EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automation of Ultrasonic Monitoring for Resistance Spot Welding Using Deep Learning

Ryan Scott, Danilo Stocco, Sheida Sarafan, Lukas Behnen, Andriy M. Chertov, Priti Wanjara, Roman Gr. Maev

Journal of Manufacturing and Materials Processing · 17.03.2026 · 10 (3) · 101

DOI: 10.3390/jmmp10030101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Manufacturing and Materials Processing, online erschienen am 17.03.2026. Verfasst von Ryan Scott und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Council Canada Industrial Research Assistance Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable process monitoring and quality evaluation for resistance spot welding (RSW) have become more important now than ever. An ultrasonic probe embedded into welding electrodes has enabled the acquisition of data about molten pool formation throughout welding, but automation of high-performance ultrasonic data analyses is still necessary to fully realize a monitoring system. This work proposes a two-stage deep learning (DL) approach for automated ultrasonic data analysis for RSW processing monitoring. The first stage conducts semantic segmentation on ultrasonic M-scan welding process signatures, yielding masks for identified molten pool and stack regions from which weld penetration measurements can be directly extracted, as well as expulsion occurrences throughout welding. From input images and segmentation outputs, the second stage directly estimates resultant weld nugget diameters using an additional neural network. Both stages leveraged architectures based on TransUNet, mixing elements of both convolutional neural networks (CNN) and vision transformers, and the effect of cross-attention for stack-up sheet thickness data fusion was investigated via an ablation study. Additionally, in the diameter estimation stage, the ablation study included alternative feature extraction architectures in the network and investigated the provision of M-scans to the model alongside segmentation masks. In both cases, cross-attention was determined to improve performance, and in the case of diameter estimation, providing M-scans as input was found to be beneficial in general. With cross-attention, the segmentation approach yielded a mean intersection over union (IoU) of 0.942 on molten pool, stack, and expulsion regions in the M-scans with 13.4 ms inference time. With cross-attention, diameter estimates yielded a mean absolute error of 0.432 mm with 4.3 ms inference time, representing a significant improvement over algorithmic approaches based on ultrasonic time of flight. Additionally, the approach attained >90% probability of detection (POD) at 0.830 mm below the acceptable diameter threshold and

Förderung

  • National Research Council Canada Industrial Research Assistance Program

Zitieren

APA

Scott, R., Stocco, D., Sarafan, S., Behnen, L., Chertov, A. M., Wanjara, P., & Maev, R. G. (2026). Automation of Ultrasonic Monitoring for Resistance Spot Welding Using Deep Learning. Journal of Manufacturing and Materials Processing, 10(3), 101. https://doi.org/10.3390/jmmp10030101

Vancouver

Scott R, Stocco D, Sarafan S, Behnen L, Chertov AM, Wanjara P, et al. Automation of Ultrasonic Monitoring for Resistance Spot Welding Using Deep Learning. Journal of Manufacturing and Materials Processing. 2026;10(3):101. doi:10.3390/jmmp10030101

BibTeX
@article{Scott2026,
  author = {Scott, Ryan and Stocco, Danilo and Sarafan, Sheida and Behnen, Lukas and Chertov, Andriy M. and Wanjara, Priti and Maev, Roman Gr.},
  title = {Automation of Ultrasonic Monitoring for Resistance Spot Welding Using Deep Learning},
  journal = {Journal of Manufacturing and Materials Processing},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {101},
  doi = {10.3390/jmmp10030101}
}
Kostenlos starten →