There is a tendency to increase the use of demand response technology in the Russian Federation along with other developing countries, covering not only large industries, but also individual households and organizations. Reducing peak loads of electricity consumption and increasing energy efficient use of equipment in the power system is achieved by applying demand management technology based on modeling and predicting consumer behavior in an educational institution. The study proposes to consider the possibility of participating in the concept of demand management of educational institutions with a typical workload schedule of the work week. For the study, statistical data of open services and sources, Russian and foreign research on the use of digital and information technologies, analytical methods, methods of mathematical modeling, methods of analysis, and generalization of data and statistical methods of data processing are used. An algorithm for collecting and processing power consumption data and a load planning algorithm were developed, including all levels of interaction between devices. A comparison was made between the values of the maximum daily consumption before and after optimization, as well as the magnitude of the decrease in the maximum consumption after applying the genetic algorithm. The developed algorithm has the ability to scale, which will increase the effect of using the results of this study to more significant values. Load switching helps to reduce peak consumption charges, which often represent a significant portion of the electricity cost.

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 research considers conducting orthogonal experiment (OT) as one of the stages in developing a new discrete element method (DEM) parameters calibration approach. The measured responses in experiment are the parameters obtained by DEM animation processing using machine vision system (MVS). The variable factors in experiment are DEM parameters. A brief overview of an existing calibration approaches given in the article. The choice of OT as a design of experiment tool among other mathematical tools discussed. Experiments conducted using specially developed rig where bulk material's flow captured as DEM animation. DEM animation converted to video and then processed using MVS that allow register the values of such parameters as angle of repose or expiration time (measured responses). The results of the OT show that it is possible to identify four measured responses with the most valuable correlation coefficient. DEM parameters with the biggest influence on the measured responses identified for each of the obtained regression. Obtained results are useful in learning or iterative algorithms development for DEM parameters calibration.