基于被动视觉的窄间隙振摆动热丝GTAW焊缝跟踪系统设计

doi:10.3901/JME.2025.12.164

摘要/Abstract

摘要： 窄间隙振摆动热丝GTAW具有高效、绿色、优质等特点，在LNG储罐内罐立缝的焊接中已可以取代手工电弧焊并实现了示范应用。但在实际生产中，仍需要熟练焊工全程进行焊接位置的实时调整与控制。为了避免人工焊缝跟踪的不稳定性、提高焊接过程的自动化程度，提出基于被动视觉的坡口与电弧位置检测方法，并利用建立的光学系统及自适应图像特征增强算法获得焊接过程的高动态范围成像，通过检测钨极摆动时两侧的停留位置计算出钨极过零点时的中心位置，再与同步检测的窄间隙坡口中心位置进行实时比对，获得电弧零点位置的偏差信息，据此结合建立的模糊控制算法实现焊接过程电弧位置的实时跟踪与控制。试验结果表明：建立的光学系统可以有效地实现焊接过程的被动视觉图像采集，并通过自适应算法可以将图像灰度差从40左右提高至120附近；通过检测焊枪摆动时的左右停留位置，利用建立的电弧中心位置特征提取算法可以在一个摆动周期内(1.13 s)获得两次焊枪中心位置，单次准确率在80%以上；通过与检测的坡口中心位置进行对比，利用建立的模糊控制规则，在工艺试验中可以实现焊接过程的实时跟踪与控制，误差精度控制在±0.3 mm。

关键词: 焊缝跟踪, 被动视觉, 窄间隙, 振摆动热丝GTAW

Abstract: Narrow gap oscillating hot-wire gas tungsten arc welding (GTAW) is known for its efficiency, environmental friendliness, and high quality. It has been demonstrated to replace manual arc welding for welding the seams of the inner tank. Taking the example of a LNG storage tank, with individual inner shell seam lengths of approximately 12 meters, deviations in welding position due to beveling and assembly can lead to defects like incomplete fusion on the sidewall. Therefore, skilled welders are still required for real-time adjustment and control of the welding position during actual production. In order to avoid the instability of manual weld tracking and improve the automation of the welding process, a passive visual-based method for detecting bevels and arc positions is proposed. An optical system is established, along with an adaptive image feature enhancement algorithm to obtain high dynamic range images of the welding process. By detecting the stop positions on both sides of the tungsten electrode during oscillation, the central position of the tungsten electrode at the zero point is calculated. This information is then compared in real-time with the detected center position of the narrow gap bevel. Using a developed fuzzy control algorithm, real-time tracking and control of the arc position during the welding process is achieved. Experimental results show that：The established optical system can effectively capture passive visual images of the welding process, and the adaptive algorithm can increase the image grayscale difference from around 40 to approximately 120; By detecting the left and right stop positions during the welding gun oscillation and utilizing a feature extraction algorithm for the arc center position, the center position of the welding gun can be obtained twice within one oscillation cycle (1.13 seconds), with a single accuracy rate of over 80%; By comparing with the detected bevel center position, and using the established fuzzy control rules, real-time tracking and control of the welding process can be achieved in process trials, with an error accuracy controlled within ±0.3 mm.

Key words: weld seam tracking, passive vision, narrow gap, pulsed hot wire GTAW

中图分类号:

TG409

朱明, 翁军, 朱珍文, 杨彬晖, 张刚, 石玗. 基于被动视觉的窄间隙振摆动热丝GTAW焊缝跟踪系统设计[J]. 机械工程学报, 2025, 61(12): 164-172.

ZHU Ming, WENG Jun, ZHU Zhenwen, YANG Binhui, ZHANG Gang, SHI Yu. Design of a Narrow Gap Oscillating Hot Wire GTAW Seam Tracking System Based on Passive Vision[J]. Journal of Mechanical Engineering, 2025, 61(12): 164-172.

参考文献

[1] 黄帆. 我国液化天然气现状及发展前景分析[J]. 天然气技术，2007(1)：68-71，92. HUANG Fan. Analysis of the current situation and development prospects of liquefied natural gas in China[J]. Natural Gas Technology Journal，2007(1)：68-71，92.
[2] XU T，Shi Y，Jiang Z，et al. Improvement of cryogenic toughness for 9% Ni steel keyhole TIG butt-welded joints with a Ni inter layer[J]. Materials Science and Engineering：A，2022，835：142661.
[3] 郭伟，蔡艳，华学明. LNG储罐用节镍低温钢焊接接头组织与低温性能[J]. 电焊机，2022，52(1)：17-24. GUO Wei，CAI Yan，HUA Xueming. Microstructure and low-temperature performance of welded joints of nickel-saving low-temperature steel for LNG tanks[J]. Electric Welding Machine，2022，52(1)：17-24.
[4] 孟庆政，秦玉良，姜春霞，等. 提高LNG储罐内罐9%Ni钢壁板一次焊接合格率的研究[J]. 石油和化工设备，2021，24(7)：60-63. MENG Qingzheng，QIN Yuliang，JIANG Chunxia，et al. Research on improving the first welding qualification rate of 9%Ni steel inner tank wall plate for LNG tanks[J]. Oil & Chemical Equipment，2021，24(7)：60-63.
[5] 李雪梅. 浅谈LNG低温储罐内罐焊接技术[J]. 石油化工建设，2021，43(3)：63-65，70. LI Xuemei. Discussion on welding technology for inner tanks of LNG low-temperature storage tanks[J]. Petroleum and Chemical Industry Construction，2021，43(3)：63-65，70.
[6] 陈哲，韦生，陆传航，等. LNG项目超低温服役不锈钢的TIPTIG焊接工艺[J]. 焊接技术，2014，43(6)：68-71. CHEN Zhe，WEI Sheng，LU Chuanhang，et al. TIPTIG welding process for ultra-low temperature service stainless steel in LNG projects[J]. Welding Technology Journal，2014，43(6)：68-71.
[7] XU T，SHI Y，JIANG Z，et al. Improvement of cryogenic toughness for 9% Ni steel keyhole TIG butt-welded joints with a Ni interlayer[J]. Materials Science and Engineering：A，2022，835：142661.
[8] KUSANO K，WATANABE H. Recent trends in development of high‐efficiency TIG welding; high deposition TIG welding and ultranarrow-gap TIG welding[J]. Welding International，2002，16(12)：986-991.
[9] SHARMA G，TYAGI R，SHARMA P. Variants of TIG welding process for improvement of weld penetration depth-A review[J]. Materials Today：Proceedings，2022，64：1362-1366.
[10] LI S，ZHOU E，PAN Q，et al. Closed-loop control of thin plate TIG butt welding with reserved gap based on fusion hole[J]. Journal of Manufacturing Processes，2023，85：666-682.
[11] LE J，Zhang H，Chen X. Right-angle fillet weld tracking by robots based on rotating arc sensors in GMAW[J]. The International Journal of Advanced Manufacturing Technology，2017，93(1)：605-616.
[12] Wang H，Lei T，Rong Y M，et al. Arc length stable method of GTAW based on adaptive Kalman filter[J]. Journal of Manufacturing Processes，2021，63：130-138.
[13] VOLODYMYR S，IEVGEN Z，ARTEMII B，et al. Contactless monitoring of welding processes with computer processing of acoustic emission signals[C]//201814th International Conference on Advanced Trends in Radioelecrtronics，Telecommunications and Computer Engineering (TCSET)，2018.
[14] Moon H，Kim Y B，Beattie R J. Multi sensor data fusion for improving performance and reliability of fully automatic welding system[J]. The International Journal of Advanced Manufacturing Technology，2006，28(3)：286-293.
[15] XU Y，LV N，Zhong J，et al. Research on the real-time tracking information of three-dimension welding seam in robotic GTAW process based on composite sensor technology[J]. Journal of Intelligent & Robotic Systems，2012，68(2)：89-103.
[16] 王志江，薛坤喜，吴定勇，等. 基于视觉传感的机器人焊缝纠偏控制系统[J]. 机械工程学报，2019，55(17)：48-55. WANG Zhijiang，XUE Kunxi，WU Dingyong，et al. Vision-based robot weld seam correction control system[J]. Journal of Mechanical Engineering，2019，55(17)：48-55.
[17] 黄军芬，薛龙，黄继强，等. 基于视觉传感的GMAW熔透状态预测[J]. 机械工程学报，2019，55(17)：41-47. HUANG Junfen，XUE Long，HUANG Jiqiang，et al. Prediction of GMAW penetration state based on visual sensing[J]. Journal of Mechanical Engineering，2019，55(17)：41-47.
[18] XU Y，YU H，ZHONG J，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.
[19] SHI Y H，YOO W S，NA S J. Mathematical modelling of rotational arc sensor in GMAW and its applications to seam tracking and endpoint detection[J]. Science and Technology of Welding and Joining，2006，11(6)：723-730.
[20] MUHAMMAD J，ALTUN H，ABO-SERIE E. A robust butt welding seam finding technique for intelligent robotic welding system using active laser vision[J]. The International Journal of Advanced Manufacturing Technology，2018，94(1)：13-29.
[21] XIAO R，XU Y，HOU Z，et al. An adaptive feature extraction algorithm for multiple typical seam tracking based on vision sensor in robotic arc welding[J]. Sensors and Actuators A：Physical，2019，297：111533.