Residual U-Net segmentation method for laser cladding molten pool based on spatial feature fusion and attention mechanism
Journal of Laser Applications · 01.11.2026 · 38 (4)
DOI: 10.2351/7.0002246 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Laser Applications, online erschienen am 05.11.2026. Verfasst von Changying Dang und 5 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Gefördert von: The Major Scientific and Technological Special Project of Shanxi Province, The Special Fund for Science and Technology Innovation Teams of Shanxi Province, The First Batch of Projects Under the Double Hundred Breakthrough Initiative.
Abstract (Originalsprache)
To address the challenges in laser-cladding molten pool image segmentation, such as inadequate multilevel feature extraction, poor multiscale spatial feature fusion, ineffective noise suppression, and limited segmentation adaptability, a laser-cladding-oriented molten pool segmentation framework based on spatial feature fusion and an attention mechanism (RAE-U-Net) is proposed. The framework integrates the U-Net architecture with the ResNet-50 residual network, adaptive spatial feature fusion, and efficient channel attention mechanism to enhance feature extraction, multiscale feature fusion, and channelwise feature representation for laser-cladding molten pool images. The proposed framework enables multilevel and multiscale feature representation and achieves high-precision molten pool segmentation within the investigated dataset. Experimental results show that RAE-U-Net achieves a mean intersection over union of 97.33%, with mean pixel accuracy, precision, and recall values of 98.82%, 98.41%, and 98.82%, respectively. These results demonstrate the effectiveness of the integrated framework for laser-cladding molten pool image segmentation and provide a vision-based solution for molten pool segmentation under the investigated process conditions.
Förderung
- The Major Scientific and Technological Special Project of Shanxi Province
- The Special Fund for Science and Technology Innovation Teams of Shanxi Province
- The First Batch of Projects Under the Double Hundred Breakthrough Initiative
- The Open Fund of the State Key Laboratory of Intelligent Mining Equipment Technology
Zitieren
APA
Dang, C., Liu, H., Li, Z., Li, J., Chen, X., & Chang, W. (2026). Residual U-Net segmentation method for laser cladding molten pool based on spatial feature fusion and attention mechanism. Journal of Laser Applications, 38(4). https://doi.org/10.2351/7.0002246
Vancouver
Dang C, Liu H, Li Z, Li J, Chen X, Chang W. Residual U-Net segmentation method for laser cladding molten pool based on spatial feature fusion and attention mechanism. Journal of Laser Applications. 2026;38(4). doi:10.2351/7.0002246
BibTeX
@article{Dang2026,
author = {Dang, Changying and Liu, Haofeng and Li, Zhonghua and Li, Jiansu and Chen, Xueli and Chang, Wenbiao},
title = {Residual U-Net segmentation method for laser cladding molten pool based on spatial feature fusion and attention mechanism},
journal = {Journal of Laser Applications},
year = {2026},
volume = {38},
number = {4},
doi = {10.2351/7.0002246}
}
EUVIMED