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 50 条
  • [41] Vision-Based Real-Time Posture Tracking for Multiple Construction Workers
    Lin, Xiao
    Guo, Ziyang
    Guo, Hongling
    Zhou, Ying
    JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2024, 38 (04)
  • [42] An adaptive feature extraction algorithm for multiple typical seam tracking based on vision sensor in robotic arc welding
    Xiao, Runquan
    Xu, Yanling
    Hou, Zhen
    Chen, Chao
    Chen, Shanben
    SENSORS AND ACTUATORS A-PHYSICAL, 2019, 297
  • [43] Deviation detection and real-time seam tracking system based on magnetic-control arc sensor
    School of Mechanical Engineering, Xiangtan University, Xiangtan 411105, China
    Shanghai Jiaotong Daxue Xuebao, 2008, SUPPL. 1 (50-52+56):
  • [44] Research on real-time tracking algorithm of weld seam based on Fourier Transform Profilometry
    Liu Qingyu
    Wang Xinghua
    Sun Hongwei
    MULTIMODAL SENSING: TECHNOLOGIES AND APPLICATIONS, 2019, 11059
  • [45] Real-time Vision-based Telepresence Robot Hand Control
    Deng, Chuanyun
    Lu, Jie
    Lam, Tin Lun
    2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS IEEE-ROBIO 2014, 2014, : 463 - 468
  • [46] Real-time vision-based control of a nonholonomic mobile robot
    Das, AK
    Fierro, R
    Kumar, V
    Southall, B
    Spletzer, J
    Taylor, CJ
    2001 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS, 2001, : 1714 - 1719
  • [47] Seam welding monitoring system based on real-time electrical signal analysis
    Lanzoni, Massimo
    Salomoni, Mirko
    Riccò, Bruno
    Welding Journal (Miami, Fla), 2010, 89 (10):
  • [48] Real time optimization of robotic arc welding based on machine vision and neural networks
    Peng, J
    Chen, Q
    Lu, J
    Jin, J
    van Luttervelt, CA
    IECON '98 - PROCEEDINGS OF THE 24TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4, 1998, : 1279 - 1283
  • [49] Vision-based integrated mobile robotic system for real-time applications in construction
    Asadi, Khashayar
    Ramshankar, Hariharan
    Pullagurla, Harish
    Bhandare, Aishwarya
    Shanbhag, Suraj
    Mehta, Pooja
    Kundu, Spondon
    Han, Kevin
    Lobaton, Edgar
    Wu, Tianfu
    AUTOMATION IN CONSTRUCTION, 2018, 96 : 470 - 482
  • [50] Real-Time Weld Gap Monitoring and Quality Control Algorithm during Weaving Flux-Cored Arc Welding Using Deep Learning
    Jin, Chengnan
    Rhee, Sehun
    METALS, 2021, 11 (07)