This article takes an approach to creating a machine learning model for the oil and gas industry. This task is dedicated to the most up-to-date issues of machine learning and artificial intelligence. One of the goals of this research was to build a model to predict the possible risks arising in the process of drilling wells. Drilling of wells for oil and gas production is a highly complex and expensive part of reservoir development. Thus, together with injury prevention, there is a goal to save cost expenditures on downtime and repair of drilling equipment. Nowadays, companies have begun to look for ways to improve the efficiency of drilling and minimize non-production time with the help of new technologies. To support decisions in a narrow time frame, it is valuable to have an early warning system. Such a decision support system will help an engineer to intervene in the drilling process and prevent high expenses of unproductive time and equipment repair due to a problem. This work describes a comparison of machine learning algorithms for anomaly detection during well drilling. In particular, machine learning algorithms will make it possible to make decisions when determining the geometry of the grid of wells—the nature of the relative position of production and injection wells at the production facility. Development systems are most often subdivided into the following: placement of wells along a symmetric grid, and placement of wells along a non-symmetric grid (mainly in rows). The tested models classify drilling problems based on historical data from previously drilled wells. To validate anomaly detection algorithms, we used historical logs of drilling problems for 67 wells at a large brownfield in Siberia, Russia. Wells with problems were selected and analyzed. It should be noted that out of the 67 wells, 20 wells were drilled without expenses for unproductive time. The experiential results illustrate that a model based on gradient boosting can classify the complications in the drilling process better than other models.

Aluminum master alloys with rare earth metals are widely studied by many scientists around the world, but research on the production of Al-Er master alloys is still limited. The purpose of this work is to study the microstructure parameters of aluminum-erbium master alloys obtained by metallothermic reduction of salt mixtures containing erbium oxide or fluoride. The structural features were investigated by optical and scanning electron microscopy, and the dependence of the microhardness of the eutectic and solid solution fields of obtained master alloys on the content of erbium in the master alloy was determined. Studies have shown that master alloys obtained by metallothermic reduction of erbium compounds from chloride–fluoride melts are characterized by a uniform distribution of Al₃Er intermetallic compounds in the volume of double eutectic [(Al) + Al₃Er] and have a strong grain refinement effect. The analysis of the microstructure showed that the structure of the master alloys varies depending on the content of erbium. When the content of erbium in the master alloy is up to 6 wt.%, the eutectic structure is preserved. When the content of erbium in the master alloy is 8 wt.% or more, the structure becomes a solid solution with individual inclusions of various shapes and intermetallic compounds.

Iron and steel industry is one of the industrial branches making substantial input in provision of economic growth in Russian Federation; in this connection, innovation development of the metallurgical industry is rather important. The patent researches, in their turn, allow to get statistical data about the patents that are indicators of technological development and reliable parameter of innovation activity in the industry. The paper is devoted to study of the tendencies of innovation development of the national vertically integrated mining and metallurgical companies in order to reveal technological and innovation leaders and trends in this industry. The paper uses the patent method of technological prediction based on patent researches. The results of analysis of patent documents for the large metallurgical companies (Severstal, Magnitogorsk Iron and Steel Works (MMK), Novolipetsk Iron and Steel Works (NLMK), Metalloinvest Management Company, EVRAZ Group, Mechel) are presented. The rating of Russian patentee companies — leaders in iron and steel industry — is prepared for the period 2000-2020. The legal status of patent documents included in the patent portfolios of the companies is determined. Patent activity of the companies is analyzed during the examined period with differentiation by years. The patent documents registered in Russia during 20 years, as well as the documents of Nippon Steel and JFE Holdings are also analyzed for comparison. The collection for each patentee was obtained and their interest areas (corresponding to the definite classes of International Patent Classification (IPC)) were examined with revealing of the most important IPC subgroups. Activity of authors of the examined companies is investigated in order to find out the leading technological development specialists.

The article is devoted to the study of the process of synthesis of master alloys, the magnesium-gadolinium. Based on the analysis of diagrams of the state and requirements for fluxes for melting magnesium alloys, the composition of the salt mixture was chosen. Differential thermal analysis (DTA) determined the temperature ranges of thermal effects in the melting of components of the salt mixture KCl – NaCl – CaCl2 – MgCl2 – CaF2 – GdF3 and in the reduction of compounds of gadolinium magnesium. It is established that upon contact of the molten technological salt mixture, a complex compound of gadolinium Na5Gd9F32 is formed, which in the preparation of Mg – Gd master alloy is a precursor for the recovery of gadolinium. As a result of a series of experimental melting, the basic laws of the synthesis of magnesium-gadolinium master alloy from the selected technological salt mixture were revealed, the main factors of the metallothermic process affecting the degree of gadolinium recovery were determined. The necessary content of the alloying element in the master alloy is achieved by preliminary adjustment of the content of the initial compound of gadolinium fluoride in the technological salt mixture. The influence of technological parameters on the yield of gadolinium in the master alloy was determined on the basis of experimental melting. The maximum yield of gadolinium — 98.4%, is achieved by using a technological salt mixture of the composition KCl – NaCl – CaCl2 – MgCl2 – CaF2 – GdF3, intensive stirring of the melt at a holding time of 25–30 minutes and a temperature of at least 720 оC. The microstructure, chemical and phase composition of the obtained master alloys samples were investigated. It is established that the structure of the samples of the obtained magnesium-gadolinium master is dendrites of a solid solution of α-Mg, along the boundaries of which MgxGdy compounds are located.

The article is devoted to the research into the process of the triple magnesium-zinc-gadolinium master alloys synthesis. As a result of thermal analysis, the temperature intervals of thermal effects during the process of gadolinium recovery from its fluoride in the melt of KCl – NaCl – СaCl2 salts with magnesium and zinc were established. As a consequence of a series of experiments, the main regularities of the magnesium-zinc-gadolinium master alloy synthesis from the selected technological salt mixture were recognized, and the main factors of the metallothermic process affecting the degree of gadolinium recovery were also determined. It is experimentally proved that during the triple Mg – Zn – Gd master alloy synthesis, the rational magnesium to zinc ratio, which reduces the synthesis temperature and synthesis time of triple master alloys when reducing gadolinium from the technological KCl – NaCl – СaCl2 – GdF3 salt mixture, is 1:2. The magnesium-thermal reduction process on zinc addition is characterized by the high extraction level of gadolinium (up to 99.2%). The microstructure analysis has showed that a uniform distribution of intermetallic compounds (Mg3GdZn6) in the magnesium-zinc double eutectic volume distinguishes the resulting 25Mg – 50Zn – 25Gd triple master alloys. The authors express their gratitude to V. L. Ugolkov, Candidate of Technical Sciences, Senior Researcher of the Nanostructure Research Laboratory of the Institute of Silicate Chemistry of Russian Academy of Sciences, for assistance in conducting thermal analysis.