• Home
  • Search
  • Internal Defect Classification for Large‐Section Continuous Casting Round Billets via Multi‐Scale Feature Fusion and Attention Enhancement
  • https://doi.org/10.1002/srin.202500998Copy DOI Icon

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

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

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.

Similar Papers
  • PDF
  • Research Article
  • Citations1

Effect of Fusion of Statistical and Texture Features on HSI based Leaf Images with Both Dorsal and Ventral Sides

  • Jan 01, 2018
  • International Journal of Advanced Computer Science and Applications
  • Poonam Saini +1
  • Book Chapter

Detection of Small Targets in Aerial Images Based on Feature Fusion

  • Jan 01, 2022
  • Aiguo Lu +4
  • Research Article
  • Citations1

A hybrid multi-measure and improved UMAP approach for train traction motor bearing protection state assessment

  • Aug 12, 2024
  • Measurement Science and Technology
  • Shuli Liu +5
  • Research Article
  • Citations19

A uniform transformer-based structure for feature fusion and enhancement for RGB-D saliency detection

  • Mar 09, 2023
  • Pattern Recognition
  • Yue Wang +5
  • Research Article
  • Citations7

Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network

  • Jun 23, 2023
  • Energies
  • Bizhen Zhang +5
  • Research Article

INDT-YOLOV11 detection model based on variable space pooling denoising for rapid identification of bubbles and delamination

  • Oct 16, 2025
  • Measurement Science and Technology
  • Jianing Zhang +2
  • Research Article
  • Citations32

No-Reference Image Quality Assessment Based on the Fusion of Statistical and Perceptual Features

  • Jul 30, 2020
  • Journal of Imaging
  • Domonkos Varga
  • Research Article

Optimized clustering-based fusion for skin lesion image classification: Leveraging marine predators algorithm

  • Sep 16, 2024
  • Intelligent Decision Technologies
  • Niharika Mohanty +5
  • Research Article
  • Citations5

Multi-source unsupervised domain adaptive mill load forecasting method based on deep learning and fusion features

  • Mar 04, 2024
  • Minerals Engineering
  • Yiwen Liu +5
  • Conference Article
  • Citations32

Fusion of transfer learning features and its application in image classification

  • Apr 01, 2017
  • Thangarajah Akilan +3
  • Research Article
  • Citations4

A Dual-Branch Spatial-Frequency Domain Fusion Method with Cross Attention for SAR Image Target Recognition

  • Jul 10, 2025
  • Remote Sensing
  • Chao Li +4
  • Conference Article
  • Citations2

Research on Time-frequency Feature Fusion Method based on Dynamic Gesture Identity Authentication

  • Jun 18, 2021
  • Wang Yanna
  • Research Article
  • Citations2

Hyperspectral Image Classification Based on Fractional Fourier Transform

  • Jun 15, 2025
  • Remote Sensing
  • Jing Liu +3
  • Research Article
  • Citations4

CenterPoint-SE: A Single-Stage Anchor-Free 3-D Object Detection Algorithm With Spatial Awareness Enhancement

  • Oct 01, 2023
  • IEEE Transactions on Intelligent Transportation Systems
  • Hai Wang +6
  • Research Article

GATSiamNet: a dual branch network for few-shot hyperspectral image classification

  • Dec 31, 2026
  • International Journal of Image and Data Fusion
  • Rushi Sun +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.