Seam Feature Point Acquisition Based on Efficient Convolution Operator and Particle Filter in GMAW

• Published in: IEEE transactions on industrial informatics Vol. 17; no. 2; pp. 1220 - 1230
• Main Authors: Fan, Junfeng, Deng, Sai, Ma, Yunkai, Zhou, Chao, Jing, Fengshui, Tan, Min
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.02.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Arc seam welding; Butt joints; Cameras; Convolution; Efficient convolution operator (ECO); Feature extraction; Gas metal arc welding; Image acquisition; Lap joints; particle filter (PF); Position measurement; robot intelligent welding; Robots; seam feature acquisition; Seam tracking; Seams; structured light vision; Target tracking; Vision sensors; Welded joints; Welding
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2020.2977121

Seam feature point acquisition is the premise of the intelligent welding process such as initial point guiding and seam tracking. However, conventional seam feature point acquisition methods based on geometric feature have shortcomings of poor flexibility and robustness. In this article, a seam feature point acquisition method based on efficient convolution operator (ECO) and particle filter (PF) is proposed, which could be applied to different weld types and could achieve fast and accurate seam feature point acquisition even under the interference of welding arc light and spatter noises. First, a structured light vision sensor is developed to acquire welding image. Second, the ECO algorithm is adopted to track the seam region and acquire seam feature point during gas metal arc welding process. Third, the state and measurement equations of the weld seam position are established, and PF is applied to improve seam feature point acquisition accuracy. Finally, a welding experiment system is built and a series of seam feature point acquisition experiments of butt joint, lap joint, and fillet joint are carried out to validate the performance of the proposed method. The experiment results demonstrate that the processing speed of the proposed method could reach up 35 Hz, and the seam feature point acquisition errors are smaller than 0.15 mm, which could meet the real-time and accuracy requirement for subsequent initial point guiding and seam tracking.