Technical Diagnostics and Non-Destructive Testing, 2026, №03

2026 №03 (02)

2026 №03 (04)

---

"Tekhnichna Diahnostyka ta Neruinivnyi Kontrol" (Technical Diagnostics and Non-Destructive Testing) #3, 2026, pp. 38-47

Automation of the defects detection process in magnetic particle inspection images

A.S. Momot¹, V.S. Yakotyuk¹, Iu.Yu. Lysenko^1,3, R.M. Galagan¹, Y. Mirchev^2,3

¹1National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute». 37 Beresteysky Ave., 03056, Kyiv, Ukraine. E-mail: j.lysenko@kpi.ua
²Institute of Mechanics at the Bulgarian Academy of Sciences. 1113, Acad. G. Bonchev Str., Sofia, Bulgaria
³Center of Competence for Mechatronics and Clean Technologies «Mechatronics, Innovation, Robotics, Automation and Clean Technologies» – MIRACle, Bulgaria. E-mail: a.momot@kpi.ua

This paper considers the possibilities of applying deep learning models of the YOLO11 family to the task of automating defect detection in magnetic particle inspection images. Magnetic particle inspection is widely used to test ferromagnetic parts, and decisions based on its results affect operational safety and costs. At the same time, magnetic particle inspection images often contain a grainy background, uneven lighting and glare, which masks low-contrast magnetic patterns and reduces the reliability of simple analysis methods. A software approach is proposed in which camera frames are automatically processed by a neural network, and the output forms defect localization frames and classifies them by type. Real images were used to train the models, the number of which was increased by augmentation through transformations that simulate typical deviations in shooting parameters. The dataset was labelled according to three defect classes and divided into training, validation, and test sets. Training and comparison of the YOLO11n, YOLO11s, YOLO11m, and YOLO11l models were performed using the Precision, Recall, mAP50, and mAP50-95 metrics and frame processing time. It was shown that increasing the size of the model does not provide a proportional increase in quality on the available dataset. The best balance between accuracy and speed was provided by the YOLO11m model with an mAP50-95 score of 0.238 and a frame processing time of 29.5 ms. Analysis of the training results showed higher quality detection of linear defects and complexity in detecting small group defects, which is due to the lack of training data and noisy background. Recommendations are given on methods to reduce false positives and expand data to improve the representativeness of the training set. 16 Ref., 4 Tabl., 5 Fig.
Keywords: magnetic particle inspection, defect detection, computer vision, artificial intelligence, neural networks

Received: 01.06.2026
Received in revised form: 29.07.2026
Accepted: 06.09.2026
Posted online: 22.09.2026

References

1. International Organization for Standardization (2016) ISO 9934-1:2016 Non-destructive testing. Magnetic particle testing. Pt 1 General principles. Geneva, ISO.
2. Yakotiuk, V.S., Hlabets, S.M., Lysenko, Yu.Yu., Momot, A.S. (2025) Practical experience of using and analyzing the efficiency of various magnetic suspensions. Technical Diagnostics and Non-Destructive Testing, 4, 44–48 [in Ukrainian]. DOI: https://doi.org/10.37434/tdnk2025.04.06
3. Yang, Y., Yang, Y., Li, L. et al (2022) Automatic defect identification method for magnetic particle inspection of bearing rings based on visual characteristics and highlevel features. Appl. Sci., 12(3), 1293. DOI: https://doi.org/10.3390/app12031293
4. Mao, Z., Wu, Q., Qin, X. et al (2023) Magnetic particle inspection. Status, advances, and challenges. Demands for automatic non-destructive testing. NDT & E International, 143, 103030. DOI: https://doi.org/10.1016/j.ndteint.2023.103030
5. Wu, Q., Qin, X., Dong, K. et al (2023) A learning-based crack defect detection and 3D localization framework for automated fluorescent magnetic particle inspection. Expert Systems with Applications, 214, 118966. DOI: https://doi.org/10.1016/j.eswa.2022.118966
6. Tout, K., Meguenani, A., Urban, J.-P., Cudel, C. (2021) Automated vision system for magnetic particle inspection of crankshafts using convolutional neural networks. The Internnational J. of Advanced Manufacturing Technology, 112(8), 3307–3326. DOI: https://doi.org/10.1007/s00170-020-06467-4
7. Chen, J., Tong, J., Su, J. (2025) Design of a real-time abnormal detection system for rotating machinery based on YOLOv8. Frontiers in Mechanical Engineering, 11, 1683572. DOI: https://doi.org/10.3389/fmech.2025.1683572
8. Momot, A., Kretsul, V., Muraviov, O., Galagan, R. (2024) Automated defect detection in printed circuit boards based on the YOLOv5 neural network. The Paton Welding J., 4, 46–52. DOI: https://doi.org/10.37434/tpwj2024.04.07
9. Shi, A., Wu, Q., Qin, X. et al (2024) Lightweight detector based on knowledge distillation for magnetic particle inspection of forgings. NDT & E International, 143, 103052. DOI: https://doi.org/10.1016/j.ndteint.2024.103052
10. Wu, Q., Qin, X., Xiong, X. (2025) Investigating the effects of data and image enhancement techniques on crack detection accuracy in FMPI. Advanced Engineering Informatics, 65(PA), 103169. DOI: https://doi.org/10.1016/j.aei.2025.103169
11. Wang, H., Du, W., Xu, G. et al (2024) Automated crack detection of train rivets using fluorescent magnetic particle inspection and instance segmentation. Sci. Reports, 14, 10666. DOI: https://doi.org/10.1038/s41598-024-61396-6
12. Ivasenko, I.B., Vorobel, R.A., Uchanin, V.M. et al. (2023) Detection of chalcopyrite in digital images of copper ore sample sections. Information Extraction and Processing, 51(127), 52–61. DOI: https://doi.org/10.15407/vidbir2023.51.052
13. Storozhyk, D., Protasov, A., Kuts, Yu. et al. (2024) Enhancing neural network efficiency in automated image analysis for thermal nondestructive testing. J. of Theoretical and Applied Mechanics, 54, 242–252. DOI: https://doi.org/10.55787/jtams.24.54.2.242
14. Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016) You only look once: Unified, real-time object detection. In: Proce. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 779–788. DOI: https://doi.org/10.48550/arXiv.1506.02640
15. Wang, J., Wang, Y., Li, X. et al (2025) SCI-YOLO11: An improved defect detection algorithm for transmission line insulators based on YOLO11. Plos One, 20(10), e0322561. DOI: https://doi.org/10.1371/journal.pone.0322561
16. Everingham, M., Van Gool, L., Williams, C.K.I. et al (2010) The PASCAL visual object classes (VOC) challenge. Int. J. of Comput. Vis., 88,

---

This article is licensed under a Creative Commons Attribution Non-Commercial 4.0 International (CC-BY-NC).

---

Suggested Citation

A.S. Momot, V.S. Yakotyuk, Iu.Yu. Lysenko, R.M. Galagan, Y. Mirchev (2026) Automation of the defects detection process in magnetic particle inspection images. Technical Diagnostics and Non-Destructive Testing, 03, 38-47.

---

Advertising in this issue:

---