A forecasting model-based discovery of causal links of key influencing performance quality indicators for sinter production improvement

Matej Vukovic, Vaishali Dhanoa, Markus Jäger, Conny Walchshofer, Josef Küng, Petra Krahwinkler, Belgin Mutlu, Stefan Thalmann

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

4 Citations (Scopus)

Abstract

Sintering is a complex production process where the process stability and product quality depend on various parameters. Building a forecasting model improves this process. Artificial intelligence (AI) approaches show promising results in comparison to current physical models. They are mostly considered black box models because of their hidden layers. Due to their complexity and limited traceability, it is difficult to draw conclusions for real sinter processes and improving the physical models in a running plant. This challenge is addressed by focusing on detecting causal links from AI-based forecasting models in order to improve the understanding of sintering and optimizing existing physical models.

Original languageEnglish
Title of host publicationProceedings of the Iron and Steel Technology Conference, AISTech 2020
PublisherIron and Steel Society
Pages2028-2038
Number of pages11
ISBN (Electronic)9781935117872
DOIs
Publication statusPublished - 2020
EventAISTech 2020 Iron and Steel Technology Conference - Cleveland, United States
Duration: 31 Aug 20203 Sept 2020

Publication series

NameAISTech - Iron and Steel Technology Conference Proceedings
Volume3
ISSN (Print)1551-6997

Conference

ConferenceAISTech 2020 Iron and Steel Technology Conference
Country/TerritoryUnited States
CityCleveland
Period31.08.202003.09.2020

Keywords

  • Causality detection
  • Machine learning
  • Quality control
  • Sintering
  • Visual analytics

Fingerprint

Dive into the research topics of 'A forecasting model-based discovery of causal links of key influencing performance quality indicators for sinter production improvement'. Together they form a unique fingerprint.

Cite this