The chemical composition of standard Inconel 740 superalloy was modified by changes in the Al/Ti ratio (0.7, 1.5, 3.4) and addition of Ta (2.0, 3.0, 4.0%). Remelted Inconel 740 (A0) and nine variants with various chemical compositions were fabricated by lost-wax casting. The microstructure, microsegregation, phase transformation temperatures, thermal expansion coefficients and hardness of the superalloys were investigated by scanning electron microscopy, energy dispersive X-ray spectroscopy, differential scanning calorimetry, dilatometry and Vickers measurements. Typical dendritic microstructure was revealed with microsegregation of the alloying elements. Segregation coefficient kⁱ for Ti, Nb and Ta did not exceed unity, and so precipitates enriched mainly in these elements were found in interdendritic spaces. The Nb-rich blocky precipitates, MC carbides, MN nitrides, oxides, and fine γ’ was in all modified castings. Presence of other microstructural features, such as Ti-rich needles, eutectic γ-γ’ islands, small Al-rich and Cr-rich precipitates depended on the casting composition. The lowest solidus and liquidus temperatures were observed in superalloys with a high Al/Ti ratio. Consequently, in A7–A9 variants, the solidification range did not exceed 100 °C. In the A0 variant the difference between liquidus and solidus temperature was 138 °C. Hardness of all modified superalloys was at least 50% higher than for the remelted Inconel 740 (209 HV10).

The aim of the work is to investigate the effectiveness of selected classification algorithms and their extensions in assessing microstructure of castings. Experiments were carried out in which the prepared algorithms and machine learning methods were tested in various conditions and configurations, as well as for various input data, which are photos of castings (photos of the microstructure) or information about the material (e.g., type, composition). As shown by the literature review, there are few scientific papers on this subject (i.e., in the use of machine learning to assess the quality of the microstructure and the obtained strength properties of cast iron). The effectiveness of machine learning algorithms in assessing the quality of castings will be tested using the most universal methods. Results obtained by classic machine learning methods and by neural networks will be compared with each other, taking into account aspects such as interpretability of results, ease of model implementation, algorithm simplicity, and learning time.

The as-cast microstructure, alloying element segregation, solidification behavior, and thermal stability of model superalloys based on Inconel 740 with various Al/Ti ratios (0.7, 1.5, 3.4) and Ta (2.0, 3.0, 4.0 wt%) concentrations were investigated via ThermoCalc simulations, scanning and transmission electron microscopy, energy-dispersive X-ray spectroscopy, dilatometry, and differential scanning calorimetry. The solidification of the superalloys began with the formation of primary γ dendrites, followed by MC carbides. The type of subsequently formed phases depended on the superalloys’ initial Al/Ti ratio and Ta concentration. The results obtained from solidification simulations were compared to the obtained microstructures. For all castings, the dendritic regions consisted of fine γ′ precipitates, with their size mainly depending on the initial Al/Ti ratio, whereas in the interdendritic spaces, (Nb, Ta, Ti)C carbides and Nb-rich Laves phase precipitates were present. In high Al/Ti ratio superalloys, β-NiAl precipitates, strengthened by η and α-Cr phases, were observed. Based on dilatometric results, the dissolution of γ′ precipitates was accompanied by a substantial increase in the coefficient of thermal expansion. The end of the dilatation effect took place around the γ′ solvus temperature, as determined via calorimetry. Moreover, the bulk solidus temperature was preceded by the dissolution of the Laves phase, which may be accompanied by local melting.

The wear characteristics and related mechanisms of the Longwall Shearer Haulage System were investigated. Wear is one of the main reasons for failures and downtimes. This knowledge can help solve engineering problems. The research was carried out at a laboratory station and a test stand. The publication presents the results of tribological tests carried out in laboratory conditions. The aim research was to select the alloy intended for casting the toothed segments of the haulage system. The track wheel was made by the forging method using steel 20H2N4A. Haulage System was tested on the ground using a longwall shearer. Selected toothed segments were subjected to tests on this stand. The cooperation of the track wheel and toothed segments in the tootbar were analyzed by a 3D scanner. Debris chemical composition was also appointed, as well as mass loss of toothed segments. The developed solution toothed segment an increase in the service life of the track wheel in real conditions. The results of the research also contribute to reducing the operating costs of the mining process.

The article presents the developed IT solutions supporting the material and technological conversion process in terms of the possibility of using the casting technology of selected alloys to produce products previously manufactured with the use of other methods and materials. The solutions are based on artificial intelligence, machine learning and statistical methods. The prototype module of the information and decision-making system allows for a preliminary assessment of the feasibility of this type of procedure. Currently, the selection of the method of manufacturing a product is based on the knowledge and experience of the technologist and constructor. In the described approach, this process is supported by the proprietary module of the information and decision-making system, which, based on the accumulated knowledge, allows for an initial assessment of the feasibility of a selected element in a given technology. It allows taking into account a large number of intuitive factors, as well as recording expert knowledge with the use of formal languages. Additionally, the possibility of searching for and collecting data on innovative solutions, supplying the knowledge base, should be taken into account. The developed and applied models should allow for the effective use and representation of knowledge expressed in linguistic form. In this solution, it is important to use methods that support the selection of parameters for the production of casting. The type, number and characteristics of data have an impact on the effectiveness of solutions in terms of classification and prediction of data and the relationships detected.