Publication with K1-MET as a main author

We are proud to announce the publication of a new peer-reviewed paper in the journal Metallurgical and Materials Transactions B with Daniel Kavic of K1-MET as the main author.

The paper presents a hybrid approach for enhanced temperature prediction in ladle furnace steel refining combining computational thermodynamics with statistical learning methods. This research demonstrates how steelmakers can use process data to investigate process influences that affect the steel temperature and combine it with modern thermodynamic databases such as FactSage to gain deeper insights into optimized temperature control in steel production. The work forms an important part of the developed “i-clean” software, which can be used to investigate secondary steelmaking processes.

The full paper is available here: https://rdcu.be/eyV0U