• Media type: E-Article
  • Title: Deep learning for robust forecasting of hot metal silicon content in a blast furnace
  • Contributor: Giannetti, Cinzia; Borghini, Eugenio; Carr, Alex; Raleigh, James; Rackham, Ben
  • imprint: Springer Science and Business Media LLC, 2024
  • Published in: The International Journal of Advanced Manufacturing Technology
  • Language: English
  • DOI: 10.1007/s00170-024-13214-6
  • ISSN: 0268-3768; 1433-3015
  • Keywords: Industrial and Manufacturing Engineering ; Computer Science Applications ; Mechanical Engineering ; Software ; Control and Systems Engineering
  • Origination:
  • Footnote:
  • Description: <jats:title>Abstract</jats:title><jats:p>The hot metal silicon content is a key indicator of the thermal state in the blast furnace and it needs to be kept within a pre-defined range in order to ensure efficient operations. Effective monitoring of silicon content is challenging due to the harsh environment in the furnace and irregularly sampled measurements. Data-driven approaches have been proposed in the literature to predict silicon content using process data and overcome the sparsity of silicon content measurements. However, these approaches rely on the selection of hand-crafted features and ad hoc interpolation methods to deal with irregular sampling of the process variables, adding complexity to model training and optimisation, and requiring significant effort when tuning the model over time to keep it to the required level of accuracy. This paper proposes an improved framework for the prediction of silicon content using a novel deep learning approach based on Phased LSTM. The model has been trained using 3 years of data and validated over a 1-year period using a robust walk-forward validation method, therefore providing confidence in the model performance over time. The Phased LSTM model outperforms competing approaches due to its in-built ability to learn from event-based sequences and scalability for real-world deployments. This is the first time that Phased LSTM has been applied to real-world datasets and results suggest that the ability to learn from event-based data can be beneficial for the process industry where event-driven signals from multiple sensors are common.</jats:p>