Automatic Segmentation of Gas Metal Arc Welding for Cleaner Productions
Source abstract
Abstract
In the industry, the robotic gas metal arc welding (GMAW) process has a huge range of applications, including in the automotive sector, construction companies, the shipping industry, and many more. Automatic quality inspection in robotic welding is crucial because it ensures the uniformity, strength, and safety of welded joints without the need for constant human intervention. Detecting defects in real time prevents defective products from reaching advanced production stages, reducing reprocessing costs. In addition, the use of materials is optimized by avoiding defective welds that require rework, contributing to cleaner production. This paper presents a novel dataset of robot GMAW images for experimental purposes, including human-expert segmentation and human knowledge labeling regarding the different errors that may appear in welding. In addition, it tests an automatic segmentation approach for robot GMAW quality assessment. The results presented confirm that automatic segmentation is comparable to human segmentation, guaranteeing a correct welding quality assessment to provide feedback on the robot welding process.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Advanced machining processes and optimization · Additive Manufacturing Materials and Processes
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Escuela Superior de Ingeniería Mecánica y Eléctrica Unidad Culhuacan, Instituto Politécnico Nacional, Av. Sta. Ana 1000, San Francisco Culhuacan, Culhuacan CTM V, Coyoacán, Mexico City 04440, Mexico
Escuela Superior de Ingeniería Mecánica y Eléctrica Unidad Azcapotzalco, Instituto Politécnico Nacional, Av. de las Granjas, Mexico City 02550, Mexico
Centro de Innovación y Desarrollo Tecnológico en Cómputo, Instituto Politécnico Nacional, Juan de Dios Bátiz s/n, Gustavo A. Madero, Mexico City 07700, Mexico
References (39)
Show source-provided references
1. Moinuddin, S.Q., Saheb, S.H., Dewangan, A.K., Cheepu, M.M., and Balamurugan, S. (2024). Automation in the Welding Industry: Incorporating Artificial Intelligence, Machine Learning and Other Technologies, John Wiley & Sons.10.1002/9781394172948 ↗
2. Diaz-Cano, I., Morgado-Estevez, A., Rodríguez Corral, J.M., Medina-Coello, P., Salvador-Dominguez, B., and Alvarez-Alcon, M. (2025). Automated fillet weld inspection based on deep learning from 2D images. Appl. Sci., 15.10.3390/app15020899 ↗
3. Li, H., Ma, Y., Duan, M., Wang, X., and Che, T. (2023). Defects detection of GMAW process based on convolutional neural network algorithm. Sci. Rep., 13.10.1038/s41598-023-48698-x ↗
4. Application of Deep Learning for the Identification of Surface Defects Used in Manufacturing Quality Control and Industrial Production: A Literature Review
5. A low-cost vision-based weld-line detection and measurement technique for robotic welding10.1080/0951192X.2024.2314784 ↗
6. Kim, D.-Y., Lee, H.W., Yu, J., and Park, J.-K. (2024). Application of Convolutional Neural Networks for Classifying Penetration Conditions in GMAW Processes Using STFT of Welding Data. Appl. Sci., 14.10.3390/app14114883 ↗
7. Kralj, V. (1968). Biocybernetic Investigations of Hand Movements of Human Operator in Hand Welding, International Institute of Welding.
8. Kim, D.-Y., and Yu, J. (2024). Evaluation of Continuous GMA Welding Characteristics Based on the Copper-Plating Method of Solid Wire Surfaces. Metals, 14.10.3390/met14111300 ↗
9. Application of microcomputers to automatic weld quality control10.1115/1.3149598 ↗
10. Artificial neural network controlled GMAW system: Penetration and quality assurance in a multi-pass butt weld application10.1007/s00170-019-04424-4 ↗
11. Penttilä, S., Lund, H., and Skriko, T. (2023). Possibilities of artificial intelligence-enabled feedback control system in robotized gas metal arc welding. J. Manuf. Mater. Process., 7.10.3390/jmmp7030102 ↗
12. Reisgen, U., Mann, S., Oster, L., Gött, G., Sharma, R., and Uhrlandt, D. (2020, January 20–21). Study on identifying GMAW process deviations by means of optical and electrical process data using ANN. Proceedings of the IEEE 16th International Conference on Automation Science and Engineering (CASE), Hong Kong, China.10.1109/CASE48305.2020.9216744 ↗
13. Njock Bayock, F., Nlend, R., Mbou Tiaya, E., Appiah Kesse, M., Kamdem, B., and Kah, P. (2025). Development of an Artificial Intelligence-Based Algorithm for Predicting the Mechanical Properties of Weld Joints of Dissimilar S700MC-S960QC Steel Structures. Civ. Eng. Infrastruct. J., in press.
14. Burn-through prediction and weld depth estimation by deep learning model monitoring the molten pool in gas metal arc welding with gap fluctuation10.1016/j.jmapro.2020.10.019 ↗
15. Real-time recognition of arc weld pool using image segmentation network10.1016/j.jmapro.2021.10.019 ↗
16. Enriquez, M.L., Concepcion, R., Relano, R.-J., Francisco, K., Mayol, A.P., Española, J., Vicerra, R.R., Bandala, A., Co, H., and Dadios, E. (2021, January 28–30). Prediction of Weld Current Using Deep Transfer Image Networks Based on Weld Signatures for Quality Control. Proceedings of the 2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), Manila, Philippines.10.1109/HNICEM54116.2021.9731979 ↗
17. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
18. Convolutional networks with dense connectivity10.1109/TPAMI.2019.2918284 ↗
19. Tan, M., and Le, Q. (2019, January 9–15). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
20. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
21. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18–23). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
22. Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018, January 18–23). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00907 ↗
23. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
24. Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.195 ↗
25. Enhanced automatic weld seam tracking: Bayesian optimization and information-based pruning of compact denoising and object detection models10.1016/j.eswa.2024.126132 ↗
26. Jocher, G. (2025, February 19). Ultralytics YOLOv5, Version 7.0. Available online: https://docs.ultralytics.com/models/yolov5/#citations-and-acknowledgements.
27. Generative adversarial networks (GAN) model for dynamically adjusted weld pool image toward human-based model predictive control (MPC)10.1016/j.jmapro.2025.02.053 ↗
28. A fuzzy logic system for process monitoring and quality evaluation in GMAW
29. Geometries and quality assesment of weld beads in 5052-H32 aluminum alloys joined by semiautomated GMAW through a double fuzzy system10.1007/s00170-023-12337-6 ↗
30. An artificial intelligence system for quality level–based prediction of welding parameters for robotic gas metal arc welding10.1007/s00170-024-13518-7 ↗
31. Chen, T., Xue, S., Wang, B., Zhai, P., and Long, W. (2019). Study on short-circuiting GMAW pool behavior and microstructure of the weld with different waveform control methods. Metals, 9.10.3390/met9121326 ↗
32. Preliminary Study of Bead-On-Plate Welding Bead Geometry for 316L Stainless Steel Using GMAW10.5937/fme2404563W ↗
33. Heterogeneous Measurement System for Data Mining Robotic GMAW Weld Quality10.29391/2022.101.008 ↗
34. Online defect detection and penetration estimation system for gas metal arc welding10.1007/s00170-024-14932-7 ↗
35. Acoustic emission exposes cracks during welding (Acoustic emission from welds in stainless steel plates used for detecting defects in single and multiple pass machine welds)
36. Robotic welding system for adaptive process control in gas metal arc welding10.1007/s40194-024-01756-y ↗
37. Kim, G.-G., Kim, Y.-M., Kim, D.-Y., Park, J.-K., Park, J., and Yu, J. (2024). Vision-Based Online Molten Pool Image Acquisition and Assessment for Quality Monitoring in Gas-Metal Arc Welding. Appl. Sci., 14.10.3390/app14145998 ↗
38. Vision-based seam tracking for GMAW fillet welding based on keypoint detection deep learning model10.1016/j.jmapro.2024.03.006 ↗
39. Structural similarity index (SSIM) revisited: A data-driven approach10.1016/j.eswa.2021.116087 ↗