Next Article in Journal
Deep Learning-Based Segmentation and Spatial Distribution Characteristics of Coal Matrix Pores in FIB-SEM Images
Previous Article in Journal
Inversion and Dynamic Control of Local Heating Temperature Fields in Wellhead-Produced Fluids
Previous Article in Special Issue
Towards Sustainable Industry 5.0: An LLM-Based Co-Pilot for Energy-Efficient Factory Scheduling
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Processes
Volume 14
Issue 12
10.3390/pr14121892
processes-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Feature-Embedded Transformer-Based Classification of Steel Plate Defects for Robust Industrial Process Inspection

by
Bowen Dong
1,*,
Xinyu Zhang
2,
Chaoya Yan
3,
Weiyan Zhu
4,
Lingmin Hou
2,
Yifan Feng
5 and
Lixing Lin
6
1
School of Electrical Automation and Information Engineering, Tianjin University, Tianjin 300072, China
2
Department of Computer Science, Rochester Institute of Technology, Rochester, NY 14623, USA
3
Department of Computer Science, Rutgers University, New Brunswick, NJ 08901, USA
4
Meta Platforms Inc., Menlo Park, CA 94025, USA
5
Department of Computer Science and Engineering, Santa Clara University, Santa Clara, CA 95053, USA
6
Graduate School of Arts and Science, Yale University, New Haven, CT 06520, USA
*
Author to whom correspondence should be addressed.
Processes 2026, 14(12), 1892; https://doi.org/10.3390/pr14121892
Submission received: 17 May 2026 / Revised: 8 June 2026 / Accepted: 9 June 2026 / Published: 10 June 2026
(This article belongs to the Special Issue Machine Learning for Predictive Modeling and Optimization of Manufacturing Processes)
Versions Notes

Abstract

Robust defect classification is critical for intelligent process inspection and quality control in steel manufacturing, but it remains challenging when industrial tabular data are small, imbalanced, statistically skewed, and characterized by nonlinear inter-feature dependencies. This study proposes a robust steel plate defect classification framework based on a feature-embedded Transformer. A quantile-based transformation is first introduced to regularize heterogeneous and heavy-tailed process descriptors. Each numerical variable is then represented as a learnable feature token and processed by a Transformer encoder to model contextual interactions among positional, geometric, luminosity-related, and morphological attributes. Experiments were conducted on the Steel Plates Faults dataset, containing 1941 samples, 27 input features, and 7 defect categories. On the held-out test set, the model achieved an accuracy of 0.735, remaining competitive with XGBoost (0.794) and Random Forest (0.783). SHAP and self-attention analyses further indicate that the model captures distributed and interaction-aware defect representations, providing an interpretable solution for robust industrial defect classification.
Keywords: steel manufacturing; process inspection; defect classification; industrial tabular data; feature-embedded Transformer steel manufacturing; process inspection; defect classification; industrial tabular data; feature-embedded Transformer

Share and Cite

MDPI and ACS Style

Dong, B.; Zhang, X.; Yan, C.; Zhu, W.; Hou, L.; Feng, Y.; Lin, L. Feature-Embedded Transformer-Based Classification of Steel Plate Defects for Robust Industrial Process Inspection. Processes 2026, 14, 1892. https://doi.org/10.3390/pr14121892

AMA Style

Dong B, Zhang X, Yan C, Zhu W, Hou L, Feng Y, Lin L. Feature-Embedded Transformer-Based Classification of Steel Plate Defects for Robust Industrial Process Inspection. Processes. 2026; 14(12):1892. https://doi.org/10.3390/pr14121892

Chicago/Turabian Style

Dong, Bowen, Xinyu Zhang, Chaoya Yan, Weiyan Zhu, Lingmin Hou, Yifan Feng, and Lixing Lin. 2026. "Feature-Embedded Transformer-Based Classification of Steel Plate Defects for Robust Industrial Process Inspection" Processes 14, no. 12: 1892. https://doi.org/10.3390/pr14121892

APA Style

Dong, B., Zhang, X., Yan, C., Zhu, W., Hou, L., Feng, Y., & Lin, L. (2026). Feature-Embedded Transformer-Based Classification of Steel Plate Defects for Robust Industrial Process Inspection. Processes, 14(12), 1892. https://doi.org/10.3390/pr14121892

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop