Nowadays, digitalization and automation in both industrial and research activities are driving forces of innovations. In recent years, machine learning (ML) techniques have been widely applied in these areas. A paramount direction in the application of ML models is the prediction of the material service time in heating devices. The results of ML algorithms are easy to interpret and can significantly shorten the time required for research and decision-making, substituting the trial-and-error approach and allowing for more sustainable processes. This work presents the state of the art in the application of machine learning for the investigation of MgO-C refractories, which are materials mainly consumed by the steel industry. Firstly, ML algorithms are presented, with an emphasis on the most commonly used ones in refractories engineering. Then, we reveal the application of ML in laboratory and industrial-scale investigations of MgO-C refractories. The first group reveals the implementation of ML techniques in the prediction of the most critical properties of MgO-C, including oxidation resistance, optimization of the C content, corrosion resistance, and thermomechanical properties. For the second group, ML was shown to be mostly utilized for the prediction of the service time of refractories. The work is summarized by indicating the opportunities and limitations of ML in the refractories engineering field. Above all, reliable models require an appropriate amount of high-quality data, which is the greatest current challenge and a call to the industry for data sharing, which will be reimbursed over the longer lifetimes of devices.

MgO‐C refractories are zonally installed in most of the key heat devices of steel and iron metallurgy with the exposure to various corrosive factors. One of the most significant factors is low‐temperature decarburization resulting in the oxidation of carbon in MgO‐C refractories and loss of its properties. Moreover MgO‐C materials are exposed for direct attack of liquid slag or steel melt which easily infiltrate the porous, decarburized hot face of the bricks. Cost of MgO‐C materials of high quality is important for refractories user. For this reason researches try to develop materials of high quality but with lower cost by substituting fused raw materials with sintered ones or with recycled MgO‐C. In this article, method of selecting the raw materials for production of MgO‐C bricks with comparable properties is shown. Twenty different variants of MgO‐C materials were prepared with the use of various quality raw materials. Basic properties of the industrially produced MgO‐C bricks were measured. To select recipes with similar quality principal components analysis method and K‐medoids algorithm were applied. To verify the results corrosion resistance of selected MgO‐C materials were tested with the use of induction furnace of medium frequency.

Nowadays, digitalization and automation in both industrial and research activities is a driving force for innovations. In recent years, Machine Learning (ML) techniques - the subset of Artificial Intelligence - have been widely applied as a key tool to automize and digitalize numerous in-dustrial processes. ML models can predict specific features, like materials' lifetime in a heating device, based on recently trained algorithms with applied input data. The results of ML algorithms are easy to interpret and can significantly decrease the time of research and decision-making, thus, substituting the trial-error approach. This work presents the state of the art in the application of Machine Learning in the investigation of MgO-C refractories for the steel industry. Also, the work presents an overview of the most commonly used ML algorithms in refractory engineering. So far published results confirm the high performance of ML, e.g., for prediction of oxidation behaviour, optimum graphite content and wear rate of MgO-C refractories, or for clustering materials based on various fused and sintered MgO sources into groups with similar corrosion resistance, thus, permitting to reduce expensive fused raw materials content. Most of the presented works were positively validated via experiment.

The ceramic–carbon refractory lining of an oxygen converter is subjected to variable thermochemical stresses, causing a progressive loss of material over time, which is expressed in a decreasing residual thickness of the lining. The forecasting method using Bayesian statistics has become a valuable skill in steel production planning and is one of the main conditions constituting the appropriate organization of steel and refractories production. This paper presents examples of Bayesian modelling of the unit wear rate value of the refractory materials for the zone with the highest wear in the refractory lining of a converter. From the experience gained during long-term operation of a steel-producing oxygen converter, it was found that the value of the unit wear rate of the refractory material in the slag spout zone of the steel-producing oxygen converter is subjected to an a posteriori normal distribution, with the following parameters: mean value µ = 401.23 µ heat⁻¹, standard deviation σ = 13.74 µm heat⁻¹. The forecasted mean value of the unit wear rate of the MC95/10 refractories lined in the slag spout zone of the oxygen converter used for steel production, and which operates in intensive exploitation conditions, was equal to µ = 420 µm heat⁻¹.