Enhancing weld quality of novel robotic-arm arc welding: Vision-based monitoring, real-time control seam tracking

被引:2
|
作者
Sharma, Aman [1 ]
Chaturvedi, Rishabh [1 ]
Sharma, Kamal [1 ]
Binhowimal, Saad Abrahim [2 ]
Giri, Jayant [3 ,4 ,5 ]
Sathish, T. [6 ]
机构
[1] GLA Univ, Dept Mech Engn, Mathura 281406, India
[2] King Abdulaziz City Sci & Technol, Adv Mfg Technol Inst, Riyadh 11442, Saudi Arabia
[3] Yeshwantrao Chavan Coll Engn, Dept Mech Engn, Nagpur, India
[4] Lovely Profess Univ, Div Res & Dev, Phagwara, India
[5] Chitkara Univ, Chitkara Univ Inst Engn & Technol, Ctr Res Impact & Outcome, Rajpura 140401, Punjab, India
[6] SIMATS, Saveetha Sch Engn, Chennai 602105, Tamil Nadu, India
关键词
Seam tracking; Robotic-Arm Arc Welding (RAAW); Aristo Robot; Accuracy; Real-time monitoring; Fault detection and diagnostics (FDD); Vision system; Hand-eye calibration; SYSTEM;
D O I
10.1016/j.asej.2024.103109
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
A specially developed vision sensor seam tracking system is installed to improve the welding quality for RoboticArm Arc Welding (RAAW). New software is used for welding seam monitoring to examine different features of robotic arm arc welding. The software system comprises several components: welding voltage regulation, analytical parameters, image capture or analysis using enhanced algorithms, weld experts' database, robot coordination, and trajectory operations management. Experimentation is carried out to ensure the quality and reliability of various traditional welding methods and to evaluate the effectiveness of an established seamtracking process. The results indicate that seam tracking is accurate for most welding processes. However, it is noted that most image-learning algorithms have limited adaptability and capacity during welding. A vision sensor-based algorithm for adaptive extraction functionality is proposed to solve this issue. Conventional welding seams are divided into laser strip pictures into continuous and discontinuous weld seams. The vision system then processes the captured data to convert the pixel coordinates into real-world coordinates, often using hand-eye calibration techniques to align with the robot's coordinate system. The vision system captures data and processes it to convert pixel coordinates into real-world coordinates. The alignment process with the coordinate system of the robot is done using hand-eye calibration techniques. The Exponentially Weighted Moving Average (EWMA) control panel is used to diagnose and identify faults, keeping an eye on anomalous deviations from the extracted slurry profile while welding. To achieve a 96 % seam extraction ratio and +/- 0.50 mm seam tracking errors, the system uses an Aristo six-axis robot, a custom vision sensor, and seam-tracking software. The system demonstrates accuracy in industrial welding processes, with maximum and average seam tracking errors of 0.56 mm and 0.48 mm for continuous seams and 0.36 mm and 0.30 mm for non-continuous seams.
引用
收藏
页数:17
相关论文
共 42 条
  • [41] Vision-based multi-point real-time monitoring of dynamic displacement of large-span cable-stayed bridges
    Hu, Biao
    Chen, Wenjun
    Zhang, Yueqiang
    Yin, Yihe
    Yu, Qifeng
    Liu, Xiaolin
    Ding, Xiaohua
    MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 204
  • [42] A novel dynamic robotic moving phantom system for patient-specific quality assurance in real-time tumor-tracking radiotherapy
    Shiinoki, Takehiro
    Fujii, Fumitake
    Fujimoto, Koya
    Yuasa, Yuki
    Sera, Tatsuhiro
    JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, 2020, 21 (07): : 16 - 28