Robust identification of weld seam based on region of interest operation

doi:10.1007/s40436-020-00325-y

Advances in Manufacturing ›› 2020, Vol. 8 ›› Issue (4): 473-485.doi: 10.1007/s40436-020-00325-y

• ARTICLES • 上一篇

Robust identification of weld seam based on region of interest operation

Ying-Zhong Tian¹, Hong-Fei Liu¹, Long Li¹, Wen-Bin Wang², Jie-Cai Feng^1,3, Feng-Feng Xi⁴, Guang-Jie Yuan¹

1 School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, People's Republic of China;
2 School of Mechanical and Electrical, Shenzhen Polytechnic, Shenzhen 518055, Guangdong, People's Republic of China;
3 Shanghai Rui Rong Laser Welding Technology Co., Ltd, Shanghai 201306, People's Republic of China;
4 Department of Mechanical, Aerospace and Industrial Engineering, Ryerson University, Toronto, Canada

收稿日期:2020-03-17 修回日期:2020-06-25 发布日期:2020-12-07
通讯作者: Guang-Jie Yuan E-mail:guangjie@shu.edu.cn
基金资助:
This study was supported by the Special Plan of Major Scientific Instruments and Equipment of the State (Grant No. 2018YFF01013101), the National Natural Science Foundation of China (Grant Nos. 51775322, 61704102, and 61603237), Project named “Key technology research and demonstration line construction of advanced laser intelligent manufacturing equipment” from Shanghai Lingang Area Development Administration.

Robust identification of weld seam based on region of interest operation

Ying-Zhong Tian¹, Hong-Fei Liu¹, Long Li¹, Wen-Bin Wang², Jie-Cai Feng^1,3, Feng-Feng Xi⁴, Guang-Jie Yuan¹

1 School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, People's Republic of China;
2 School of Mechanical and Electrical, Shenzhen Polytechnic, Shenzhen 518055, Guangdong, People's Republic of China;
3 Shanghai Rui Rong Laser Welding Technology Co., Ltd, Shanghai 201306, People's Republic of China;
4 Department of Mechanical, Aerospace and Industrial Engineering, Ryerson University, Toronto, Canada

Received:2020-03-17 Revised:2020-06-25 Published:2020-12-07
Contact: Guang-Jie Yuan E-mail:guangjie@shu.edu.cn
Supported by:
This study was supported by the Special Plan of Major Scientific Instruments and Equipment of the State (Grant No. 2018YFF01013101), the National Natural Science Foundation of China (Grant Nos. 51775322, 61704102, and 61603237), Project named “Key technology research and demonstration line construction of advanced laser intelligent manufacturing equipment” from Shanghai Lingang Area Development Administration.

摘要/Abstract

摘要： For welding path determination, the use of vision sensors is more effective compared with complex offline programming and teaching in small to medium volume production. However, interference factors such as scratches and stains on the surface of the workpiece may affect the extraction of weld information. In the obtained weld image, the weld seams have two distinct features related to the workpiece, which are continuous in a single process and separated from the workpiece’s gray value. In this paper, a novel method is proposed to identify the welding path based on the region of interest (ROI) operation, which is concentrated around the weld seam to reduce the interference of external noise. To complete the identification of the entire welding path, a novel algorithm is used to adaptively generate a dynamic ROI (DROI) and perform iterative operations. The identification accuracy of this algorithm is improved by setting the boundary conditions within the ROI. Moreover, the experimental results confirm that the coefficient factor used for determining the ROI size is a pivotal influencing factor for the robustness of the algorithm and for obtaining an optimal solution. With this algorithm, the welding path identification accuracy is within 2 pixels for three common butt weld types.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-020-00325-y

关键词: Passive vision, Noise reduction, Welding path identification, Region of interest (ROI)

Abstract: For welding path determination, the use of vision sensors is more effective compared with complex offline programming and teaching in small to medium volume production. However, interference factors such as scratches and stains on the surface of the workpiece may affect the extraction of weld information. In the obtained weld image, the weld seams have two distinct features related to the workpiece, which are continuous in a single process and separated from the workpiece’s gray value. In this paper, a novel method is proposed to identify the welding path based on the region of interest (ROI) operation, which is concentrated around the weld seam to reduce the interference of external noise. To complete the identification of the entire welding path, a novel algorithm is used to adaptively generate a dynamic ROI (DROI) and perform iterative operations. The identification accuracy of this algorithm is improved by setting the boundary conditions within the ROI. Moreover, the experimental results confirm that the coefficient factor used for determining the ROI size is a pivotal influencing factor for the robustness of the algorithm and for obtaining an optimal solution. With this algorithm, the welding path identification accuracy is within 2 pixels for three common butt weld types.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-020-00325-y

Key words: Passive vision, Noise reduction, Welding path identification, Region of interest (ROI)

Ying-Zhong Tian, Hong-Fei Liu, Long Li, Wen-Bin Wang, Jie-Cai Feng, Feng-Feng Xi, Guang-Jie Yuan. Robust identification of weld seam based on region of interest operation[J]. Advances in Manufacturing, 2020, 8(4): 473-485.

参考文献

1. Fan J, Jing F, Fang Z et al (2017) Automatic recognition system of welding seam type based on svm method. Int J Adv Manuf Technol 92(1/4):989-999
2. Svenman E, Runnemalm A (2017) A complex response inductive method for improved gap measurement in laser welding. Int J Adv Manuf Technol 88(1/4):175-184
3. Jeong SK, Lee GY, Lee WK et al (2001) Development of high speed rotating arc sensor and seam tracking controller for welding robots. In:ISIE 2001 IEEE international symposium on industrial electronics proceedings. IEEE, vol 2, pp 845-850
4. Chen B, Feng JC (2013) A survey of underwater wet weld seam tracking based on ultrasonic sensor. Appl Mech Mater 1433:2227-2230
5. Gao X, Mo L, Xiao Z et al (2016) Seam tracking based on Kalman filtering of micro-gap weld using magneto-optical image. Int J Adv Manuf Technol 83(1/4):21-32
6. Ni D, Yew AWW, Ong SK et al (2017) Haptic and visual augmented reality interface for programming welding robots. Adv Manuf 5(3):191-198
7. Xu Y, Fang G, Chen S et al (2014) Real-time image processing for vision-based weld seam tracking in robotic GMAW. Int J Adv Manuf Technol 73(9/12):1413-1425
8. Shah HNM, Sulaiman M, Shukor AZ (2017) Autonomous detection and identification of weld seam path shape position. Int J Adv Manuf Technol 92(9/12):3739-3747
9. Li X, Li X, Khyam MO et al (2017) Robust welding seam tracking and recognition. IEEE Sens J 17(17):5609-5617
10. Yang L, Li E, Long T et al (2018) A high-speed seam extraction method based on the novel structured-light sensor for arc welding robot:a review. IEEE Sens J 18(21):8631-8641
11. Dinham M, Fang G (2012) Weld seam detection using computer vision for robotic arc welding. In:IEEE international conference on automation science and engineering. IEEE, pp 771-776
12. Moradi AN, Dezfulli BMA, Alavi CSE (2013) Development a vision based seam tracking system for none destructive testing machines. Int J Comput Sci Netw Solut 1(4):45-56
13. Ding Y, Huang W, Kovacevic R (2016) An on-line shapematching weld seam tracking system. Rob Comput Integr Manuf 42:103-112
14. Ye Z, Fang G, Chen S et al (2013) A robust algorithm for weld seam extraction based on prior knowledge of weld seam. Sens Rev 33(2):125-133
15. Yang LJ, Lou PH, Qian XM (2015) Recognition of initial welding position for large diameter pipeline based on pulse coupled neural network. Ind Robot Int J 42(4):339-346
16. Fan J, Deng S, Jing F et al (2019) An initial point alignment and seam-tracking system for narrow weld. IEEE Trans Ind Inf 16(2):1-1
17. Dinham M, Fang G (2013) Autonomous weld seam identification and localisation using eye-in-hand stereo vision for robotic arc welding. Rob Comput Integr Manuf 29(5):288-301
18. Li X, Li X, Ge SS et al (2017) Automatic welding seam tracking and identification. IEEE Trans Ind Electron 64(9):7261-7271
19. Shah HNM, Sulaiman M, Shukor AZ et al (2018) Butt welding joints recognition and location identification by using local thresholding. Rob Comput Integr Manuf 51:181-188
20. Shi F, Lin T, Chen S (2009) Efficient weld seam detection for robotic welding based on local image processing. Ind Robot Int J 36(3):277-283
21. Fang Z, Xu D, Tan M (2011) A vision-based self-tuning fuzzy controller for fillet weld seam tracking. IEEE-ASME T Mech 16(3):540-550
22. Dinham M, Fang G (2014) Detection of fillet weld joints using an adaptive line growing algorithm for robotic arc welding. Rob Comput Integr Manuf 30(3):229-243
23. Bagger C, Olsen FO (2005) Review of laser hybrid welding. J Laser Appl 17(1):2-14
24. Bunaziv I, Akselsen OM, Frostevarg J et al (2019) Application of laser-arc hybrid welding of steel for low-temperature service. Int J Adv Manuf Technol 102(5/8):2601-2613
25. Wei SC, Wang J, Lin T et al (2012) Application of image morphology in detecting and extracting the initial welding position. J Shanghai Jiaotong Univ (Sci) 17(3):323-326
26. Fang Z, Xu D, Tan M (2013) Vision-based initial weld point positioning using the geometric relation-ship between two seams. Int J Adv Manuf Technol 66(9/12):1535-1543
27. Shah HM, Sulaiman M, Shukor A et al (2016) Vision based identification and detection of initial, mid and end points of weld seams path in butt-welding joint using point detector methods. J Telecommun Electron Comput Eng 8(7):57-61
28. Tian YZ, Hu HJ, Cui HY et al (2017) Three-dimensional surface microtopography recovery from a multifocus image sequence using an omnidirectional modified laplacian operator with adaptive window size. Appl Opt 56(22):6300-6310
29. Haug K, Pritschow G (1998) Robust laser-stripe sensor for automated weld-seam-tracking in the shipbuilding industry. In:IECON'98 proceedings of the 24th annual conference of the IEEE industrial electronics society. IEEE, vol 2, pp 1236-1241
30. Liu F, Wang Z, Ji Y (2018) Precise initial weld position identification of a fillet weld seam using laser vision technology. Int J Adv Manuf Technol 99(5/8):2059-2068

Robust identification of weld seam based on region of interest operation

Robust identification of weld seam based on region of interest operation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价