Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 1, 2025

Ensembling Deep Learning Models for Metal Surface Defect Classification

View Full Paper
Ask AI
Bookmark
Share

Authors

SZSida ZhangRPRichard J. PovinelliJDJoseph Domblesky

Discussion

Loading...

Member takes

Overview

This research demonstrates an ensemble approach that improves defect classification accuracy in metal surfaces, suggesting enhanced manufacturing automation.

Key Points

  • The proposed method achieves a defect classification accuracy of 96.7% after 10-fold cross-validation.
  • By combining two convolutional neural networks and a support vector machine, the model effectively categorizes six types of defects.
  • A dataset of 1,800 images, representing various metal surface defects, was used to train and test the model.
  • The results indicate that this approach outperforms traditional inspection methods and is competitive with state-of-the-art models.

Cite This Study

Zhang et al. (2025) studied this question.

synapsesocial.com/papers/68dd91cffe798ba2fc498b7chttps://doi.org/10.1115/msec2025-155588
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Hot rolled steel surface defect detection and classification using an automatic ensemble approach2024 · 4 citations
  2. 2Research progress of metal surface defect detection based on deep learning2025 · 1 citations
  3. 3Learning-Based Approach for Automated Surface Inspection with Industrial Tomography Imaging2024 · 7 citations
  4. 4Metal Surface Defect Classification Using Custom Convolutional Neural Network with Self Attention Mechanism2024
  5. 5An ensemble deep learning approach for surface defect detection in aluminum die-cast gas meter lids2026