Big Data analysis is becoming an everyday task for companies all over the world, including Russian companies. Due to advances in technology and the reduction in the cost of storage systems, companies can now collect and store large volumes of heterogeneous data. The important step of extracting knowledge and value from such data is a challenge that will eventually be met by all companies seeking to maintain their competitiveness and place in the market. However, companies face several challenges when it comes to collecting, pre-processing, and integrating data into cohesive data sets designed to deliver analytics. In this article, the above problems and possible solutions are illustrated using the example of cleaning, integration, and normalization of data obtained in the measurement of indicators for the Vanyukov melting furnace process. The article considers an approach to the study of metallurgical processes using the analysis of large operational control data sets. Standard methods of processing the data sets of operational process control are used. The correlation analysis of the main process parameters is carried out. The results are interpreted for their further practical application.

The paper presents a methodology for training neural networks for vision tasks on synthe-sized data on the example of steel defect recognition in automated production control systems. The article describes the process of dataset procedural generation of steel slab defects with a symmetrical distribution. The results of training two neural networks Unet and Xception on a generated data grid and testing them on real data are presented. The performance of these neural networks was assessed using real data from the Severstal: Steel Defect Detection set. In both cases, the neural networks showed good results in the classification and segmentation of surface defects of steel workpieces in the image. Dice score on synthetic data reaches 0.62, and accuracy—0.81.

The article presents the results of experimental investigations of the magnitude and nature of change loads drive of mine shuttle car VS-30 used to deliver ore to extraction chambers in potash mines. The design of program-recording complex "VATUR" developed by employees of the department "Mining Electrical Engineering" Perm National Research Polytechnic University. In the investigation of operating modes of the drive of self-propelled mine wagons were carried out measurements and recording the instantaneous values of voltage and current of electric motors, calculated values of active and apparent power consumed by the motor pump stations and bottom conveyors of mine shuttle car. Carried out investigations modes of operation and changing loads on the units and details of the tram drive. It is proved that the operation of electric motors of the mine shuttle cars increased characterized by a systematic overload. Outdated system controlling the rotational speed of shafts drive motor gives rise to considerable dynamic loads on components of mechanical transmissions for shuttle cars. Significant loss of time causing the reduction in technical performance longwall set of equipment of potash mines arises during the maneuvering operations and unloading ore from shuttle cars. Based on the analysis of the change of loading drives and statistics of dangerous failures were justified the technical solutions to improve the reliability of mine shuttle car. The recommendations to increase the efficiency of transporting potash in the longwall set of equipment, improving maneuverability of self-propelled cars and reduce downtime for unloading are given.