Hybrid Temperature Modeling for the Ruhrstahl–Heraeus Process: Coupling a Data‐Driven Approach With a Physics‐Based Process Model

The Ruhrstahl–Heraeus (RH) vacuum degassing process is a key technology in modern steelmaking for producing high‐performance steel grades, performing degassing, decarburization, inclusion separation and modification, and high‐yield alloying in a single unit. Since RH treatment is often the final step before continuous casting, robust process control and reliable temperature monitoring are essential. This work presents a hybrid temperature model for continuous temperature prediction during the RH process. Enthalpy contributions from alloying additions, including the sensible heat required to reach melting temperature (), the enthalpy of fusion () where applicable, and the integral enthalpy of mixing or dissolution (), as well as reaction enthalpies (), are derived from thermodynamic calculations using FactSage databases. These values represent the exothermic and endothermic heat changes arising from physicochemical interactions among elements within the system. Heat losses by radiation and convection are included, together with an unsteady‐state term representing heat‐up of the cold vacuum vessel, parameterized by multiple linear regression based on a recent study by the authors. The model shows excellent agreement, with an RMSE of 2.79 °C, an MAE of 2.16 °C, and an R 2 of 0.98.

Authors

Institutions

Publication Details

Journal
steel research international
Published
2026-10-14
DOI
https://doi.org/10.1002/srin.70722
Primary Topic
Metallurgical Processes and Thermodynamics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Hybrid Temperature Modeling for the Ruhrstahl–Heraeus Process: Coupling a Data‐Driven Approach With a Physics‐Based Process Model

Michael Bernhard, Christian Bernhard, Daniel Kavić, Roman Rössler et al.
steel research international
Metallurgical Processes and Thermodynamics
article

Hybrid Temperature Modeling for the Ruhrstahl–Heraeus Process: Coupling a Data‐Driven Approach With a Physics‐Based Process Model

Michael Bernhard, Christian Bernhard, Daniel Kavić, Roman Rössler, Hannes Prousch
article en

Abstract

The Ruhrstahl–Heraeus (RH) vacuum degassing process is a key technology in modern steelmaking for producing high‐performance steel grades, performing degassing, decarburization, inclusion separation and modification, and high‐yield alloying in a single unit. Since RH treatment is often the final step before continuous casting, robust process control and reliable temperature monitoring are essential. This work presents a hybrid temperature model for continuous temperature prediction during the RH process. Enthalpy contributions from alloying additions, including the sensible heat required to reach melting temperature (), the enthalpy of fusion () where applicable, and the integral enthalpy of mixing or dissolution (), as well as reaction enthalpies (), are derived from thermodynamic calculations using FactSage databases. These values represent the exothermic and endothermic heat changes arising from physicochemical interactions among elements within the system. Heat losses by radiation and convection are included, together with an unsteady‐state term representing heat‐up of the cold vacuum vessel, parameterized by multiple linear regression based on a recent study by the authors. The model shows excellent agreement, with an RMSE of 2.79 °C, an MAE of 2.16 °C, and an R 2 of 0.98.

steel research international
Montanuniversität Leoben (AT), Voestalpine (Austria) (AT)
Steirische Wirtschaftsförderungsgesellschaft
Openalex Percentile: Top 22%
Metallurgical Processes and Thermodynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.