Physical and chemical calculations of steelmaking processes and predictive models for the production of clean steel

Abstract

The results of physicochemical calculations of steelmaking processes for the production of clean steels deoxidized with aluminum are presented. The efficiency of the calculations was achieved using as the main scientific idea the position on the leading role of the oxidation potential in the metal – slag – gas system, while controlling the external supply of oxygen from the atmosphere, materials, slag and refractories. The advantage of this idea lies in the fact that thanks to it it provides a quick identification of critical points in developed and existing technologies, and determines effective ways to solve emerging quality problems in clean and ultra-clean steels. An approach is considered to improve the technology of clean steel production, including elements of mathematical and thermodynamic models, as well as algorithmic approaches for building static models using machine learning technology to improve efficiency in steelmaking technologies. For the application of the presented approach it is necessary to prepare the data set before-hand, as well as to carry out the interpretation of the results of machine learning, based on fundamental laws and physical and chemical processes occurring in steelmaking production. As a result of the thermodynamic calculations performed in the STM program, measures were developed for the production of clean steels. On the examples of the production of thin slabs and billets search and confirmation of significant technological parameters in the formation of steel-making defects due to non-metallic inclusions was carried out using methods of in-depth analytics and machine learning