Deep Learning Method for Defect Detection for Industrial Robot-based Magnetic Particle Inspection
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/33288 ↗Kurz gefasst
Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Kevin Schmitz und 6 weiteren Autor:innen.
Abstract (Originalsprache)
This work focuses on an AI-based data analysis for the robot-guided magnetic particle inspection (MPI) developed as part of the SeConRob project. The primary aim here is to create deep learning-based methods to detect defects in MPI images of real components using a robot-guided camera. The project in total strives to integrate defect detection algorithms into the robotized production environment. This contribution covers the practical application, the image acquisition system, the individual analysis regarding defects, and the evaluation results. The deep learning challenge comprises semantic image segmentation. The approach involves classifying each pixel of the image as either “defect” or “non-defect”. A ResNet based encoder with a U-Net style decoder is employed for the segmentation. ImageNet pretrained weights are leveraged as an initialization for transfer learning. The training datasets include both laboratory-generated images and images captured by robots in a real production environment.
Zitieren
APA
Schmitz, K., Groß, D., Römer, F., Heinrich, M., Ardıç, C. E., Rabung, M., & Martelli, S. (2026). Deep Learning Method for Defect Detection for Industrial Robot-based Magnetic Particle Inspection. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33288
Vancouver
Schmitz K, Groß D, Römer F, Heinrich M, Ardıç CE, Rabung M, et al. Deep Learning Method for Defect Detection for Industrial Robot-based Magnetic Particle Inspection. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33288
BibTeX
@article{Schmitz2026,
author = {Schmitz, Kevin and Groß, Daniel and Römer, Florian and Heinrich, Matthias and Ardıç, Cemil Emre and Rabung, Madalina and Martelli, Samuele},
title = {Deep Learning Method for Defect Detection for Industrial Robot-based Magnetic Particle Inspection},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/33288}
}
EUVIMED