In this paper, the possibility of applying graph neural networks (NN) to study the structure of copper centers of zeolites is considered. The dataset used for NN training was prepared using the FDMNES software based on the finite difference method and included more than 2100 Cu K-XANES spectra for Cu-MOR. The performed study demonstrated the capability of graph neural networks to reproduce the Cu K-XANES spectrum corresponding to a particular model of the copper center in the zeolite framework.

Keywords: zeolite, mordenite, atomic structure, XANES, machine learning, graph neural networks

Based on the experience gained during the use of Autodesk Revit in the design of power supply systems, the authors assess the features of the implementation of the construction of projects in this section that meet domestic regulatory documentation. A comparative analysis of the methods of constructing power supply projects is given, their advantages and disadvantages are revealed, which is important both from a scientific and practical point of view with a small amount of information in this area that does not have an advertising component.

Keywords: Autodesk Revit, BIM, information model, bilding engineering, power supply system, building technology

This article discusses the forecasting of the collection of payments in post offices, taking into account seasonality and the use of machine learning. An algorithm for constructing a calculation model has been developed, which provides an opportunity for analysts of the Russian Post to make a monthly forecast of the collection of payments for each UFPS (Federal Postal Administration), taking into account seasonality. This model allows you to identify deviations from the norm in matters related to the collection of payments and more accurately adjust the increase in tariffs for services. The SSA algorithm is considered, which consists of 4 steps: embedding, singular decomposition, grouping, diagonal averaging. This information system is implemented in the form of a website using a framework ASP.NET Core and libraries for machine learning ML.NET . Then the forecast is evaluated using various methods.

Keywords: mathematical modeling, seasonally adjusted forecasting, collection of payments, machine learning, neural network

The dynamic model of personnel management in a real estate agency is investigated. The structure of the management system includes a real estate company as a Leader and a realtor as a Slave. The relations between them are built on the basis of a hierarchy corresponding to the information regulations of the Stackelberg games. Motivation is used as a method of hierarchical management. Algorithms for achieving equilibrium in different information regulations are presented. The numerical implementation of these algorithms is based on simulation modeling, the results are analyzed.

Keywords: real estate company, hierarchy, simulation, stackelberg's game, stackelberg's game with feedback, motivation, leader, slave, dynamic system

The article discusses the methods and approaches developed by the authors for the recommendation system, which are aimed at improving the quality of rehabilitation of the patient during respiratory training. To describe the training, we developed our own language for a specific subject area, as well as its grammar and syntax analyzer. Thanks to this language, it is possible to build a devereve describing a specific patient's training. Two main methods considered in the article are applied to the resulting tree: "A method for analyzing problem areas during training by patients" and "A method for fuzzy search of similar areas in training". With the help of these methods, it is proposed to analyze the problem areas of patients' training during rehabilitation and look for similar difficult areas of the patient to select similar exercises in order to maintain the level of diversity of tasks and involve the patient in the process.

Keywords: Recommendation system, learning management system, rehabilitation, medicine, respiratory training, marker system, domain-specific language, Levenshtein distance

The article is devoted to modeling heating of fuel oil using a pulsed fluid flow in the SolidWorks Flow Simulation software module. In the future, the use of this technological solution can be considered by a number of industries in the Russian Federation and abroad. The purpose of this article is to describe the results of a computer model of the technological process under study. The computer calculation of the fuel oil heating model using a pulse flow makes it possible to evaluate the efficiency of the process and determine the optimal parameters to achieve maximum efficiency. This will help to reduce the cost of heating fuel oil and increase the efficiency of industrial equipment of enterprises.

Keywords: fuel oil, oil, coolant, shock unit, diaphragm pump, pulse flow, turbulent mode, cavitation, solidworks flow simulation

The paper describes the procedure for conducting a competition for regression models based on statistical data for the East Siberian Railway. At the same time, it is assumed to build a set of additive alternative versions of the model with the subsequent choice of the best option based on the involvement of a number of adequacy criteria. The unloading of wagons is singled out as the output variable of the model, and the input variables are: the average gross weight of a freight train, cases of failures of technical means of the 1st – 2nd category of operational nature, the working fleet of freight wagons. The implementation of the model competition allowed us to build over two hundred alternative options, from which the best alternative was selected using multi-criteria selection methods based in this case on a continuous criterion of consistency of behavior.

Keywords: railway transport, mathematical model, regression analysis, least squares method, model competition, adequacy criteria, multi-criteria selection

In this article, a computer simulation of the movement of passengers on escalators was carried out, taking into account different (four) scenarios for organizing the movement of passengers, the intensity of passenger flow, and also analyzes the influence of social distance on the speed of ascent. The dependences of the change in the time spent by passengers on covering the path from the center of the platform to the moment of ascending the corresponding escalator were constructed. The results of the study make it possible to identify differences in the efficiency and comfort of passenger movement depending on the chosen layout and load. These findings can be useful for optimizing the operation of public transport and metro systems, providing safer and more comfortable travel for passengers in various conditions.

Keywords: analysis of human flows, ensuring safety in the metro, organizing human flows, computer modeling, optimization of passenger flow

Diseases of the cardiovascular system are the main cause of death in the world. The main way to diagnose diseases of the cardiovascular system is to take an electrocardiogram of the patient. Automatic processing of electrocardiogram signals will allow doctors to quickly identify heart problems in a patient. This article presents a method for calculating the detail vector for neural network processing of a twelve-channel electrocardiogram signal. Adding a detail vector to the electrocardiogram signals improves the classification accuracy to 87.50%. The proposed method can be used to automatically classify two or more channel electrocardiogram signals.

Keywords: electrocardiogram, recurrent neural network, neural network with long-term short memory, detailing vector, PhysioNet Computing in Cardiology Challenge 2021

In today's world, facial recognition is becoming an increasingly important and relevant task. With the development of technology and the increasing amount of data, the need for reliable, accurate and efficient face recognition systems increases. Neural networks demonstrate high efficiency in solving computer vision problems and have great potential for improving existing mathematical models of face recognition. This paper is devoted to the study of methods for human face recognition, the Viola-Jones algorithm will be discussed in detail, which, which can be applied in the task of face recognition using neural networks. It will also analyse techniques for training deep learning models using libraries that also use the Viola-Jones algorithm and describe an algorithm for using the trained model in an API that can be used in desktop and mobile applications.

Keywords: biometric identification, human face recognition, mathematical models, face recognition methods, deep learning, convolutional neural networks, tensorflow

The article proposes a method for determining the optimal location of a self-supporting fiber-optic cable laid along the supports of high-voltage power transmission lines. The methodology is focused on the use of both a manual calculation method and with the use of electronic computing equipment.

Keywords: fiber-optic communication line, electric field, induced voltage potential, electrothermal degradation, optimization of placement of self-supporting fiber-optic cable

This article proposes a method for correcting the intermediate trajectory obtained by one of the planning methods, taking into account the limitations on the linear velocity and acceleration of the apparatus, as well as on the angle of its pitch. This technique is combined with the smoothing procedure, which includes the stage of minimizing the length of a piecewise polyline trajectory and rounding the corners at the vertices with the construction of a smooth time parametric representation of it using the modified Dubins method.

Keywords: robotics complex, unmanned aerial vehicle, stability and controllability of the vehicle, motion planning, local adjustment of the planned trajectory, reduction of energy costs

When choosing an intensification method, the assessment of thermal-hydraulic efficiency is an important criterion. In this paper, the thermal-hydraulic efficiency of the pulsating method of heat transfer intensification was assessed as applied to an in-line tube bundle. The thermohydraulic efficiency was estimated by comparing the ratio of the increase in the Nusselt number to the increase in the coefficient of friction factor in a pulsating flow compared to a stationary flow. The coefficient of friction factor was determined by numerical simulation in AnsysFluent. The results of a numerical study showed that an increase in the product of the pulsation amplitude and the Strouhal number leads to a decrease in the thermal-hydraulic efficiency at all values of the Reynolds number, while the thermal-hydraulic efficiency is higher at the minimum values of the Reynolds number.

Keywords: Reynolds analogy factor, flow pulsation, heat transfer enhancement, thermal hydraulic efficiency.

Construction control at the stage of preparation for the commissioning of the object requires checking the quality of external enclosing structures according to the air permeability parameter. The GOST 31167 methodology available to specialists, as well as other similar methods, is based on the principle of creating and maintaining the required pressure drop in the room and beyond its boundary for a long time while simultaneously determining the flow rate of the air supplied for testing. The essence of this method is that it limits the possibility of quantifying the values of air permeability through specific sections of external enclosing structures and allows you to determine only complex indicators for one room or a group of rooms without specifying specific values of defects in various types of exterior walls, window fillings, door openings, and abutments. The proposed method of qualitative and quantitative assessment of air permeability is based on an additional analysis of the temperature fields of the internal surfaces of external enclosing structures while ensuring a given difference in pressure and temperature of the indoor and outdoor air entering the room by creating a vacuum. Conducting field studies is necessarily complemented by the results of numerical modeling of structures in undisturbed and defective states.

Keywords: non-stationary heat transfer, numerical modeling, calculation of temperatures in the defect region, analysis of temperature fields, air permeability resistance, experimental evaluation of air permeability

In the work, a method was implemented that allowed estimating the parameters of a control object based on the objective function, the least squares method, and the solution to the system of nonlinear equations was the Levenberg-Marquardt method. The numerical and laboratory experiments carried out allow us to speak about the effectiveness of the proposed method.

Keywords: identification, optimization, least squares method, Levenberg-Marquardt method, differential equation

In this paper, we review a number of algorithms for solving the problem of building a map and the problem of SLAM - Simultaneous localization and mapping - in various formulations. These tasks are solved on a graph structure that describes a mine working, in which a localization system from stationary access points is installed. To solve the SLAM problem, the FastSLAM algorithm is used in various modifications, depending on the method for estimating the positions of access points. In all the proposed solutions, it was possible to achieve an error in estimating the positions of access points of no more than 2 meters. The problem of building a map is solved as a combinatorial problem of searching for a permutation of access points by known positions. The proposed permutation search algorithm showed tangible advantages in terms of execution time over the exhaustive search method on systems with 5 or more access points.

Keywords: graph, mining, localization, map construction, SLAM, MCMC, particle filter, Kalman filter, Bayes method

The comparison of technological settlement values during the construction of various variants of diaphragm wall is presented. Numerical modeling of the construction of a diaphragm wall enclosure was performed in weak water-saturated clayey soils using the Plaxis 3D software package. The investigation results revealed that the technological settlement of the building foundation caused by constructing a trench-type diaphragm wall significantly exceeds the values observed in the construction of a diaphragm wall with augered piles.

Keywords: technological settlement, excavation enclosure, diaphragm wall, numerical modeling, Plaxis

The article discusses a mathematical model of an excavator's hydraulic shears, which describes the functional dependencies of their main parameters based on regression statistics. An algorithm for the process of selecting optimal parameters for hydraulic shears used to destroy metal structures during the dismantling process is presented, and a description of the developed software application that automates the process of selecting these parameters is given. The application described in the article will reduce the time required for the design stage of excavator attachments.

Keywords: attachments, hydraulic shears, dismantling, metal cutting, design, mathematical model, automation, selection of parameters, algorithm, program

The article discusses automatic selection of coefficients for PID controllers of quadcopter motors based on a 3D model. This selection became possible thanks to the method discussed in the article for exporting a 3D model of a quadcopter, created in the Solidworks CAD system, into the Matlab/Simulink environment, as well as with the further use of the SimMechanics library. To select the coefficients, a quadcopter control system is also implemented to the Simulink project, the signals from one sent to the motors in accordance with their physical location. The result of the article is a flight visualization of a 3D model of a quadcopter with a control system implemented in Simulink.

Keywords: solidworks, matlab, simulink, quadcopter, uav, pid, simmechanics

The paper calculates the probability of failure-free operation of parts of the supporting structure of foreign-made lifting equipment designed to perform loading and unloading operations of stone building material. When performing calculations, computer modeling of the stress-strain state by the finite element method was used. A distinctive feature of the proposed calculation methodology is the minimum required number of computer experiments, given that some of the input data are variable.

Keywords: probability of failure-free operation, lifting equipment, reliability

Currently, loaders for piece loads used in the technological process of loading-transporting and laying barrels of oil are widely used in industry. In particular cases, during loading and transport operations, the functionality of the loader is sufficient, but when laying cargo or obstacles occur, it is necessary to maneuver using the loader chassis, which significantly increases the execution time of the technological process. The results of the conducted studies have shown that when performing the technological operation of capturing, transporting and stacking barrels, the time to move the chassis is up to 12%, while the loader performance coefficient is 0.65. Numerical modeling of the positioning process of the load-handling body of the output link of the loading and transport unit is carried out, on this basis, a loader design based on a stacker is proposed and developed. The degree of mobility of the manipulation mechanism is calculated.

Keywords: numerical modeling, loader, manipulator, hinges, chassis, structural analysis, degree of mobility, kinematic analysis, service area, lifting body, mechanism

There are now many reasons why training in artificial intelligence (AI) technologies can be important for today's students. Therefore, AI-related disciplines are actively included by universities in undergraduate and graduate programs. It is important to teach students to understand how such technologies work and how they can be used to solve various problems. In turn, training is unthinkable without demonstrating examples of solving various problems. An important step in solving the problem of machine learning in general, incl. task of computer vision, is the stage of formation of the training sample. Therefore, the idea arose of writing a program that would be able to generate datasets on various topics for computer vision tasks. The data format of the generated sample for training train.csv is generally accepted and looks like this: each line is a description of one image; the first column contains the class labels to which the image belongs; the remaining columns contain the pixel values of the image, for example as a flat vector, where each value corresponds to the brightness of a corresponding pixel in the image. The resulting datasets can be used to organize the project activities of students on artificial intelligence.

Keywords: artificial intelligence, machine learning, computer vision, neural network, training set, dataset, C#, pixel, subpixel image processing, organization of student project activities

In this study, the thermal properties of porous materials with the topology of triply periodic minimal surfaces (TPMS) of Schwarz are investigated. By generalizing the results of computational experiments, the dependencies of the thermophysical properties of TPMS materials on macrostructural parameters such as size and thickness of the elementary cell have been obtained. The properties of the most common thermoplastic polymers PETG, ABS, PLA, and PHP used in additive manufacturing have been explored. It is demonstrated that the thermal conductivity coefficients of the examined TPMS materials can be represented as a linear function of the dimensionless geometric parameter – the relative thickness of the elementary cell wall. By varying this parameter, and consequently the geometric structure of the porous medium, it is possible to obtain a material with desired thermophysical properties. Verification of the obtained finite element method results is conducted based on the analysis of mesh convergence of solutions.

Keywords: effective thermal conductivity; heat transfer; porous material; porosity; thermoplastic polymer; ordered macrostructure; Schwarz minimal surface; triply periodic surface

The possibilities of a little-studied method for obtaining nanosized materials of electronic engineering with a given substructure, the zone sublimation epitaxy (ZSE) method, are discussed. In the work, it is combined with the method of gradient liquid phase epitaxy (GLE). A specific feature is mass transfer in a two-phase medium (a solid substrate and an inert gas phase acting as a transport medium) with preliminary deposition of a matrix layer formed from the melt. A feature of the sublimation process in the study was the crystallization of low-melting iron-silicon eutectic. A mathematical model of the process was proposed and compared with the experimental results. Island structures of the composition silicon (more than 90%), iron (up to 8%) and chromium (about 1.5%) have been obtained. Their parameters and size distribution were studied. A Solver-HV scanning probe microscope and a Quanta-200 scanning electron microscope were used. The study shows that the use of sublimation transfer transients makes it possible to reproducibly form doped silicon nanolayers and transform them into regular mesostructures.

Keywords: microsize growth cell method, zone sublimation epitaxy, gradient liquid phase epitaxy, island nanostructures

Forecasting the consumption of electrical energy and power is an urgent and significant problem. This paper discusses current methods for predicting the consumption of electrical energy, reflected in various scientific papers, their analysis is carried out with the identification of more promising forecasting methods.

Keywords: energy consumption forecasting, statistical forecasting methods, neural network forecasting methods, hybrid forecasting methods