The results of tests for resistance to abrasive wear on highly abrasive hard rock white electrocorundum are presented. The main material of fast-wearing elements of mining and processing equipment-110G13L steel (Gadfield steel) in comparison with other 9 grades of steel and cast iron, including specially developed wear-resistant foreign steels such as Hardox and Miiluks, is analyzed. The studies were carried out using an experimental stand for studying the material wearing process. On the stand the sample was fixed in a holding device and, after being brought into contact with the abrasive, it was rotated under a constant load. As a result of the experiments, it was confirmed that the order of placement of the tested materials in terms of increasing wear resistance coincides with their placement in terms of increasing hardness. At the same time, the wear resistance of the most resistant material – U8A steel after quenching – is about 4 times higher than this indicator for the least resistant components – low-carbon steel 25L, including gray and high-strength cast iron SCH21, VCH35. The wear resistance of 110G13L steel, as well as 65G, U8 steels in the hardened state, is from 1.5 to 2 times higher than that of foreign steels M400, H450, M500, H500. The results of the conducted studies allow us to evaluate the analyzed materials on the basis of their wear resistance and hardness indicators on the feasibility of using them in the manufacture of fast-wearing parts of mining equipment. Based on the research data, it seems promising to develop new ways to increase the wear resistance of domestic steel, including 110G13L steel traditionally used in mining.

This article is devoted to the prediction of the residual life based on an estimate of the technical state of the induction motor. The proposed system allows to increase the accuracy and completeness of diagnostics by using an artificial neural network (ANN), and also identify and predict faulty states of an electrical equipment in dynamics. The results of the proposed system for estimation the technical condition are probability technical state diagrams and a quantitative evaluation of the residual life, taking into account electrical, vibrational, indirect parameters and detected defects. Based on the evaluation of the technical condition and the prediction of the residual life, a decision is made to change the control of the operating and maintenance modes of the electric motors.

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.