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.

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 oil&gas enterprises have their own safety concerns list. Poor maintenance of equipment is one of the top safety concerns for many enterprises. There are a lot of methods of increasing of safety, but its shouldn’t be used alone. A complex approach and addition the modern technologies in safety ensuring make possible not only increase the quality but increase the efficiently of production. There are a lot of kinds of quality improving of maintenance of electromechanical equipment, one of them are the augmented reality system. This is a new technology and there are no methods and effective estimation for developing and using this technology in industrial production. Developing the special unified modules of augmented reality for maintenance of electromechanical equipment is the actual task. The aim of this research-to identify possible uses, to estimate the effectiveness in ensuring the safety of production and to develop a way of integrating into typical process control systems of the augmented reality system for maintenance of electromechanical equipment.