Skip to main navigation Skip to search Skip to main content

Neural network approximation of iron oxide reduction process

  • Tomasz Wiltowski
  • , Krzysztof Piotrowski
  • , Hana Lorethova
  • , Lubor Stonawski
  • , Kanchan Mondal
  • , S. B. Lalvani
  • Southern Illinois University

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)

Abstract

The kinetics of Fe2O3 to FeO reduction process was investigated using the thermogravimetric data. The authors' previous experimental results indicated that initially the reduction of hematite is a surface controlled process, however once a thin layer of lower oxidation state iron oxides (magnetite, wüstite) is formed on the surface, it changes to diffusion control. In order to analyze the time-behavior of Fe2O 3 reduction under various process conditions, artificial neural network (ANN) was tested for modeling of this complex reaction pathways. The data used included the reduction of hematite in various temperatures by CO, H2 and a mixture of CO and H2. The ANN model proved its applicability and capability to mimic some extreme (minimum) of reaction rate within specific temperature range, when the classical Arrhenius equation is of limited use.

Original languageEnglish
Pages (from-to)775-783
Number of pages9
JournalChemical Engineering and Processing - Process Intensification
Volume44
Issue number7
DOIs
Publication statusPublished - Jul 2005

Keywords

  • Artificial neural network (ANN)
  • Backpropagation error algorithm
  • Feed-forward multilayer network
  • Iron oxides reduction
  • Isothermal solid-state reaction kinetics

ASJC Scopus subject areas

  • General Chemistry
  • General Chemical Engineering
  • Energy Engineering and Power Technology
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Neural network approximation of iron oxide reduction process'. Together they form a unique fingerprint.

Cite this