Data-driven modelling, learning and stochastic predictive control for the steel industry

D. Herceg, G. Georgoulas, P. Sopasakis, M. Castaño, P. Patrinos, A. Bemporad, J. Niemi, G. Nikolakopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)
Original languageUndefined/Unknown
Title of host publication2017 25th Mediterranean Conference on Control and Automation (MED)
Pages1361-1366
Number of pages6
DOIs
Publication statusPublished - 01 Jul 2017

Keywords

  • air pollution control
  • combustion
  • energy consumption
  • furnaces
  • heating
  • learning systems
  • predictive control
  • steel industry
  • stochastic processes
  • learning control
  • stochastic predictive control
  • data-driven modelling
  • energy-intensive processes
  • controlled process
  • online modelling
  • uncertainty-aware predictive control
  • risk-sensitive model selection
  • risk measures
  • dynamical models
  • process data
  • walking beam furnace
  • Swerea MEFOS
  • scenario-based model predictive controller
  • temperature references
  • heating zones
  • classifier training
  • oxygen
  • thermal efficiency
  • Furnaces
  • Predictive models
  • Heating systems
  • Combustion
  • Legged locomotion
  • Computational modeling
  • Process control
  • Advanced Process Control
  • Machine Learning
  • Stochastic Model Predictive Control
  • Risk-sensitive Model Selection
  • Cyber-Physical Systems

Cite this