EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Full penetration detection in fiber laser remote cutting of electrical steel sheets from in situ monitored images using convolutional neural networks

Max Schleier, Cemal Esen, Ralf Hellmann

Journal of Laser Applications · 01.05.2025 · 37 (2)

DOI: 10.2351/7.0001610 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Laser Applications, online erschienen am 31.03.2025. Verfasst von Max Schleier und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bundesministerium für Bildung und Forschung.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In laser remote cutting, a cut through is usually realized by repeating a scanning process for several ablation cycles. The material removal rate depends primarily on the laser power, feed rate, and number of cycles. Too few cycles will not achieve a full penetration, whereas too many cycles may cause the workpiece to reweld on the sheet. In either case, the workpiece cannot be detached from the sheet. In this contribution, we present an in situ monitoring system using convolutional neural networks (CNNs), from recordings of the process zone during remote cutting, to detect full penetration in thin electrical sheets. The monitoring system, based on a high-speed camera, is attached to a conventional laser scanner, whereby the optical detection path is aligned coaxially to the incident laser. Images with a size of 256 × 256 px2 are recorded with a sample rate of 20 × 103 fps and an exposure time of 20 μs. Without external illumination, the thermal radiation of the process zone is captured in the VIS spectrum. A dataset of images is labeled for cycles before a cut through, during a full penetration and for too many cycles, to train the networks. As a result, a full penetration is recognized by the trained CNN models, and the detection accuracies of AlexNet, VGGNet, and ResNet are compared.

Förderung

  • Bundesministerium für Bildung und Forschung

Zitieren

APA

Schleier, M., Esen, C., & Hellmann, R. (2025). Full penetration detection in fiber laser remote cutting of electrical steel sheets from in situ monitored images using convolutional neural networks. Journal of Laser Applications, 37(2). https://doi.org/10.2351/7.0001610

Vancouver

Schleier M, Esen C, Hellmann R. Full penetration detection in fiber laser remote cutting of electrical steel sheets from in situ monitored images using convolutional neural networks. Journal of Laser Applications. 2025;37(2). doi:10.2351/7.0001610

BibTeX
@article{Schleier2025,
  author = {Schleier, Max and Esen, Cemal and Hellmann, Ralf},
  title = {Full penetration detection in fiber laser remote cutting of electrical steel sheets from in situ monitored images using convolutional neural networks},
  journal = {Journal of Laser Applications},
  year = {2025},
  volume = {37},
  number = {2},
  doi = {10.2351/7.0001610}
}
Kostenlos starten →