EUVIMEDEUVIMED entdecken
Crossref

Internal Defect Classification for Large‐Section Continuous Casting Round Billets via Multi‐Scale Feature Fusion and Attention Enhancement

Qiang Shi, Min Li, Jiajin Chen, Yanbo Liu, Zheng Wang

steel research international · 2026-11 · 97 (11) · 5672-5687

DOI: 10.1002/srin.202500998 ↗

Kurz gefasst

Fachartikel in der Zeitschrift steel research international, online erschienen am 16.03.2026. Verfasst von Qiang Shi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate identification of internal defects in large‐section continuously cast round billets is critical for ensuring high‐grade special steel quality. Traditional ultrasonic A‐scan detection methods rely on manual experience and suffer from low signal‐to‐noise ratios and high defect signal similarity, resulting in insufficient identification accuracy. This study proposes a deep learning classification method based on multi‐scale feature fusion and attention enhancement. The method designs a multi‐dimensional feature extraction framework integrating time‐domain statistical features with fractional Fourier transform (FRFT) domain features, utilizing Fisher Score and mutual information mechanisms to select 16 key features from 123 initial dimensions. A three‐branch parallel network structure incorporates adaptive attention mechanisms for dynamic multi‐modal feature fusion. Learnable weighted combination of cross‐entropy, triplet, and contrastive losses addresses class imbalance issues. Experiments on an industrial dataset of 319 S355NL(Q355NE) continuously cast round billet samples demonstrate overall classification accuracy of 89.3% for five defect types: core porosity, shrinkage cavities, cracks, normal conditions, and composite defects, achieving a macro‐average F 1 ‐score of 0.893. Crack defect identification reaches 94.4% accuracy. Compared to baseline methods including MLP, ResNet, and FCN, the proposed method achieves the best trade‐off between classification performance and computational efficiency.

Zitieren

APA

Shi, Q., Li, M., Chen, J., Liu, Y., & Wang, Z. (2026). Internal Defect Classification for Large‐Section Continuous Casting Round Billets via Multi‐Scale Feature Fusion and Attention Enhancement. steel research international, 97(11), 5672-5687. https://doi.org/10.1002/srin.202500998

Vancouver

Shi Q, Li M, Chen J, Liu Y, Wang Z. Internal Defect Classification for Large‐Section Continuous Casting Round Billets via Multi‐Scale Feature Fusion and Attention Enhancement. steel research international. 2026;97(11):5672-5687. doi:10.1002/srin.202500998

BibTeX
@article{Shi2026,
  author = {Shi, Qiang and Li, Min and Chen, Jiajin and Liu, Yanbo and Wang, Zheng},
  title = {Internal Defect Classification for Large‐Section Continuous Casting Round Billets via Multi‐Scale Feature Fusion and Attention Enhancement},
  journal = {steel research international},
  year = {2026},
  volume = {97},
  number = {11},
  pages = {5672--5687},
  doi = {10.1002/srin.202500998}
}
Kostenlos starten →