A STUDY ON DETECTING THE WELD SPOT FOR BUILDING AN AUTOMATIC WELDING ROBOT:

Long Trinh; Cong-Duy Do; Quang-Tu Ngo; Viet-Hoi Tran; Tien-Sy Nguyen

doi:10.5937/jaes0-55518

Van-Long Trinh School of Mechanical and Automotive Engineering, Hanoi University of Industry, 298 Caudien Street, Hanoi 10000, Vietnam
Cong-Duy Do School of Mechanical and Automotive Engineering, Hanoi University of Industry 298 Cau Dien str., Bac Tu Liem dist., Hanoi 10000, Hanoi, Vietnam
Quang-Tu Ngo School of Mechanical and Automotive Engineering, Hanoi University of Industry 298 Cau Dien str., Bac Tu Liem dist., Hanoi 10000, Hanoi, Vietnam
Viet-Hoi Tran School of Mechanical and Automotive Engineering, Hanoi University of Industry 298 Cau Dien str., Bac Tu Liem dist., Hanoi 10000, Hanoi, Vietnam
Tien-Sy Nguyen School of Mechanical and Automotive Engineering, Hanoi University of Industry 298 Cau Dien str., Bac Tu Liem dist., Hanoi 10000, Hanoi, Vietnam

DOI: https://doi.org/10.5937/jaes0-55518

Keywords: Industrial robot, automatic welding robot, deep learning network, artificial intelligence, sustainable development.

Abstract

The use of automatic welding robots has become an important trend in the industry. Applying this technology not only helps increase production efficiency but also reduces risks and labor costs. In this context, our study proposes an advanced method by incorporating the YOLOv8 deep learning network into an automatic welding robot. The task of the YOLOv8 model is to detect and monitor welds in real time through a camera system. This helps automate the welding process by providing information about the position and shape of the weld points. Welding coordinate values are transmitted and the welding tip is adjusted to target specific welding points, creating an efficient and precise automated welding process. The paper also hopes that this research will encourage the development and application of artificial intelligence (AI) in the field of welding. By combining welding technology and artificial intelligence, it is believed that the welding industry will continue to progress and modernize while contributing to the sustainable development of global manufacturing.

References

[1] Zhu, Y., He, X., Liu, Q., & Guo, W. (2022). Semiclosed-loop motion control with robust weld bead tracking for a spiral seam weld beads grinding robot. Robotics and Computer-Integrated Manufacturing, 73, 102254.
[2] Zhou, B., Liu, Y., Xiao, Y., Zhou, R., Gan, Y., & Fang, F. (2021). Intelligent guidance programming of welding robot for 3D curved welding seam. IEEE Access, 9, 42345-42357.
[3] Liu, J., Jiao, T., Li, S., Wu, Z., & Chen, Y. F. (2022). Automatic seam detection of welding robots using deep learning. Automation in Construction, 143, 104582.
[4] Liu, W., Ma, L., & Wang, J. (2018). Detection of multiclass objects in optical remote sensing images. IEEE Geoscience and Remote Sensing Letters, 16(5), 791-795.
[5] HONG, Zhonghua, et al. Multi-scale ship detection from SAR and optical imagery via a more accurate YOLOv3. IEEE Journal of Selected Topics in Applied Earth Observa-tions and Remote Sensing, 2021, 14: 6083-6101.
[6] Yang, Z., Xu, Z., & Wang, Y. (2022). Bidirection-fusion-YOLOv3: An improved method for insulator defect detection using UAV image. IEEE Transactions on Instrumentation and Measurement, 71, 1-8.
[7] Kumar, C., & Punitha, R. (2020, August). Yolov3 and yolov4: Multiple object detection for surveillance applications. In 2020 Third international conference on smart systems and inventive technology (ICSSIT) (pp. 1316-1321). IEEE.
[8] Anwar, N., Shen, Z., Wei, Q., Xiong, G., Ye, P., Li, Z., ... & Zhao, H. (2021, September). YOLOv4 based deep learning algorithm for defects detection and classification of rail surfaces. In 2021 IEEE International Intelligent Transportation Systems Conference (ITSC) (pp. 1616-1620). IEEE.
[9] Yijing, W., Yi, Y., Xue-fen, W., Jian, C., & Xinyun, L. (2021, May). Fig fruit recognition method based on YOLO v4 deep learning. In 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) (pp. 303-306). IEEE.
[10] Yung, N. D. T., Wong, W. K., Juwono, F. H., & Sim, Z. A. (2022, October). Safety helmet detection using deep learning: Implementation and comparative study using YOLOv5, YOLOv6, and YOLOv7. In 2022 International Conference on Green Energy, Computing and Sustainable Technology (GECOST) (pp. 164-170). IEEE.
[11] Jabnouni, H., Arfaoui, I., Cherni, M. A., Bouchouicha, M., & Sayadi, M. (2023, October). YOLOv6 for Fire Images detection. In 2023 International Conference on Cyberworlds (CW) (pp. 500-501). IEEE.
[12] Dewi, C., Chen, A. P. S., & Christanto, H. J. (2023, March). YOLOv7 for face mask identification based on deep learning. In 2023 15th International Conference on Computer and Automation Engineering (ICCAE) (pp. 193-197). IEEE.
[13] AFDHAL, Saddami, et al. Real-Time Object Detection Performance of YOLOv8 Models for Self-Driving Cars in a Mixed Traffic Environment. In: 2023 2nd International Conference on Computer System, Information Technology, and Electrical Engineering (COSITE). IEEE, 2023. p. 260-265.
[14] Rivas, D., Quiza, R., Rivas, M., & Haber, R. E. (2020). Towards sustainability of manufacturing processes by multiobjective optimization: A case study on a submerged arc welding process. IEEE Access, 8, 212904-212916.