EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WPSeg-Net: A Boundary-Guided Dual-Branch Network for Molten Pool Segmentation

Xin Heng, Yongjing Wang, Wanqiang Zhang, Jin Huang

Applied Sciences · 14.08.2026 · 16 (16) · 8110

DOI: 10.3390/app16168110 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 14.08.2026. Verfasst von Xin Heng und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The geometric morphology and dynamic evolution of the molten pool are key indicators of heat input, metal transfer, and solidification behavior during welding, making them critical for quality monitoring and process control. To address the challenges of molten pool image segmentation under complex conditions, including strong arc interference, blurred boundaries, small foreground regions, and significant shape variations, a MIG welding-based visual acquisition system is established to construct a multi-condition dataset. Based on this dataset, an efficient boundary-guided dual-branch network, WPSeg-Net, is proposed. The network employs ResNet-34 as the encoder, integrates a lightweight Transformer module for global context modeling, and adopts BiFPN for multi-scale feature fusion. A region branch and a boundary branch with a mutual guidance mechanism are further designed to improve segmentation accuracy and boundary refinement. Experimental results demonstrate that WPSeg-Net achieves an IoU of 92.83% and a Dice score of 96.28%, improving by 0.98% and 0.58% over DeepLabV3+, respectively. Meanwhile, the proposed method reduces the parameter size from 22.43 MB to 21.78 MB and decreases FLOPs from 62.25 G to 31.90 G, achieving a better balance between segmentation performance and computational efficiency.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Heng, X., Wang, Y., Zhang, W., & Huang, J. (2026). WPSeg-Net: A Boundary-Guided Dual-Branch Network for Molten Pool Segmentation. Applied Sciences, 16(16), 8110. https://doi.org/10.3390/app16168110

Vancouver

Heng X, Wang Y, Zhang W, Huang J. WPSeg-Net: A Boundary-Guided Dual-Branch Network for Molten Pool Segmentation. Applied Sciences. 2026;16(16):8110. doi:10.3390/app16168110

BibTeX
@article{Heng2026,
  author = {Heng, Xin and Wang, Yongjing and Zhang, Wanqiang and Huang, Jin},
  title = {WPSeg-Net: A Boundary-Guided Dual-Branch Network for Molten Pool Segmentation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {8110},
  doi = {10.3390/app16168110}
}
Kostenlos starten →