Chinese Journal of Mechanical Engineering >

2020 , Vol. 33 >Issue 1: 21 - 21

DOI: https://doi.org/10.1186/s10033-020-00438-2

Intelligent Manufacturing Technology

Discerning Weld Seam Profiles from Strong Arc Background for the Robotic Automated Welding Process via Visual Attention Features

  • Yinshui He ,
  • Zhuohua Yu ,
  • Jian Li ,
  • Lesheng Yu ,
  • Guohong Ma
展开
  • 1. School of Environment and Chemical Engineering, Nanchang University, Nanchang 330031, China;
    2. School of Mechanical Engineering, Key Laboratory of Lightweight and High Strength Structural Materials of Jiangxi Province, Nanchang University, Nanchang 330031, China;
    3. Institute of Technology. East China Jiao Tong University, Nanchang 330100, China

收稿日期: 2019-06-27

  修回日期: 2020-01-17

  网络出版日期: 2020-05-18

基金资助

Supported by National Natural Science Foundation of China (Grant Nos. 51575349, 51665037, 51575348), and State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System (Grant No. GZ2016KF002)

收起

Discerning Weld Seam Profiles from Strong Arc Background for the Robotic Automated Welding Process via Visual Attention Features

  • Yinshui He ,
  • Zhuohua Yu ,
  • Jian Li ,
  • Lesheng Yu ,
  • Guohong Ma
Expand
  • 1. School of Environment and Chemical Engineering, Nanchang University, Nanchang 330031, China;
    2. School of Mechanical Engineering, Key Laboratory of Lightweight and High Strength Structural Materials of Jiangxi Province, Nanchang University, Nanchang 330031, China;
    3. Institute of Technology. East China Jiao Tong University, Nanchang 330100, China

Received date: 2019-06-27

  Revised date: 2020-01-17

  Online published: 2020-05-18

Supported by

Supported by National Natural Science Foundation of China (Grant Nos. 51575349, 51665037, 51575348), and State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System (Grant No. GZ2016KF002)

Fold

摘要

In the robotic welding process with thick steel plates, laser vision sensors are widely used to profile the weld seam to implement automatic seam tracking. The weld seam profile extraction (WSPE) result is a crucial step for identifying the feature points of the extracted profile to guide the welding torch in real time. The visual information processing system may collapse when interference data points in the image survive during the phase of feature point identification, which results in low tracking accuracy and poor welding quality. This paper presents a visual attention feature-based method to extract the weld seam profile (WSP) from the strong arc background using clustering results. First, a binary image is obtained through the preprocessing stage. Second, all data points with a gray value 255 are clustered with the nearest neighborhood clustering algorithm. Third, a strategy is developed to discern one cluster belonging to the WSP from the appointed candidate clusters in each loop, and a scheme is proposed to extract the entire WSP using visual continuity. Compared with the previous methods the proposed method in this paper can extract more useful details of the WSP and has better stability in terms of removing the interference data. Considerable WSPE tests with butt joints and T-joints show the anti-interference ability of the proposed method, which contributes to smoothing the welding process and shows its practical value in robotic automated welding with thick steel plates.

关键词： Weld seam profile extraction; Visual attention features; Clustering; Robotic welding

本文引用格式

Yinshui He , Zhuohua Yu , Jian Li , Lesheng Yu , Guohong Ma . Discerning Weld Seam Profiles from Strong Arc Background for the Robotic Automated Welding Process via Visual Attention Features[J]. Chinese Journal of Mechanical Engineering, 2020 , 33(1) : 21 -21 . DOI: 10.1186/s10033-020-00438-2

Abstract

In the robotic welding process with thick steel plates, laser vision sensors are widely used to profile the weld seam to implement automatic seam tracking. The weld seam profile extraction (WSPE) result is a crucial step for identifying the feature points of the extracted profile to guide the welding torch in real time. The visual information processing system may collapse when interference data points in the image survive during the phase of feature point identification, which results in low tracking accuracy and poor welding quality. This paper presents a visual attention feature-based method to extract the weld seam profile (WSP) from the strong arc background using clustering results. First, a binary image is obtained through the preprocessing stage. Second, all data points with a gray value 255 are clustered with the nearest neighborhood clustering algorithm. Third, a strategy is developed to discern one cluster belonging to the WSP from the appointed candidate clusters in each loop, and a scheme is proposed to extract the entire WSP using visual continuity. Compared with the previous methods the proposed method in this paper can extract more useful details of the WSP and has better stability in terms of removing the interference data. Considerable WSPE tests with butt joints and T-joints show the anti-interference ability of the proposed method, which contributes to smoothing the welding process and shows its practical value in robotic automated welding with thick steel plates.

Key words： Weld seam profile extraction; Visual attention features; Clustering; Robotic welding

参考文献

[1] Y M Zhang, R Kovacevic, L Li. Characterization and real-time measurement of geometrical appearance of the weld pool. International Journal of Machine Tools & Manufacture, 1996, 36(7): 799-816.
[2] N Lv, Y Xu, Z Zhang, et al. Audio sensing and modeling of arc dynamic characteristic during pulsed Al alloy GTAW process. Sensor Review, 2013, 33(2): 141-156.
[3] Y Xu, G Fang, S Chen, et al. Real-time image processing for vision-based weld seam tracking in robotic GMAW. International Journal of Advanced Manufacturing Technology, 2014, 73(9-12): 1413-1425.
[4] Y He, H Chen, Y Huang, et al. Parameter self-optimizing clustering for autonomous extraction of the weld seam based on orientation saliency in robotic MAG welding. Journal of Intelligent & Robotic Systems, 2016, 83(2): 219-237.
[5] S Y Liu, G R Wang, Z Hua, et al. Design of robot welding seam tracking system with structured light vision. Chinese Journal of Mechanical Engineering, 2010, 23(4): 436-442.
[6] J Muhammad, H Altun, E. Abo-Serie. A robust butt welding seam finding technique for intelligent robotic welding system using active laser vision. The International Journal of Advanced Manufacturing Technology, 2018, 94(1): 13-29.
[7] J Fan, F Jing, Y Lei, et al. A precise seam tracking method for narrow butt seams based on structured light vision sensor. Optics & Laser Technology, 2019, 109(1): 616-626.
[8] Y F Gong, X Z Dai, X D Li. Structured-light based joint recognition using bottom-up and top-down combined visual processing. 2010 International Conference on Image Analysis and Signal Processing (IASP), Zhejiang, China, April 9-11, 2010: 507-512. https://www.researchgate.net/publication/251927209_Structured-light_based_joint_recognition_using_bottom-up_and_top-down_combined_visual_processing?ev=auth_pub
[9] R Xiao, Y Xu, Z Hou, et al. An adaptive feature extraction algorithm for multiple typical seam tracking based on vision sensor in robotic arc welding. Sensors and Actuators A: Physical, 2019, 297: 111533.
[10] S Liu, H Zhang, J Jia, et al. Feature recognition for underwater weld images. 29th Chinese Control Conference (CCC), 2010, Beijing, China, July 29-31, 2010: 2729-2734. (in Chinese) http://cpfd.cnki.com.cn/Article/CPFDTOTAL-KZLL201007001527.htm
[11] J Du, W Xiong, W Chen, et al. Robust laser stripe extraction using ridge segmentation and region ranking for 3D reconstruction of reflective and uneven surface. Proceedings of the IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada, September 27-30, 2015: 4912-4916. https://www.researchgate.net/publication/308627364_Robust_laser_stripe_extraction_using_ridge_segmentation_and_region_ranking_for_3D_reconstruction_of_reflective_and_uneven_surface
[12] W P Gu, Z Y Xiong, W Wan. Autonomous seam acquisition and tracking system for multi-pass welding based on vision sensor. The International Journal of Advanced Manufacturing Technology, 2013, 69(1-4): 451-460.
[13] X Wang, R Bai, Z Liu. Weld seam detection and feature extraction based on laser vision. 33rd Chinese Control Conference (CCC), 2014, Nanjing, China, July 28-30, 2014: 8249-8252. (in Chinese)https://www.researchgate.net/publication/286650662_Weld_seam_detection_and_feature_extraction_based_on_laser_vision
[14] H-C Nguyen, B-R Lee. Laser-vision-based quality inspection system for small-bead laser welding. International Journal of Precision Engineering and Manufacturing, 2014, 15(3): 415-423.
[15] Y He, Z Yu, J Li, et al. Weld seam profile extraction using top-down visual attention and fault detection and diagnosis via EWMA for the stable robotic welding process. The International Journal of Advanced Manufacturing Technology, 2019, 104 (9): 3883-3897.
[16] Q-Q Wu, J-P Lee, M-H Park, et al. A study on development of optimal noise filter algorithm for laser vision system in GMA welding. Procedia Engineering, 2014, 97: 819-827.
[17] Z Lei, Z Mingyang, Z Lihua. Vision-based profile generation method of TWB for a new automatic laser welding line. 2007 IEEE International Conference on Automation and Logistics, Jinan, China, August 18-21, 2007: 1658-1663. https://www.researchgate.net/publication/224288724_Vision-Based_Profile_Generation_Method_of_TWB_for_a_New_Automatic_Laser_Welding_Line
[18] Y L Xie, L Zhang, C Y Wu, et al. A method of robotic visual tracking for a new automatic laser welding line. 2008 International Conference on Computer Science and Software Engineering, Hubei, China, December 12-14, 2008: 891-894. http://www.researchgate.net/publication/224361933_A_Method_of_Robotic_Visual_Tracking_for_a_New_Automatic_Laser_Welding_Line
[19] L Zhang, C Wu, Y Zou. An on-line visual seam tracking sensor system during laser beam welding. International Conference on Information Technology and Computer Science, Kiev, Ukraine, July 25-26, 2009: 361-364. http://www.researchgate.net/publication/232629375_An_On-line_Visual_Seam_Tracking_Sensor_System_During_Laser_Beam_Welding?_sg=wRImcWMFkSkh_ev1twG7mdf26Ri7IJf8eCmef5whb0pM6yn-NmdwUfwUyB8UTTYj-PnikNofGCwaCV4k28VEug
[20] C Gu, Y Li, Q Wang, D Xu, et al. Robust features extraction for lap welding seam tracking system. 2009. YC-ICT '09. IEEE Youth Conference on Information, Computing and Telecommunication, Beijing, China, September 20-21, 2010: 319-322.http://www.researchgate.net/publication/224099812_Robust_features_extraction_for_lap_welding_seam_tracking_system
[21] Y He, Y Chen, Y Xu, et al. Autonomous detection of weld seam profiles via a model of saliency-based visual attention for robotic arc welding. Journal of Intelligent & Robotic Systems, 2016, 81(3-4): 395-406.
[22] Y He, Y Xu, Y Chen, et al. Weld seam profile detection and feature point extraction for multi-pass route planning based on visual attention model. Robotics and Computer-Integrated Manufacturing, 2016, 37: 251-261.
[23] Y He, H Zhou, J Wang, et al. Weld seam profile extraction of T-joints based on orientation saliency for path planning and seam tracking. 2016 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO), Shanghai, China, July 8-10, 2016: 110-115. http://www.researchgate.net/publication/309760261_Weld_seam_profile_extraction_of_T-joints_based_on_orientation_saliency_for_path_planning_and_seam_tracking
[24] Y S He, Y X Chen, D Wu, et al. A detection framework for weld seam profiles based on visual saliency. In: Tarn TJ., Chen SB., Chen XQ. (eds). Robotic Welding, Intelligence and Automation. RWIA 2014. Advances in Intelligent Systems and Computing, 2015, 363: 311-319.http://link.springer.com/chapter/10.1007/978-3-319-18997-0_27
Options
文章导航

/

〈 〉

版权所有 © 《Chinese Journal of Mechanical Engineering》编辑部

技术支持：北京玛格泰克科技发展有限公司