APPLICATION OF COMPUTER VISION TO DETECT DEFECTS IN WELDS
Main Article Content
Abstract
In the context of increasing wear and tear of utility pipelines, improving the quality of diagnostics of their technical condition, as well as improving the quality of control over construction and repair work, is of particular importance. Timely detection of defects and damage helps prevent emergency situations and negative socio-economic and environmental consequences. Traditional methods of visual and instrumental control have a number of disadvantages, in particular, high labor intensity, long information processing time, and insufficient accuracy. This problem can be solved by using computer vision to identify and classify damage, which will improve the quality of defect detection, reduce the likelihood of human error, and speed up the diagnostic process. However, different levels of readiness of the developed machine learning algorithms require additional research to confirm the effectiveness of their use in professional fields, for example, when inspecting structures, which justifies the relevance of this study. The object of the study was the YOLO family of computer vision models capable of identifying various classes of defects. The aim of the study was to train the YOLOv5, YOLOv8, and YOLO11 detection algorithms and to perform a comparative analysis of their speed and accuracy of data processing using weld defects as an example. The results of the experimental studies show that the use of the latest version of the model does not lead to significant improvements in the quality of defect detection compared to previous versions. The results presented in the work allow us to assess the feasibility of using the new YOLO11 model to detect defects in radiographic images. Based on the experiments, researchers using computer vision methods to control the quality of welds can make an informed decision about whether to use this model or use previous versions of the algorithms.
Downloads
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
References
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, vol. 15, no. 10, pp. 3697. DOI: 10.3390/ma15103697
Zhukovsky E.A., Khoroshev V.N. (2005) Modern equipment for non-destructive quality control of welded joints of pipelines by radiographic method. Russian journal of heavy machinery, no. 9, pp. 8–10.
Kazantsev I., Lemahieu I., Salov G.I., Denys R. (2002) Statistical detection of defects in radiographic images in nondestructive testing. Signal Processing, vol. 82, no. 5, pp. 791–801. DOI: 10.1016/S0165-1684(02)00158-5
Valavanis I., Kosmopoulos D. (2010) Multiclass defect detection and classification in weld radiographic images using geometric and texture features. Expert. Syst. Appl., vol. 37, Is. 12, pp. 7606–7614. DOI: 10.1016/j.eswa.2010.04.082
Boaretto N., Centeno T.M. (2017) Automated detection of welding defects in pipelines from radiographic images DWDI. NDT and Int., vol. 86, pp. 7–13. DOI: 10.1016/j.ndteint.2016.11.003
Hou W., Zhang D., Wei Y., Guo J., Zhang X. (2020) Review on computer aided weld defect detection from radiography images. Appl. Sci., vol. 10(5), p. 1878. DOI: 10.3390/app10051878
Garisto D. (2024) How cutting-edge computer chips are speeding up the AI revolution. Nature, vol. 630, no. 8017, pp. 544–546. DOI: 10.1038/d41586-024-01544-0
Andriyanov N.A., Dementiev V.E., Tashlinskii A.G. (2022) Detection of objects in the images: from likelihood relationships towards scalable and efficient neural networks. Computer Optics, vol. 46, Is. 1, pp. 139–159. DOI: 10.18287/2412-6179-CO-922
Yemelyanova M.G., Smailova S.S., Baklanova O.E. (2023) Detection of surface defects in welded joints during visual inspections using machine vision methods. Computer optics, vol. 47, no. 1, pp. 112–117. DOI: 10.18287/2412-6179-CO-1137
Fan X., Gao X., Liu G., Ma N., Zhang Y. (2021) Research and prospect of welding onitoring technology based on machine vision. J. Adv. Manuf. Technol., vol. 115, pp. 3365–3391. DOI: 10.1007/s00170-021-07398-4
Gordeev D.V. (2018) Application of machine vision for searching and detection of surface defects of weld seam. Juvenis Scientia, no. 3. pp. 4–5.
Praveen Kumar R., Deivanathan R., Jegadeeshwaran R. (2021) Welding defect identification with machine vision system using machine learning. J. of Phys.: Conf. Ser., vol. 1716, p. 12023. DOI: 10.1088/1742-6596/1716/1/012023
Sun J., Li C., Wu X.J., Palade V., Fang W. (2019) An effective method of weld defect detection and classification based on machine vision. IEEE Trans. Industr. Inform., vol. 15, no. 12, pp. 6322–6333. DOI: 10.1109/TII.2019.2896357
Muravyov S.V., Pogadaeva E.Y. (2020) Computer-aided recognition of defects in welded joints during visual inspections based on geometric attributes. Russian Journal of Nondestructive Testing, vol. 56, no. 3, pp. 259–267. DOI: 10.1134/S1061830920030055
Shao J., Shi H., Du D., Wang L., Cao H. (2011) Automatic weld defect detection in real-time X-ray images based on support vector machine. Proc. 4th Int. Congr. Image Signal Process., vol. 4, pp. 1842–1846. DOI: 10.1109/CISP.2011.6100637
Duan F., Yin S., Song P., Zhang W., Zhu C., Yokoi H. (2019) Automatic Welding Defect Detection of X-Ray Images by Using Cascade AdaBoost With Penalty Term. IEEE Access, vol. 7, pp. 125929–125938. DOI: 10.1109/ACCESS.2019.2927258
Yaping L., Weixin G. (2019) Research on X-ray welding image defect detection based on convolution neural network. IOP Conf. Series: J. Phys. Conf. Ser., vol. 1237, Is. 3, p. 032005. DOI 10.1088/1742-6596/1237/3/032005
Wang X., He F., Huang X. (2024) A new method for deep learning detection of defects in X-ray images of pressure vessel welds. Sci Rep., vol. 14, pp. 6312. DOI: 10.1038/s41598-024-56794-9
Yang D., Cui Y., Yu Z., Yuan H. (2021) Deep Learning Based Steel Pipe Weld Defect Detection. Applied Artificial Intelligence, vol. 35, no. 15, pp. 1237–1249. DOI:10.48550/arXiv.2104.14907
Terven J., Córdova-Esparza D.-M., Romero-González J.-A. (2023) A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, vol. 5(4), pp. 1680–1716. DOI: 10.3390/make5040083
Cherkasov S., Ivanov M., Ivanov A. (2023) Detection of Defects in Welded Joints Based on Data from the Computer Vision System Using YOLOv5. Int. Ural Conf. on Electrical Power Eng. (UralCon), Magnitogorsk, Russian Federation, pp. 780–784, DOI: 10.1109/UralCon59258.2023.10291074
Guo J., Dong L., Xu H. (2024) Welding Image Defect Detection Based on YOLOv5. 4th Int. Conf. on Neural Networks, Information and Communication (NNICE), Guangzhou, China, pp. 469–472. DOI: 10.1109/NNICE61279.2024.10498851
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, vol. 23(12), pp. 5640. DOI: 10.3390/s23125640
Pan K., Hu H., Gu P. (2023) WD-YOLO: A More Accurate YOLO for Defect Detection in Weld X-ray Images. Sensors, vol. 23(21), pp. 8677. DOI: 10.3390/s23218677
Zhou J., Zhang W., Sui X., Chen Y. (2024) Welding defect detection based on YOLOv8. J. Phys.: Conf. Ser., vol. 2816, p. 012045. DOI: 10.1088/1742-6596/2816/1/012045
Chen J., Liu J. (2023) Enhancing Welding Defect Detection: An Improved YOLOv8 Model with Feature Augmentation and Scale Fusion. IEEE 11th Joint Int. Inf. Tech. and Artificial Intell. Conf. (ITAIC), Chongqing, China, pp. 1619–1622. DOI: 10.1109/ITAIC58329.2023.10408771
Sulake N.R. (2025) A Comprehensive Guide to YOLOv11 Object Detection. URL:https://www.analyticsvidhya.com/blog/2024/10/yolov11-object-detection/
Ultralytics. (2025) Ultralytics YOLO11. URL:https://docs.ultralytics.com/ru/models/yolo11
Khanam R., Hussain M. (2024) YOLOv11: An Overview of the Key Architectural Enhancements. eprint arXiv, DOI: 10.48550/arXiv.2410.17725
Loshchilov I., Hutter F. (2019) Decoupled Weight Decay Regularization. ICLR, DOI: 10.48550/arXiv.1711.05101