin-Hyun Park. A study on development of inductive sensor for automatic weld seam tracking[J]. Journal of Materials Processing Technology, 2006, 176(3): 111～116.
[19] B-H You and J-W Kimo A study on an automatic seam tracking system by using an electromagnetic sensor for sheet metal arc welding of butt joints[J]. Journal of Engineering Manufacture, 2002,216(B6): 911～920.
[20] J-W Kim and J-H Shin. A study of a dual-electromagnetic sensor system for weld seam tracking of I-butt joints[J]. Journal of Engineering Manufacture, 2003, 217(9): 1305～1313.
[21] 王伟，邹奇仕，朱六妹等．视觉传感焊缝跟踪技术的发展状况及实施方案探讨[J]．电焊机，2002，32(5)：1～8．
[22] 李原，徐德，沈扬等．一种焊缝结构光图像处理与特征提取方法[J]．焊接学报，2006，27(9)：25～30．
[23] 刘明友，刘南生，郭昌荣等．V型焊缝的视觉图像传感图像处理研究[J]．电焊机，2006，36(10)：7～9．
[24] 刘明友，刘南生，郭昌荣等．搭接焊缝的视觉传感图像预处理及信息提取[J]．焊接，2006(3)：25～27．
[25] 崔元彪，闰志峰，管晓光等．焊缝跟踪图像处理系统研究[J]．哈尔滨理工大学学报，2006，11(4)：85～88．
[26] 熊震宇，姜建锋．弧焊机器人焊缝图像处理与识别方法的研究[J]．焊接技术，2006，35(3)：8～10．
[27] 杜玉红，李亮玉，李晓青等．基于结构光三维视觉焊缝跟踪系统的研究[J]．天津工业大学学报，2006，25(2)：68～70．
[28] 刘明友，刘南生，郭昌荣等．基于结构光视觉传感的V形焊缝信息提取[J]．焊接技术，2006，35(5)：20～21．
[29] 朱六妹，杨先林，王伟等．基于主动光视觉法的实时焊缝跟踪控制系统的研究[J]．电焊机，2006，36(10)：1～6．
[30] 张虓，马兆瑞，郑军等．结构光视觉焊缝跟踪传感器光学系统的研究[J]．电焊机，2006，36(5)：22～26．
[31] 谢志孟，高向东．基于视觉传感的焊缝跟踪技术研究和展望[J]．焊接，2005(4)：5～9．
[32] 薛家祥，贾林，李海宝．基于M带小波变换的焊接熔池图像边缘检测[J]．焊接学报，2004，15(13)：1144～1146．
[33] 朱若磊，黄石生，张红兵．基于分形理论的焊缝信息提取[J]．华南理工大学学报，2004，32(6)：1～4．
[34] 刘国平，王洪亮，胡荣华等．模板匹配技术在焊缝图像处理中的应用[J]．焊接技术，2004，33(4)：14～15．
[35] Zh.Y Zhu, T. Lin, Y.J. Piao, et al. Recognition of the initial position of weld based on the image pattern match technology for welding robot[J]. International Journal of Advance Manufacturing Technology,2005,26(8):784～788.
[36] Hong Luo, Xiaoqi Chen. Laser visual sensing for seam tracking in robotic arc welding of titanium alloys[J]. International Journal of Advance Manufacturing Technology,2005,26(10): 1012～1017.
[37] 刘超英，黄石生．数学形态学在自动焊接过程熔池图像识别中的应用[J]．内蒙古大学学报，2005，36(6)：689～692．
[38] 降雨志，张义顺，张华军等．投影法和差影法在焊缝跟踪图像识别中的应用[J]．沈阳工业大学学报，2005，27(5)：558～561．
[39] 谷春艳，张立斌，胡宝坚等．图像处理技术在C02焊自动跟踪中的应用[J]．焊接学报，2004，25(4)：70～72．
[40] Pi-Cheng Tung, Ming-Chang Wu, Yean-Ren Hwang. An image-guided mobile robotic welding system for SMAW repair processes[J]. International Journal of Machine tool and Manufacture, 2004,44(11): 1223～1233.
[41] Jeng-Ywan Jeng, Tzuoh-Fei Mau and Shyeu-Ming Leu. Computer integrated vision and neural network technologies for intelligent automatic laser butt joint welding[J]. Computer Integrated Manufacture, 2000, 13(4): 345～357.
[42] Hsing-Chia Kuo, Li-Jen Wu. An image tracking system for welded seams using fuzzy logic [J]. Journal of Materials Processing Technology,2002,120(2): 169～185.
[43] M Labudovic, D Hu and R Kovacevic. Three-dimensional finite element modeling of laser modification[J]. Journal of Engineering Manufacturing,2000,214(8):683～692.
[44] 谢志孟，高向东．基于Canny算子的焊缝图像边缘检测技术[J]．焊接学报，2006，27(1)：29～36．
[45] 朱若磊．基于焊缝中心的焊缝信息的直接提取[J]．机床与液压，2006(4)：22～23．
[46] J. Y. Jeng, T. F. Mau and S. M. Leu. Gap Inspection and Alignment Using a Vision Technique for Laser Butt Joint Welding[J]. International Journal of Advance Manufacturing Technology, 2000,16(3): 212～216.
[47] Jingguo Ge, Zhengqiang Zhu, Defu He, et al. A vision-based algorithm for seam detection in a PAW process for large-diameter stainless steel pipes[J]. International Journal of Advance Manufacturing Technology, 2005,26(10): 1006～1011.
[48] S. B. Chen, X. Z. Chen and T. Qiu. Acquisition of Weld Seam Dimensional Position Information for Arc Welding Robot Based on Vision Computing[J]. Journal of Intelligent and Robotic Systems, 2005(43): 77～97.
[49] Xiangdong Gao, Suck Joo Na. Detection of Weld Position Based on Kalman Filtering of Weld Pool Images[J]. Journal of Information and Computational Science,2005,2(1): 13～18.
[50] 李弼程，彭天强，彭波等．智能图像处理技术[M]．北京：电子工业出版社，2004．
[51] 闫志鸿，张广军，邱美珍等．脉冲熔化极气体保护焊熔池图像的检测与处理[J]．焊接学报，2005，26(2)：37～40．
[52] 高向东，罗锡柱．一种基于图像质心的焊缝跟踪新方法[J]．焊接学报，2003，24(6)：15～18．
[53] 王武义，徐定杰，陈健翼．误差原理与数据处理[M]．哈尔滨：哈尔滨工业大学出版社，2001．
[54] 朱大奇，史慧．人工神经网络原理及应用[M]．北京：科学出版社，2006．
[55] 高隽．人工神经网络原理及仿真实例[M]．北京：机械工业出版社，2003．
[56] Martin T．Hagan，Howard B．Demuth，Mark Beale．Neural Network Design[M]．北京：机械工业出版社，2002．
[2] 吴林，陈善本．智能化焊接技术[M]．北京：国防工业出版社，2000．
[3] Yu Xue,I.S.Kim, J.S.Son, et al. Fuzzy regression method for prediction and control the bead width in the robotic arc-welding[J]. Journal of Material Process,2005(164):1134～1139.
[4] K.-Y.Bae, T.-H.Lee, K.-C.Ahn, et al. An optical sensing system for seam tracking and weld pool control in gas metal arc welding of steel pipe[J].Joumal of Material Processing Technology,2002(120):458～465.
[5] M.Vasudevan, B.P.C.Rao, B.Venkatraman, et al. Artificial neural network modeling for evaluating austenitic stainless steel and Zircaloy-2 welding[J]. Journal of Material Processing Technology,2005(169): 396～400.
[6] Cook, George E, Smartt, et al. Controlling robotic friction stir welding[J].Welding Journal,2003,82(6): 28～34.
[7] Adolfo Bauchspiecs, Sadek C.Absi Alfaro, Leszek A.Dobrzenski. Prediction sensor guided robotic manipulator in automated welding cells[J]. Journal of Material Processing Technology,2001 (109): 13～19.
[8] I.S.Kim, J.S.Son, C.E.Park, et al. A study on prediction of bead height in robotic arc welding using a neural network[J]. Journal of Material Processing Technology, 2002(130):229～234.
[9] 丁坤，于洽，丘华等．摆动跟踪传感器在全位置焊接中的应用[J]．焊接，2004(5)：29～31．
[10] 熊震宇，张华，潘际銮．电弧传感器的发展状况及应用前景[J]．焊接技术，2001，30(5)：2～5．
[11] 贾剑平，张华，徐健宁．电弧传感器的研究现状与展望[J]．焊接，2005(11)：14～18．
[12] 廖宝剑，吴世德，潘际銮．电弧传感器理论模型及信息处理[J]．焊接学报，1996，17(4)：263～270．
[13] 李顺华，胡绳荪．超生波传感器在焊缝跟踪中的应用[J]．焊接技术，2000，29(5)：33～34．
[14] 鲍加铭，胡绳荪，王玉龙．超声传感焊缝自动跟踪的研究[J]．焊接技术，2000，29(增 刊)：18～19．
[15] 胡绳荪，李顺华，孙栋等．CO_2焊接超声传感焊缝跟踪控制规则与参数[J]．焊接学报，2003，24(2)：22～26．
[16] 尹懿，洪波，张晨曙等．光电传感器式焊缝自动跟踪系统[J]．焊接学报，2006，27(9)：93～98．
[17] 李安强，洪波，屈岳波等．基于ACFM技术的焊缝跟踪传感器设计与实现[J]．电焊机，2006，36(10)：13～16．
[18] Kang-Yul Bae, Jin-Hyun Park. A study on development of inductive sensor for automatic weld seam tracking[J]. Journal of Materials Processing Technology, 2006, 176(3): 111～116.
[19] B-H You and J-W Kimo A study on an automatic seam tracking system by using an electromagnetic sensor for sheet metal arc welding of butt joints[J]. Journal of Engineering Manufacture, 2002,216(B6): 911～920.
[20] J-W Kim and J-H Shin. A study of a dual-electromagnetic sensor system for weld seam tracking of I-butt joints[J]. Journal of Engineering Manufacture, 2003, 217(9): 1305～1313.
[21] 王伟，邹奇仕，朱六妹等．视觉传感焊缝跟踪技术的发展状况及实施方案探讨[J]．电焊机，2002，32(5)：1～8．
[22] 李原，徐德，沈扬等．一种焊缝结构光图像处理与特征提取方法[J]．焊接学报，2006，27(9)：25～30．
[23] 刘明友，刘南生，郭昌荣等．V型焊缝的视觉图像传感图像处理研究[J]．电焊机，2006，36(10)：7～9．
[24] 刘明友，刘南生，郭昌荣等．搭接焊缝的视觉传感图像预处理及信息提取[J]．焊接，2006(3)：25～27．
[25] 崔元彪，闰志峰，管晓光等．焊缝跟踪图像处理系统研究[J]．哈尔滨理工大学学报，2006，11(4)：85～88．
[26] 熊震宇，姜建锋．弧焊机器人焊缝图像处理与识别方法的研究[J]．焊接技术，2006，35(3)：8～10．
[27] 杜玉红，李亮玉，李晓青等．基于结构光三维视觉焊缝跟踪系统的研究[J]．天津工业大学学报，2006，25(2)：68～70．
[28] 刘明友，刘南生，郭昌荣等．基于结构光视觉传感的V形焊缝信息提取[J]．焊接技术，2006，35(5)：20～21．
[29] 朱六妹，杨先林，王伟等．基于主动光视觉法的实时焊缝跟踪控制系统的研究[J]．电焊机，2006，36(10)：1～6．
[30] 张虓，马兆瑞，郑军等．结构光视觉焊缝跟踪传感器光学系统的研究[J]．电焊机，2006，36(5)：22～26．
[31] 谢志孟，高向东．基于视觉传感的焊缝跟踪技术研究和展望[J]．焊接，2005(4)：5～9．
[32] 薛家祥，贾林，李海宝．基于M带小波变换的焊接熔池图像边缘检测[J]．焊接学报，2004，15(13)：1144～1146．
[33] 朱若磊，黄石生，张红兵．基于分形理论的焊缝信息提取[J]．华南理工大学学报，2004，32(6)：1～4．
[34] 刘国平，王洪亮，胡荣华等．模板匹配技术在焊缝图像处理中的应用[J]．焊接技术，2004，33(4)：14～15．
[35] Zh.Y Zhu, T. Lin, Y.J. Piao, et al. Recognition of the initial position of weld based on the image pattern match technology for welding robot[J]. International Journal of Advance Manufacturing Technology,2005,26(8):784～788.
[36] Hong Luo, Xiaoqi Chen. Laser visual sensing for seam tracking in robotic arc welding of titanium alloys[J]. International Journal of Advance Manufacturing Technology,2005,26(10): 1012～1017.
[37] 刘超英，黄石生．数学形态学在自动焊接过程熔池图像识别中的应用[J]．内蒙古大学学报，2005，36(6)：689～692．
[38] 降雨志，张义顺，张华军等．投影法和差影法在焊缝跟踪图像识别中的应用[J]．沈阳工业大学学报，2005，27(5)：558～561．
[39] 谷春艳，张立斌，胡宝坚等．图像处理技术在C02焊自动跟踪中的应用[J]．焊接学报，2004，25(4)：70～72．
[40] Pi-Cheng Tung, Ming-Chang Wu, Yean-Ren Hwang. An image-guided mobile robotic welding system for SMAW repair processes[J]. International Journal of Machine tool and Manufacture, 2004,44(11): 1223～1233.
[41] Jeng-Ywan Jeng, Tzuoh-Fei Mau and Shyeu-Ming Leu. Computer integrated vision and neural network technologies for intelligent automatic laser butt joint welding[J]. Computer Integrated Manufacture, 2000, 13(4): 345～357.
[42] Hsing-Chia Kuo, Li-Jen Wu. An image tracking system for welded seams using fuzzy logic [J]. Journal of Materials Processing Technology,2002,120(2): 169～185.
[43] M Labudovic, D Hu and R Kovacevic. Three-dimensional finite element modeling of laser modification[J]. Journal of Engineering Manufacturing,2000,214(8):683～692.
[44] 谢志孟，高向东．基于Canny算子的焊缝图像边缘检测技术[J]．焊接学报，2006，27(1)：29～36．
[45] 朱若磊．基于焊缝中心的焊缝信息的直接提取[J]．机床与液压，2006(4)：22～23．
[46] J. Y. Jeng, T. F. Mau and S. M. Leu. Gap Inspection and Alignment Using a Vision Technique for Laser Butt Joint Welding[J]. International Journal of Advance Manufacturing Technology, 2000,16(3): 212～216.
[47] Jingguo Ge, Zhengqiang Zhu, Defu He, et al. A vision-based algorithm for seam detection in a PAW process for large-diameter stainless steel pipes[J]. International Journal of Advance Manufacturing Technology, 2005,26(10): 1006～1011.
[48] S. B. Chen, X. Z. Chen and T. Qiu. Acquisition of Weld Seam Dimensional Position Information for Arc Welding Robot Based on Vision Computing[J]. Journal of Intelligent and Robotic Systems, 2005(43): 77～97.
[49] Xiangdong Gao, Suck Joo Na. Detection of Weld Position Based on Kalman Filtering of Weld Pool Images[J]. Journal of Information and Computational Science,2005,2(1): 13～18.
[50] 李弼程，彭天强，彭波等．智能图像处理技术[M]．北京：电子工业出版社，2004．
[51] 闫志鸿，张广军，邱美珍等．脉冲熔化极气体保护焊熔池图像的检测与处理[J]．焊接学报，2005，26(2)：37～40．
[52] 高向东，罗锡柱．一种基于图像质心的焊缝跟踪新方法[J]．焊接学报，2003，24(6)：15～18．
[53] 王武义，徐定杰，陈健翼．误差原理与数据处理[M]．哈尔滨：哈尔滨工业大学出版社，2001．
[54] 朱大奇，史慧．人工神经网络原理及应用[M]．北京：科学出版社，2006．
[55] 高隽．人工神经网络原理及仿真实例[M]．北京：机械工业出版社，2003．
[56] Martin T．Hagan，Howard B．Demuth，Mark Beale．Neural Network Design[M]．北京：机械工业出版社，2002．