Online Extraction of Pose Information of 3D Zigzag-Line Welding Seams for Welding Seam Tracking
Abstract
:1. Introduction
2. Fast Acquisition of Point Cloud Data for 3D Zigzag-Line Welding Seams
3. Extraction of the Pose Information for 3D Zigzag-Line Welding Seams
3.1. Point Cloud Segmentation
3.2. Extraction of Point Cloud Data of 3D Zigzag-Line Welding Seams
- The point cloud was preprocessed using the bilateral filtering algorithm.
- If c = 3, Steps 3, 4 and 5 would be implemented; if c = 2, only Step 3 would be implemented.
- The RANSAC algorithm was used to extract the point cloud to obtain the point set . Moreover, all the points belonging to were subtracted, and the remaining points were outlier.
- The bilateral filtering algorithm was applied to process the outlier.
- The RANSAC algorithm was used to fit the straight lines connected by the points in the outlier to obtain the point set .
3.3. 3D Zigzag-Line Welding Seams Trajectory Fitting
3.4. Attitude Estimation of 3D Zigzag-Line Welding Seams
- If , calculate , by Formulas (7) and (8), where is the point on the welding seam .
- If , calculate , , by Formulas (7)–(9), where are points on and respectively.
4. Results and Analysis
4.1. System Platform
4.2. Experimental Verification
4.3. Error Analysis
4.4. Efficiency of the Algorithm
5. Discussion
6. Conclusions
- (1)
- An online extraction system for the pose information of 3D zigzag-line welding seams was successfully established for the real-time tracking of welding seams
- (2)
- A 3D zigzag-line welding seam point cloud segmentation method based on the ρ-Approximate DBSCAN clustering algorithm was used to achieve the online segmentation of the point cloud data of 3D zigzag-line welding seams. The running time of the main algorithm is less than 120 ms, which meets the requirement for the online extraction of welding seam pose information for high-speed welding with a welding speed exceeding 1500 mm/min.
- (3)
- A number of welding experiments were carried out on 3D zigzag-line welding seams with a fold angle ranging from 130° to 230°. The results of the experiments showed that when the welding velocity was 1000 mm/min, the proposed method achieved a welding seam position detection error of less than 0.35 mm, and a welding seam attitude estimation error of less than 2 degrees. This met the requirements for the online extraction of the pose information for 3D zigzag-line welding seams for the real-time tracking of welding seams.
- (4)
- The proposed method was applicable to swing welding. The method is expected to be extensively used in the welding of middle thickness plates during the manufacturing of marine engineering equipment, heavy lifting equipment, and logistics transportation equipment.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Pedro, N.; Mendes, N. Direct off-Line Robot Programming via a Common CAD Package. Robot. Auton. Syst. 2013, 61, 896–910. [Google Scholar]
- Baizid, K.; Ćuković, S.; Iqbal, J.; Yousnadj, A.; Chellali, R.; Meddahi, A.; Devedžićl, G.; Ghionea, I. IRoSim: Industrial Robotics Simulation Design Planning and Optimization Platform Based on CAD and Knowledgeware Technologies. Robot. Comput.-Integr. Manuf. 2016, 42, 121–134. [Google Scholar] [CrossRef]
- Xu, Y.; Lv, N.; Fang, G.; Du, S.; Zhao, W.; Ye, Z.; Chen, S. Welding Seam Tracking in Robotic Gas Metal Arc Welding. J. Mater. Process. Technol. 2017, 248, 18–30. [Google Scholar] [CrossRef]
- Hong, Y.; Du, D.; Pan, J.; Li, X. Seam-tracking based on dynamic trajectory planning for a mobile welding robot. China Weld. 2019, 28, 46–50. [Google Scholar]
- Du, J.; Yong, L.Y.; Sun, M.; Ge, J.S. Study on Stereo Vision for 3D Reconstruction of Welding Seam. Adv. Mater. Res. 2013, 850, 212–216. [Google Scholar] [CrossRef]
- Li, J.; Chen, Z.; Rao, G.; Xu, J. Structured Light-Based Visual Servoing for Robotic Pipe Welding Pose Optimization. IEEE Access 2019, 7, 138327–138340. [Google Scholar] [CrossRef]
- Li, G.; Hong, Y.; Gao, J.; Hong, B.; Li, X. Welding Seam Trajectory Recognition for Automated Skip Welding Guidance of a Spatially Intermittent Welding Seam Based on Laser Vision Sensor. Sensors 2020, 20, 3657. [Google Scholar] [CrossRef] [PubMed]
- Zou, Y.; Chen, J.; Wei, X. Research on a real-time pose estimation method for a seam tracking system. Opt. Lasers Eng. 2020, 127, 105947. [Google Scholar] [CrossRef]
- Chen, X.; Huang, Y.; Chen, S. Model analysis and experimental technique on computing accuracy of seam spatial position information based on stereo vision for welding robot. Ind. Robot An Int. J. 2012, 39, 349–356. [Google Scholar] [CrossRef]
- Dinham, M.; Fang, G. Autonomous weld seam identification and localisation using eye-in-hand stereo vision for robotic arc welding. Robot. Comput.-Integr. Manuf. 2013, 29, 288–301. [Google Scholar] [CrossRef]
- Jia, T.; Fu, Y.; Peng, B.; Song, Z.; Chen, D. Depth Information Extraction of Seam Structure based on Visual Method. In Proceedings of the 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), Honolulu, HI, USA, 31 July–4 August 2017; pp. 179–182. [Google Scholar]
- Jing, L.; Fengshui, J.; En, L. RGB-D sensor-based auto path generation method for arc welding robot. In Proceedings of the 2016 Chinese control and decision conference (CCDC), Yinchuan, China, 28–30 May 2016; pp. 4390–4395. [Google Scholar]
- Silvers, G.A.; Fang, G. Human machine interface in weld seam detection using an RGB-D camera. Adv. Mater. Res. 2014, 875, 1967–1971. [Google Scholar] [CrossRef]
- Rui, P.; Navarro-Alarcon, D.; Wu, V.; Yang, W. A Point Cloud-Based Method for Automatic Groove Detection and Trajectory Generation of Robotic Arc Welding Tasks. In Proceedings of the 2020 17th International Conference on Ubiquitous Robots (UR), Kyoto, Japan, 22–26 June 2020; pp. 380–386. [Google Scholar]
- Zeng, J.; Chang, B.; Du, D.; Peng, G.; Chang, S.; Hong, Y.; Wang, L.; Shan, J. A vision-aided 3D path teaching method before narrow butt joint welding. Sensors 2017, 17, 1099. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Peng, G.; Xue, B.; Gao, Y.; Tian, Z.; Hong, Y.; Chang, B.; Du, D. Vision sensing and surface fitting for real-time detection of tight butt joints. J. Phys. Conf. Ser. 2018, 1074, 12001. [Google Scholar] [CrossRef] [Green Version]
- Yan, M.; Zhang, K.; Liu, D.; Yang, H.; Li, Z. Autonomous programming and adaptive filling of lap joint based on three-dimensional welding-seam model by laser scanning. J. Manuf. Process. 2020, 53, 396–405. [Google Scholar] [CrossRef]
- Patil, V.; Patil, I.; Kalaichelvi, V.; Karthikeyan, R. Extraction of Weld Seam in 3D Point Clouds for Real Time Welding Using 5 DOF Robotic Arm. In Proceedings of the 2019 5th International Conference on Control, Automation and Robotics (ICCAR), Beijing, China, 19–22 April 2019; pp. 727–733. [Google Scholar]
- Yang, L.; Liu, Y.; Peng, J.; Liang, Z. A novel system for off-line 3D seam extraction and path planning based on point cloud segmentation for arc welding robot. Robot. Comput.-Integr. Manuf. 2020, 64, 101929. [Google Scholar] [CrossRef]
- Gan, J.; Tao, Y. DBSCAN Revisited: Mis-Claim, Un-Fixability, and Approximation. In Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Victoria, Australia, 31 May–4 June 2015; pp. 519–530. [Google Scholar]
- Fischler, M.A.; Bolles, R.C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Commun. ACM 1981, 24, 381–395. [Google Scholar] [CrossRef]
- Ester, M.; Kriegel, H.P.; Sander, J.; Xu, X. A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Knowl. Discov. Data Min. 1996, 96, 226–231. [Google Scholar]
- Gunawan, A. A Faster Algorithm for DBSCAN. Master’s Thesis, Eindhoven University of Technology, Eindhoven, The Netherlands, 2013. [Google Scholar]
- Zhang, K.; Yan, M.; Huang, T.; Zheng, J.; Li, Z. 3D reconstruction of complex spatial weld seam for autonomous welding by laser structured light scanning. J. Manuf. Process. 2019, 39, 200–207. [Google Scholar] [CrossRef]
- Lancaster, P.; Salkauskas, K. Surfaces generated by moving least squares methods. Math. Comput. 1981, 37, 141–158. [Google Scholar] [CrossRef]
- Zheng, J.; Zhang, K.; Luo., Z.; Wang, Z. The hand-eye calibration of welding robot based on the constraint of spatial line. Trans. China Weld. Inst. 2018, 39, 108–113. [Google Scholar]
Parameters | Value |
---|---|
Welding method | gas metal arc welding (GMAW) |
Welding voltage (V) | 28 |
Welding current (A) | 290 |
Welding speed (mm/min) | 1000 |
Wire diameter (mm) | 1.2 |
Wire extension (mm) | 12 |
Welding materal | Q235 |
Thickness of the workpiece (mm) | 5 |
Shielding gas | 80%Ar + 20%CO2 |
Weld Seam | Error | X (mm) | Y (mm) | Z (mm) | Forward Vector (Degree) | Normal Vector (Degree) |
---|---|---|---|---|---|---|
Straight line | maximum error (ME) | 0.32 | 0.24 | 0.3 | 1.8 | 1.9 |
Straight line | mean square error (MSE) | 0.15 | 0.13 | 0.19 | 1.4 | 1.6 |
Polygonal line | ME | 0.31 | 0.33 | 0.22 | 1.9 | 1.6 |
Polygonal line | MSE | 0.14 | 0.18 | 0.13 | 1.2 | 1.1 |
Inflection point | error (E) | 0.41 | 0.46 | 0.42 |
Key Steps | Running Time (ms) |
---|---|
3D reconstruction | 35 (3D reconstruction computer, One frame of data processing time) |
Point cloud segmentation | 80 (point cloud data processing computer (PCDPC)) |
Feature extraction | 25 (PCDPC) |
Path fitting | 15 (PCDPC) |
The total time | 120 (PCDPC) |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hong, B.; Jia, A.; Hong, Y.; Li, X.; Gao, J.; Qu, Y. Online Extraction of Pose Information of 3D Zigzag-Line Welding Seams for Welding Seam Tracking. Sensors 2021, 21, 375. https://doi.org/10.3390/s21020375
Hong B, Jia A, Hong Y, Li X, Gao J, Qu Y. Online Extraction of Pose Information of 3D Zigzag-Line Welding Seams for Welding Seam Tracking. Sensors. 2021; 21(2):375. https://doi.org/10.3390/s21020375
Chicago/Turabian StyleHong, Bo, Aiting Jia, Yuxiang Hong, Xiangwen Li, Jiapeng Gao, and Yuanyuan Qu. 2021. "Online Extraction of Pose Information of 3D Zigzag-Line Welding Seams for Welding Seam Tracking" Sensors 21, no. 2: 375. https://doi.org/10.3390/s21020375
APA StyleHong, B., Jia, A., Hong, Y., Li, X., Gao, J., & Qu, Y. (2021). Online Extraction of Pose Information of 3D Zigzag-Line Welding Seams for Welding Seam Tracking. Sensors, 21(2), 375. https://doi.org/10.3390/s21020375