Artificial intelligence and data-driven modeling in ironmaking - Potential and limitations

Dieter Bettinger, Harald Fritschek, Adnan Husakovic, Petra Krahwinkler, Martin Schaler, Sonja Strasser

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

Abstract

The revival of artificial intelligence (AI) promises to offer solutions in particular for complex systems that are difficult to model with classical methods. An overview of AI solutions in ironmaking is provided and their strengths and weaknesses are discussed. Topics such as the applicability for typical problem groups, pre-conditions regarding required data quality and completeness of data sets, reliability, and combination with classical approaches are covered. Further, the deployment and integration of black box models into control systems and the related stability are discussed.

Original languageEnglish
Title of host publicationAISTech 2021 - Proceedings of the Iron and Steel Technology Conference
PublisherAssociation for Iron and Steel Technology, AISTECH
Pages1919-1931
Number of pages13
ISBN (Electronic)9781935117933
DOIs
Publication statusPublished - 2021
EventAISTech 2021 Iron and Steel Technology Conference - Nashville, United States
Duration: 29 Jun 20211 Jul 2021

Publication series

NameAISTech - Iron and Steel Technology Conference Proceedings
Volume2021-June
ISSN (Print)1551-6997

Conference

ConferenceAISTech 2021 Iron and Steel Technology Conference
Country/TerritoryUnited States
CityNashville
Period29.06.202101.07.2021

Keywords

  • Artificial intelligence
  • Data analytics
  • Ironmaking
  • Process optimization

Fingerprint

Dive into the research topics of 'Artificial intelligence and data-driven modeling in ironmaking - Potential and limitations'. Together they form a unique fingerprint.

Cite this