Advanced search
2 files | 2.72 MB Add to list

Hybrid static-sensory data modeling for prediction tasks in basic oxygen furnace process

(2023) APPLIED INTELLIGENCE. 53(12). p.15163-15173
Author
Organization
Abstract
In this paper, we propose a novel data-driven prediction system for Multivariate Time Series (MTS) in an industrial context, where classic relational data contain keyinformation in order to properly interpret the MTS. Particularly we focus on the accurate endpoint prediction of temperature and chemical composition at the basic oxygen furnace, which is a step in the steel production pipeline where liquid iron is refined to steel. The precise prediction of temperature is important for proper process control while reaching the target chemical composition is essential for quality control. Our deep learning methodology employs two modules followed by an aggregation block; a Convolutional Neural Network (CNN) handles the MTS, while in parallel, the static data is processed by a Fully Connected Network (FCN). We enhance the CNN performance by adding two Squeeze-and-excitation (SE) blocks, which act like an attention module over the different channels. By taking the MTS data into account we improve the prediction by up to 10% relative over the models which only consider the static data. The hybrid FCN-CNN-SE architecture slightly improves the state-of-the-art MTS approaches by 2%, with less outliers on the prediction of final temperature and phosphorus concentration, while being easier to implement and more scalable to larger datasets and input space than current solutions.
Keywords
SERIES, STEEL, Basic oxygen furnace, Data-driven prediction models, Multivariate time, series, Neural networks, Steel production

Downloads

  • DS572 acc.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 995.85 KB
  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.72 MB

Citation

Please use this url to cite or link to this publication:

MLA
Sala, Davi Alberto, et al. “Hybrid Static-Sensory Data Modeling for Prediction Tasks in Basic Oxygen Furnace Process.” APPLIED INTELLIGENCE, vol. 53, no. 12, 2023, pp. 15163–73, doi:10.1007/s10489-022-04293-7.
APA
Sala, D. A., Van Yperen-De Deyne, A., Mannens, E., & Jalalvand, A. (2023). Hybrid static-sensory data modeling for prediction tasks in basic oxygen furnace process. APPLIED INTELLIGENCE, 53(12), 15163–15173. https://doi.org/10.1007/s10489-022-04293-7
Chicago author-date
Sala, Davi Alberto, Andy Van Yperen-De Deyne, Erik Mannens, and Azarakhsh Jalalvand. 2023. “Hybrid Static-Sensory Data Modeling for Prediction Tasks in Basic Oxygen Furnace Process.” APPLIED INTELLIGENCE 53 (12): 15163–73. https://doi.org/10.1007/s10489-022-04293-7.
Chicago author-date (all authors)
Sala, Davi Alberto, Andy Van Yperen-De Deyne, Erik Mannens, and Azarakhsh Jalalvand. 2023. “Hybrid Static-Sensory Data Modeling for Prediction Tasks in Basic Oxygen Furnace Process.” APPLIED INTELLIGENCE 53 (12): 15163–15173. doi:10.1007/s10489-022-04293-7.
Vancouver
1.
Sala DA, Van Yperen-De Deyne A, Mannens E, Jalalvand A. Hybrid static-sensory data modeling for prediction tasks in basic oxygen furnace process. APPLIED INTELLIGENCE. 2023;53(12):15163–73.
IEEE
[1]
D. A. Sala, A. Van Yperen-De Deyne, E. Mannens, and A. Jalalvand, “Hybrid static-sensory data modeling for prediction tasks in basic oxygen furnace process,” APPLIED INTELLIGENCE, vol. 53, no. 12, pp. 15163–15173, 2023.
@article{01GJMK3MNR00NTZN12DYMC7TZA,
  abstract     = {{In this paper, we propose a novel data-driven prediction system for Multivariate Time Series (MTS) in an industrial context, where classic relational data contain keyinformation in order to properly interpret the MTS. Particularly we focus on the accurate endpoint prediction of temperature and chemical composition at the basic oxygen furnace, which is a step in the steel production pipeline where liquid iron is refined to steel. The precise prediction of temperature is important for proper process control while reaching the target chemical composition is essential for quality control. Our deep learning methodology employs two modules followed by an aggregation block; a Convolutional Neural Network (CNN) handles the MTS, while in parallel, the static data is processed by a Fully Connected Network (FCN). We enhance the CNN performance by adding two Squeeze-and-excitation (SE) blocks, which act like an attention module over the different channels. By taking the MTS data into account we improve the prediction by up to 10% relative over the models which only consider the static data. The hybrid FCN-CNN-SE architecture slightly improves the state-of-the-art MTS approaches by 2%, with less outliers on the prediction of final temperature and phosphorus concentration, while being easier to implement and more scalable to larger datasets and input space than current solutions.}},
  author       = {{Sala, Davi Alberto and Van Yperen-De Deyne, Andy and Mannens, Erik and Jalalvand, Azarakhsh}},
  issn         = {{0924-669X}},
  journal      = {{APPLIED INTELLIGENCE}},
  keywords     = {{SERIES,STEEL,Basic oxygen furnace,Data-driven prediction models,Multivariate time,series,Neural networks,Steel production}},
  language     = {{eng}},
  number       = {{12}},
  pages        = {{15163--15173}},
  title        = {{Hybrid static-sensory data modeling for prediction tasks in basic oxygen furnace process}},
  url          = {{http://doi.org/10.1007/s10489-022-04293-7}},
  volume       = {{53}},
  year         = {{2023}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: