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.

Electromechanical equipment is widely used. It is used in industrial enterprises, in the spheres of public services, in everyday life, etc. Maintenance servicing of electromechanical equipment is an important part of its life cycle. High-quality and timely service can extend the life of the electromechanical equipment. The creation of special systems that simplify the process of servicing electromechanical equipment is an urgent task. Such systems can shorten the time for maintenance of electrical equipment, and, therefore, reduce the cost of maintenance in general. This article presents an analysis of information on the operation of service services for maintenance and repair of electromechanical equipment, identifies the list of services, and estimates the time required to perform basic service operations. The structure of the augmented reality system is presented, the ways of interaction of the augmented reality system with the automated control systems working at the enterprise are presented.

Radial charts were commonly used in the industry to allow retrospective assessment of technological parameters. Today it is relevant to digitize the obtained data in order to simplify the automation of technological processes. Digitization of radial charts by means of standard methods is carried out with the help of human labor at significant time costs. The article proposes an automated method for digitizing radial charts using software, developed in the LabVIEW programming environment. The results of processing radial charts are displayed on the screen in numerical and graphical form, and can also be exported to a file (for example, to Notepad or MS Excel). The presented technique can be applied to images obtained on a color or black-and-white scanner, which minimizes geometric distortions, associated with the conversion of a paper document into electronic form, and ensures recognition quality of the clear plot line with an average relative error of up to 3 %. In case of ink fading or perspective photos of the diagram, the value of relative error can reach 8 %, as a result of which additional manual correction of the data will be required.