Hybrid-input FCN-CNN-SE for industrial applications : classification of longitudinal cracks during continuous casting
- Author
- Davi Alberto Sala (UGent) , Andy Van Yperen-De Deyne (UGent) , Erik Mannens (UGent) and Azarakhsh Jalalvand (UGent)
- Organization
- Abstract
- In the presented research, machine learning methods were applied to the prediction of longitudinal cracks in steel slabs during continuous casting. We employ a deep learning approach to process 68 thermocouple signals as a multivariate time series (MTS) along with 32 static features, which encompass both chemical composition and process information. Our deep learning approach integrates two distinct parallel modules, followed by an aggregation block; a Convolutional Neural Network (CNN) processes the thermocouple MTS, while in parallel, the static data undergo processing via a Fully Connected Network (FCN). To enhance the performance of the CNN, we incorporate two Squeeze and Excitation (SE) blocks, which act as an attention mechanism across different channels. By integrating chemical information with MTS in the detection system, we improve the performance of defect detection by 15% relatively.
- Keywords
- STEEL, continuous caster, data-driven prediction models, multivariate time series, neural networks, longitudinal crack
Downloads
-
DS691.pdf
- full text (Published version)
- |
- open access
- |
- |
- 2.18 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01HFBT9XMDE3AMJBRC5MV7JJRC
- MLA
- Sala, Davi Alberto, et al. “Hybrid-Input FCN-CNN-SE for Industrial Applications : Classification of Longitudinal Cracks during Continuous Casting.” METALS, vol. 13, no. 10, 2023, doi:10.3390/met13101699.
- APA
- Sala, D. A., Van Yperen-De Deyne, A., Mannens, E., & Jalalvand, A. (2023). Hybrid-input FCN-CNN-SE for industrial applications : classification of longitudinal cracks during continuous casting. METALS, 13(10). https://doi.org/10.3390/met13101699
- Chicago author-date
- Sala, Davi Alberto, Andy Van Yperen-De Deyne, Erik Mannens, and Azarakhsh Jalalvand. 2023. “Hybrid-Input FCN-CNN-SE for Industrial Applications : Classification of Longitudinal Cracks during Continuous Casting.” METALS 13 (10). https://doi.org/10.3390/met13101699.
- Chicago author-date (all authors)
- Sala, Davi Alberto, Andy Van Yperen-De Deyne, Erik Mannens, and Azarakhsh Jalalvand. 2023. “Hybrid-Input FCN-CNN-SE for Industrial Applications : Classification of Longitudinal Cracks during Continuous Casting.” METALS 13 (10). doi:10.3390/met13101699.
- Vancouver
- 1.Sala DA, Van Yperen-De Deyne A, Mannens E, Jalalvand A. Hybrid-input FCN-CNN-SE for industrial applications : classification of longitudinal cracks during continuous casting. METALS. 2023;13(10).
- IEEE
- [1]D. A. Sala, A. Van Yperen-De Deyne, E. Mannens, and A. Jalalvand, “Hybrid-input FCN-CNN-SE for industrial applications : classification of longitudinal cracks during continuous casting,” METALS, vol. 13, no. 10, 2023.
@article{01HFBT9XMDE3AMJBRC5MV7JJRC,
abstract = {{In the presented research, machine learning methods were applied to the prediction of longitudinal cracks in steel slabs during continuous casting. We employ a deep learning approach to process 68 thermocouple signals as a multivariate time series (MTS) along with 32 static features, which encompass both chemical composition and process information. Our deep learning approach integrates two distinct parallel modules, followed by an aggregation block; a Convolutional Neural Network (CNN) processes the thermocouple MTS, while in parallel, the static data undergo processing via a Fully Connected Network (FCN). To enhance the performance of the CNN, we incorporate two Squeeze and Excitation (SE) blocks, which act as an attention mechanism across different channels. By integrating chemical information with MTS in the detection system, we improve the performance of defect detection by 15% relatively.}},
articleno = {{1699}},
author = {{Sala, Davi Alberto and Van Yperen-De Deyne, Andy and Mannens, Erik and Jalalvand, Azarakhsh}},
issn = {{2075-4701}},
journal = {{METALS}},
keywords = {{STEEL,continuous caster,data-driven prediction models,multivariate time series,neural networks,longitudinal crack}},
language = {{eng}},
number = {{10}},
pages = {{15}},
title = {{Hybrid-input FCN-CNN-SE for industrial applications : classification of longitudinal cracks during continuous casting}},
url = {{http://doi.org/10.3390/met13101699}},
volume = {{13}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: