| 2026 №03 (03) |
DOI of Article 10.37434/as2026.03.04 |
2026 №03 (05) |
"Avtomatychne Zvaryuvannya" (Automatic Welding), #3, 2026, pp. 23-33
Application of visual inspection method for weld quality metal assessment
O.S. Kostenevych
, A.S. Novodranov
E.O. Paton Electric Welding Institute of the NAS of Ukraine
11 Kazymyr Malevych Str., 03150, Kyiv, Ukraine.
E-mail: artur19940731@gmail.com
КQuality testing of welded joints is one of the main factors in ensuring the reliability and durability of welded structures. Even minor defects in the weld can cause a loss of the bearing capacity of the structure. Considering the dependence of manual welding quality on the welder’s skill, transitioning to robotic welding production is advisable. However, this approach requires automation of the relevant non-destructive testing systems. When conducting automated visual-optical quality testing of welded joints, the degree of danger of the detected defect is assessed according to applicable standards. In addition, permissible sizes of surface defects can be determined using fracture mechanics-based calculations, taking into account operating load conditions. The paper compares these two approaches and also formulates requirements for the visual-optical NDT method for welded side frame of a railway freight car bogie based on calculated allowable defect sizes. The visual-optical method of testing welded joints is capable of detecting only surface defects, which can be conservatively considered as surface elliptical cracks and evaluated using fracture mechanics methods. The results of the study prove that the visual-optical NDT method is an eff ective tool for the primary diagnosis of critical welded structures. 17 Ref., 5 Tabl., 10 Fig.
Keywords: welded joints, welded structures, freight car bogie, side frame, stress-strain state, load spectrum, mathematical modelling, fatigue resistance, permissible defect sizes, visual-optical testing
Received: 22.02.2026
Received in revised form: 10.04.2026
Accepted: 14.05.2026
Posted online 20.05.2026
References
1. Martyniuk, R.T. (2025) Main defects of welded joints. Oil and Gas Power Engineering, 1(43), 109-116. https://doi.org/10.31471/1993-9868-2025-1(43)-109-1162. Makhnenko, V.I. (2006) Resource for safe operation of welded joints and units of modern structures. Kyiv, Naukova Dumka [in Russian].
3. IIW XIII-1539-96/XV-845-96. Recommendations for Fatigue Design of Welded Joints and Components.
4. Makhnenko, V.I., Pochinok, V.E. (2006) Strength calculation of welded joints with crack-like imperfections. PWI.
5. Lobanov, L.M., Makhnenko, O.V., Knysh, V.V., Solovej, S.A., Pavlovskyi, V.I. (2020) Development of welded structure of side frame of freight car bogie of increased reliability. The Paton Welding J., 3, 13-18. https://doi.org/10.37434/tpwj2020.03.02
6. DSTU 7598:2014: Freight wagons. General requirements for calculations and design of new and modernized 1520 mm gauge (non-self-propelled) wagons [in Ukrainian].
7. Ren, Z., Fang, F., Yan, N. et al. (2022) State of the art in defect detection based on machine vision. Int. J. of Precis. Eng. and Manuf.-Green Tech, 9, 661-691. https://doi.org/10.1007/s40684-021-00343-6
8. Diaz-Cano I, Morgado-Estevez A, Rodríguez Corral JM et al. (2025) Automated fillet weld inspection based on deep learning from 2D images. Applied Sciences, 15(2), 889. https://doi.org/10.3390/app15020899
9. Elhendawy, G.A., El-Taybany, Y. (2025) Machine vision-assisted welding defect detection system with convolutional neural networks. Int. J. Precis. Eng. Manuf., 26, 3185-3194. https://doi.org/10.1007/s12541-025-01281-y
10. Chou, P.-H., Wang, C.-C., Mao, W.-L. (2024) YOLO-based defect detection for metal sheets. 2024 IEEE Int. Conf. on Imaging Systems and Techniques (IST), 1-5. https://doi.org/10.1109/IST63414.2024.10759237
11. Yun J., Shin W., Koo G., Kim M., Lee C., Lee S. (2020) Automated defect inspection system for metal surfaces based on deep learning and data augmentation. J. of Manufacturing Systems, 55, 317-324. https://doi.org/10.1016/j.jmsy.2020.03.009
12. Hou, C., Kang, Y., Qiao, T. (2025) Multi-camera hierarchical calibration and three-dimensional reconstruction method for bulk material transportation system. Sensors, 25(7), 2111. https://doi.org/10.3390/s25072111
13. Carnegie Mellon University. Camera Matrix and Projection, Course Notes 2017. https://www.cs.cmu.edu/~16385/s17/ Slides/11.1_Camera_matrix.pdf
14. DSTU EN ISO 5817:2022: Welding. Welds during fusion welding of steel, nickel, titanium and other alloys (except beam welding). Quality levels depending on defects (EN ISO 5817:2014, IDT; ISO 5817:2014, IDT) [in Ukrainian].
15. Hobbacher, A. (1994) Stress intensity factors of welded joints. Eng. Fracture Mech., 46(2), 173-182. https://doi.org/10.1016/0013-7944(93)90278-Z
16. Savrukh, M.P. (1988) Fracture mechanics and strength of materials: A reference manual. Pt 2. Stress intensity factors in bodies with cracks. Ed. by V.V. Panasyuk. Kyiv, Naukova Dumka [in Russian].
17. МР-125-01-90. Calculation of stress intensity factors and cross-sectional weakening factors for defects in welded joints. Kyiv [in Russian].
This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Suggested Citation
O.S. Kostenevych, A.S. Novodranov (2026) pplication of visual inspection method for weld quality metal assessment. Automatic Welding, 03, 23-33. https://doi.org/10.37434/as2026.03.04Advertising in this issue:
