Analysis of technical and technological conditions for the emergence of emergency situations during the operation of electromechanical equipment of enterprises of the mineral and raw materials complex shows that when developing the basis for ensuring safe operation, it is necessary to take into account not only the technical condition, but also the non-stationary operation of the operating conditions of equipment, and the nonstationarity of operational operating parameters of technological processes. Violations of the operation of individual parts of the machine, not detected in time, can lead to severe accidents at work, as well as to unplanned downtime and loss of profits. That is why, the issues of obtaining and processing Big data obtained during the life cycle of electromechanical equipment, for assessing the current state of the electromechanical equipment used, timely diagnostics of emergency and pre-emergency modes of its operation, estimating the residual resource, as well as prediction the technical state on the basis of machine learning are very important. This article is dedicated to developing the special method of data storing, collection and aggregation for definition of life-cycle resources of electromechanical equipment. This method can be used in working with big data and can allow extracting the knowledge from different data types: the plants' historical data and the factory historical data. The data of the plants contains the information about electromechanical equipment operation and the data of the factory contains the information about a production of electromechanical equipment.

A lot of researchers are developing new DEM parameters calibration approaches based on an experiment plan or the use of learning algorithms. This research is aimed at improving iterative algorithms frequently used for calibration. The big time consumption as a main problem of iterative algorithms is questioned. It is proposed to use Random forest algorithm to determine DEM parameters impact on the measured bulk responses. Measured responses are the parameters obtained by image processing using a technical vision system. As a result of 200 experiments processing, DEM parameters impact values on each bulk response were generated and presented as histograms. Obtained results were interpreted on the basis of the bulk material behavior and its physical properties. There is a discussion on the possibility of developing a universal DEM parameters calibration method based on the iterative algorithm.

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.