WeldNet: A voxel-based deep learning network for point cloud annular weld seam detection
Source abstract
Abstract
Weld seam detection is an important part of automated welding. At present, few studies have been conducted on annular weld seams, and a lot of defects exist in the point cloud model of the tube sheet obtained by RGB-D cameras and photography methods. Aiming at the above problems, this paper proposed an annular weld seam detection network named WeldNet where a voxel feature encoding layer was adaptively improved for annular weld seams, the sparse convolutional network and region proposal network (RPN) were used to detect annular weld seam position, and an annular weld seam detection loss function was designed. Further, an annular weld seam dataset was established to train the network. Compared with the random sampling consistency (RANSAC) method, WeldNet has a higher detection accuracy, as well as a higher detection success rate which has increased by 23%. Compared with U-Net, WeldNet has been proven to achieve a better detection result, and the intersection over the union of the weld seam detection is improved by 17.8%.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · 3D Surveying and Cultural Heritage · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Wang B, Hu S J, Sun L, et al. Intelligent welding system technologies: State-of-the-art review and perspectives. J Manuf Syst, 2020, 56: 373–39110.1016/j.jmsy.2020.06.020 ↗
2. Yang L, Liu Y, Peng J. Advances techniques of the structured light sensing in intelligent welding robots: A review. Int J Adv Manuf Technol, 2020, 110: 1027–104610.1007/s00170-020-05524-2 ↗
3. Li J, Jin S, Wang C, et al. Weld line recognition and path planning with spherical tank inspection robots. J Field Robotics, 2022, 39: 131–15210.1002/rob.22042 ↗
4. Vithanage R K W, Mohseni E, Qiu Z, et al. A phased array ultrasound roller probe for automated in-process/interpass inspection of multipass welds. IEEE Trans Ind Electron, 2021, 68: 12781–1279010.1109/TIE.2020.3042112 ↗
5. Yang L, Liu Y, Peng J, et al. A novel system for off-line 3D seam extraction and path planning based on point cloud segmentation for arc welding robot. Robotics Comput-Integrated Manuf, 2020, 64: 10192910.1016/j.rcim.2019.101929 ↗
6. Fan J, Deng S, Ma Y, et al. Seam feature point acquisition based on efficient convolution operator and particle filter in GMAW. IEEE Trans Ind Inf, 2021, 17: 1220–123010.1109/TII.2020.2977121 ↗
7. Fan J, Deng S, Jing F, et al. An initial point alignment and seam-tracking system for narrow weld. IEEE Trans Ind Inf, 2020, 16: 877–88610.1109/TII.2019.2919658 ↗
8. Ma Y, Fan J, Yang H, et al. An efficient and robust complex weld seam feature point extraction method for seam tracking and posture adjustment. IEEE Trans Ind Inf, 2023, 19: 10704–1071510.1109/TII.2023.3241595 ↗
9. Ma Y, Fan J, Zhou Z, et al. WeldNet: A deep learning based method for weld seam type identification and initial point guidance. Expert Syst Appl, 2024, 238: 12170010.1016/j.eswa.2023.121700 ↗
10. Wen W W, Zhang G, Hsu L T. GNSS NLOS exclusion based on dynamic object detection using LiDAR point cloud. IEEE Trans Intell Transp Syst, 2021, 22: 853–86210.1109/TITS.2019.2961128 ↗
11. Lin G, Tang Y, Zou X, et al. Color-, depth-, and shape-based 3D fruit detection. Precision Agric, 2020, 21: 1–1710.1007/s11119-019-09654-w ↗
12. Stular B, Eichert S, Lozic E. Airborne LiDAR point cloud processing for archaeology. pipeline and QGIS toolbox. Remote Sens, 2021, 13: 322510.3390/rs13163225 ↗
13. Zanjani F G, Pourtaherian A, Zinger S, et al. Mask-MCNet: Tooth instance segmentation in 3D point clouds of intra-oral scans. Neurocomputing, 2021, 453: 286–29810.1016/j.neucom.2020.06.145 ↗
14. Gao J, Li F, Zhang C, et al. A method of D-type weld seam extraction based on point clouds. IEEE Access, 2021, 9: 65401–6541010.1109/ACCESS.2021.3076006 ↗
15. Geng Y, Zhang Y, Tian X, et al. A method ofwelding path planning of steel mesh based on point cloud for welding robot. Int J Adv Manuf Technol, 2021, 116: 2943–295710.1007/s00170-021-07601-6 ↗
16. Hong B, Jia A, Hong Y, et al. Online extraction ofpose information of 3D zigzag-line welding seams for welding seam tracking. Sensors, 2021, 21: 37510.3390/s21020375 ↗
17. Kim J, Lee J, Chung M, et al. Multiple weld seam extraction from RGB-depth images for automatic robotic welding via point cloud registration. Multimed Tools Appl, 2021, 80: 9703–971910.1007/s11042-020-10138-7 ↗
18. Zhou P, Peng R, Xu M, et al. Path planning with automatic seam extraction over point cloud models for robotic arc welding. IEEE Robot Autom Lett, 2021, 6: 5002–500910.1109/LRA.2021.3070828 ↗
19. Chen L, Li X, Zhou X. A 3D seam extraction and tracking method based on binocular structured light sensor. In: Twelfth International Conference on Digital Image Processing (ICDIP 2020). Osaka, 2020. 7210.1117/12.2573270 ↗
20. Ou J, Zou L, Wan Q H, et al. Weld-seam identification and model reconstruction of remanufacturing blade based on three-dimensional vision. Adv Eng Inf, 2021, 49: 10130010.1016/j.aei.2021.101300 ↗
21. Liu C, Wang H, Huang Y, et al. Welding seam recognition and tracking for a novel mobile welding robot based on multi-layer sensing strategy. Meas Sci Technol, 2022, 33: 05510910.1088/1361-6501/ac3d06 ↗
22. Zou Y, Chen J, Wei X. Research on a real-time pose estimation method for a seam tracking system. Optics Lasers Eng, 2020, 127: 10594710.1016/j.optlaseng.2019.105947 ↗
23. Feng H, Ren X, Li L, et al. A novel feature-guided trajectory generation method based on point cloud for robotic grinding of freeform welds. Int J Adv Manuf Technol, 2021, 115: 1763–178110.1007/s00170-021-07095-2 ↗
24. Rodriguez-Gonzalvez P, Rodriguez-Martin M. Weld bead detection based on 3D geometric features and machine learning approaches. IEEE Access, 2019, 7: 14714–1472710.1109/ACCESS.2019.2891367 ↗
25. Ma Y, Fan J, Yang H, et al. A fast and robust seam tracking method for spatial circular weld based on laser visual sensor. IEEE Trans Instrum Meas, 2021, 70: 1–11
26. Tan Y Z, Pang C K, Al Mamun A, et al. Precise pose and assembly detection of generic tubular joints based on partial scan data. Neural Comput Applic, 2022, 34: 5201–521110.1007/s00521-021-06246-6 ↗
27. Wen C, Li X, Yao X, et al. Airborne LiDAR point cloud classification with global-local graph attention convolution neural network. ISPRS J Photogrammetry Remote Sens, 2021, 173: 181–19410.1016/j.isprsjprs.2021.01.007 ↗
28. Teng X, Zhou G, Wu Y, et al. Three-dimensional reconstruction method of rapeseed plants in the whole growth period using RGB-D camera. Sensors, 2021, 21: 462810.3390/s21144628 ↗
29. Bao Y, Lin P, Li Y, et al. Parallel structure from motion for sparse point cloud generation in large-scale scenes. Sensors, 2021, 21: 393910.3390/s21113939 ↗
30. Wang H, Lei T, Rong Y, et al. Arc length stable method of GTAW based on adaptive Kalman filter. J Manuf Processes, 2021, 63: 130–13810.1016/j.jmapro.2020.01.029 ↗
31. Wang H, Xu J, Huang Y, et al. Multilayer positioning strategy for tubesheet welding robot based on point cloud model. IEEE Sens J, 2023, 23: 13728–1373710.1109/JSEN.2023.3273622 ↗
32. Ji X, Zhang X, Hu H. Point cloud segmentation for complex microsurfaces based on feature line fitting. Multimed Tools Appl, 2021, 80: 4553–457810.1007/s11042-020-09910-6 ↗
33. Fan J, Ma L, Sun A, et al. An approach for extracting curve profiles based on scanned point cloud. Measurement, 2020, 149: 10702310.1016/j.measurement.2019.107023 ↗
34. Kuzelka K, Slavik M, Surový P. Very high density point clouds from UAV laser scanning for automatic tree stem detection and direct diameter measurement. Remote Sens, 2020, 12: 123610.3390/rs12081236 ↗
35. Lafiosca P, Fan I S, Avdelidis N P. Automatic segmentation of aircraft dents in point clouds. SAE Paper 2022-01-0022, 202210.4271/2022-01-0022 ↗
36. Xu Y, Tong X, Stilla U. Voxel-based representation of 3D point clouds: Methods, applications, and its potential use in the construction industry. Automation Construction, 2021, 126: 10367510.1016/j.autcon.2021.103675 ↗
37. Zhou Y, Tuzel O. VoxelNet: End-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, 2018. 4490–449910.1109/CVPR.2018.00472 ↗
38. Graham B. Submanifold Sparse Convolutional Networks. arXiv: 1706.01307
39. Schnabel R, Wahl R, Klein R. Efficient RANSAC for point-cloud shape detection. Comput Graphics Forum, 2007, 26: 214–22610.1111/j.1467-8659.2007.01016.x ↗
40. Qi C R, Yi L, Su H, et al. PointNet plus plus: Deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017
41. Shi S, Guo C, Jiang L, et al. PV-RCNN: Point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 10526–10535