Reconstruction of optimal weld seam trajectory for three axis robot using deep learning and quadratic regression approaches
,
,
,
and
*
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
This study proposes a method for the integration of a segmentation model with non-linear regression to construct weld-seam trajectories. First, the weld is precisely segmented using the YOLOv8 model. Then, its boundary pixels are extracted right after and termed SEG points. The 48, 24, and 16 SEG points are utilized as the input for regression models to estimate the weld seam center-line. Both linear and non-linear (quadratic) regression models are assessed using different types of weld images. The experimental results show that the average segmentation performance and training accuracy of the YOLO model are 94%. Additionally, both linear- and nonlinear regression models can estimate similar weld seam profiles. It is worth noting that the more the SEG points are utilized, the higher the accuracy is. However, if a number of SEG points increase, the processing time increases too. Therefore, 24 SEG points are enough for the precise estimation of the weld seam trajectory. It demonstrated that the proposed approach achieves a mean absolute trajectory error of 0.24 mm at 2.9 FPS for the end-to-end pipeline by using the Ampere GPU of NVIDIA Jetson Nano (input 416×416, FP16). Moreover, estimated weld seam trajectory is transformed into the absolute coordinate for...
Article Details
Conflict of Interest
© 2026 The authors. This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License.
References
Aboulhosn, Z., Musamih, A., Salah, K., Jayaraman, R., Omar, M., & Aung, Z. (2024). detection Detection of manufacturing defects in steel using deep learning with explainable artificial intelligence. IEEE Access, 12, 99240–99257. https://doi.org/10.1109/ACCESS.2024.3430113
Burger, W. (2016). zhang's Zhang's camera calibration algorithm: in-depth tutorial and implementation. Technical Report HGB16-05. University of Applied Sciences Upper Austria. https://doi.org/10.13140/RG.2.1.1166.1688/1
Chen, G., Zhang, Y., Ai, Y., Yu, B., & Xu, W. (2025). Real-time seam extraction using laser vision sensing: hybrid approach with dynamic ROI and optimized RANSAC. Sensors, 25(11), 3268. https://doi.org/10.3390/s25113268
Deepak, J. R., Bupesh Raja, V. K., Srikanth, D., Surendran, H., & Nickolas, M. M. (2021). Non-destructive testing (NDT) techniques for low carbon steel welded joints: A review and experimental study. Materials Today: Proceedings, 44, 3732–3737. https://doi.org/10.1016/j.matpr.2020.11.578
Ding, K., Niu, Z., Hui, J., Zhou, X., & Chan, F.T.S. (2022). A weld surface defect recognition method based on improved MobileNetV2 algorithm. Mathematics, 10, 3678. https:// doi.org/10.3390/math10193678
Gao, A., Fan, Z., Li, A., Le, Q., Wu, D., & Du, F. (2023). YOLO-Weld: A modified YOLOv5-based weld feature detection network for extreme weld noise. Sensors, 23(12), 5640. https://doi.org/10.3390/s23125640
Hashim, M. H. M., Arifin, A. M. B. T., AzmirOsman, S., Osman, S. A., Kiat, T. S., & Salihin. A. F. M. (2024). Study on MIG and TIG weldment behaviour using finite element approach. Journal of Advanced Research in Applied Sciences and Engineering Technology, 46(2), 81–89. https://doi.org/10.37934/araset.46.2.8189
Jolly, M., Prabhakar, A., Sturzu, B., Hollstein, K., Singh, R., Thomas, S., Foote, P., & Shaw, A. (2015). Review of non-destructive testing (NDT) techniques and their applicability to thick walled composites. Procedia CIRP, 38, 129–136. https://doi.org/10.1016/j.procir.2015.07.043
Kumaresan, S., Aultrin, K. S. J., Kumar, S. S., & Dev Anand, M. (2023). Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning. International Journal on Interactive Design and ManufacturingInt J Interact Des Manuf, 17, 2999–3010. https://doi.org/10.1007/s12008-023-01327-3
Kwon, J. E., Park, J. H., Kim, J. H., Lee, Y. H., & Cho, S. I. (2023). Context and scale-aware YOLO for welding defect detection. NDT & E International, 139, 102919. https://doi.org/10.1016/j.ndteint.2023.102919
Lappin, E., Oubre, J., Gurau V., & Taheri, H. (2025). Automated Robotic and AI-Driven Nondestructive Inspection for Enhanced Welding Flaw Detection, The 6th International Conference on Artificial Intelligence, Robotics and Control (AIRC), Savannah, GA, USA, (pp. 99-106). https://doi.org/10.1109/AIRC64931.2025.11077497.
Lei, T., Rong, Y., Wang, H., Huang, Y., & Li, M. (2020). A review of vision-aided robotic welding. Computers in Industry, 123, 103326. https://doi.org/10.1016/j.compind.2020.103326
Li, A., Li, D., & Wang, A. (2025). A two-stage YOLOv5s–U-Net framework for defect localization and segmentation in overhead transmission lines. Sensors, 25(9), 2903. https://doi.org/10.3390/s25092903
Li, M., Huang, J., Xue, L., & Zhang, R. (2023). A guidance system for robotic welding based on an improved YOLOV5 algorithm with a realsense depth camera. Research Square Platform LLC. https://doi.org/10.21203/rs.3.rs-3256246/v1
Li, X., Li, X., Ge, S. S., Khyam, M. O., & Luo, C. (2017). Automatic welding seam tracking and identification. IEEE Transactions on Industrial Electronics, 64(9), 7261–7271. https://doi.org/10.1109/TIE.2017.2694399
Liu, M., Chen, Y., Xie, J., He, L., & Zhang, Y. (2023). LF-YOLO: A lighter and faster yolo for weld defect detection of X-Ray image. IEEE Sensors Journal, 23(7), 7430–7439. https://doi.org/10.1109/JSEN.2023.3247006
Liu, Y., Yuan, K., Li, T., Li, S., & Ren, Y. (2022). NDT method for line laser welding based on deep learning and one-dimensional time-series data. Applied Sciences, 12(15), 7837. https://doi.org/10.3390/app12157837
Mirapeix, J., García-Allende, P. B., Cobo, A., Conde, O. M., & López-Higuera, J. M. (2007). Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks. NDT & E International, 40(4), 315-323. https://doi.org/10.1016/j.ndteint.2006.12.001
Nguyen D. T. & Nguyen H. -D. (2024). Application of a 3-axis robot arm combined with a camera supports automatic weld data collection. TNU Journal of Science and Technology, 229(14), 43 - 51. https://doi.org/10.34238/tnu-jst.10782
Nguyen, H.-D., Le, H.-D., Nguyen, V. K., & Lam, H. M. (2024). Development of the intelligent traffic light system based on image processing and fuzzy control techniques. CTU Journal of Innovation and Sustainable Development, 16(3), 9-20. https://doi.org/10.22144/ctujoisd.2024.302
Oh, S., Jung, M., Lim, C., & Shin, S. (2020). Automatic detection of welding defects using faster R-CNN. Applied Sciences, 10(23), 8629. https://doi.org/10.3390/app10238629
Penekalapati, S. V., Ramana, E. V., & Kumar, N. K. (2022). Automatic detection of sub-surface weld defects using machine learning approach. 2022 International Conference on Recent Trends in Microelectronics, Automation, Computing and Communications Systems (ICMACC) (pp. 412–415). https://doi.org/10.1109/ICMACC54824.2022.10093625
Qadoori, B. , Alaiwi, Y., Mahmoud, S. , Jundi, A., & Mulki, H. (2025). Trajectory tracking control of KUKA KR 6 R900-2 robotic arm for welding applications. Journal of Advanced Research in Applied Sciences and Engineering Technology, 64(1), 140–152. https://doi.org/10.37934/araset.64.1.140152
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779–788). https://doi.org/10.1109/CVPR.2016.91
Sapkota, R., Ahmed, D., & Karkee, M. (2024). Comparing YOLOv8 and mask R-CNN for instance segmentation in complex orchard environments. Artificial Intelligence in Agriculture, 13, 84–99. https://doi.org/10.1016/j.aiia.2024.07.001
Sarker, I. H. (2021). Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions. SN Computer Science, 2, 420. https://doi.org/10.1007/s42979-021-00815-1
Shaloo, M., Schnall, M., Klein, T., Huber, N., & Reitinger, B. (2022). A review of non-destructive testing (NDT) techniques for defect detection: application to fusion welding and future wire arc additive manufacturing processes. Materials, 15(10), 3697. https://doi.org/10.3390/ma15103697
Soares, L. B., Weis, A. A., Rodrigues, R. N., & Da C. Botelho, S. S. (2019). A robotic passive vision system for texture analysis in weld beads. 2019 IEEE 17th International Conference on Industrial Informatics (INDIN) (pp. 535–540). https://doi.org/10.1109/INDIN41052.2019.8972289
Sun, H., Xia, L., Zhou, Y., Qian, W., Wang, W., & Zhang, K. (2024). Online detection and evaluation of weld surface defects based on lightweight network VGG16-UNet and laser scanning. Journal of Manufacturing Processes, 129, 292-306, https://doi.org/10.1016/j.jmapro.2024.08.037.
Terven, J., & Cordova-Esparza, D. -M. (2023). A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond. Machine Learning and Knowledge Extraction, 5, 1680-1716. https://doi.org/10.3390/make5040083
Xu, X., & Li, X. (2024). Research on surface defect detection algorithm of pipeline weld based on YOLOv7. Scientific Reports, 14, 1881. https://doi.org/10.1038/s41598-024-52451-3
Yuan, L., Chen, Y., Tang, H., Gao R., & Wu, W. (2024). A lightweight deep-learning algorithm for welding defect detection in new energy vehicle battery current collectors. IEEE Sensors Journal, 24(13), 21655-21668, doi: 10.1109/JSEN.2024.3398769
Zhang, Y., & Ni, Q. (2023). A novel weld-seam defect detection algorithm based on the S-YOLO model. Axioms, 12(7), 7. https://doi.org/10.3390/axioms12070697
Zhang, Y., Guo, Z., Wu, J., Tian, Y., Tang, H., & Guo, X. (2022). Real-time vehicle detection based on improved YOLO v5. Sustainability, 14(19), 12274. https://doi.org/10.3390/su141912274
Zhao, M., Liu, X., Wang, K., Liu, Z., Dong, Q., Wang, P., & Su, Y. (2024). Welding seam tracking and inspection robot based on improved YOLOv8s-Seg model. Sensors, 24(14), 4690. https://doi.org/10.3390/s24144690
Zhao, M., Liu, X., Wang, K., Liu, Z., Dong, Q., Wang, P., & Su, Y. (2024). Welding seam tracking and inspection robot based on improved YOLOv8s-Seg model. Sensors, 24(14), 4690. https://doi.org/10.3390/s24144690
Zhou, J., Zhang, W., Sui, X., & Chen, Y. (2024). Welding defect detection based on YOLOv8. Journal of Physics: Conference Series, 2816(1), 012045. https://doi.org/10.1088/1742-6596/2816/1/012045
Zou, Y., & Wan, Y. (2024). Robotic seam tracking system combining lightweight segmentation network design and ADMM-based structured pruning. IEEE Transactions on Instrumentation and Measurement, 73, 1–15. https://doi.org/10.1109/TIM.2024.3381666