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

The article discusses the importance of using computer modeling to analyze the technical and operational characteristics of products, identify possible failures. The paper presents the results of a study of the operational conditions of a threaded connection, and draws conclusions about the effectiveness of using the ANSYS software in the design of mechanical engineering products.

Keywords: threaded connection, modeling, innovative technologies, optimization, safety margin, performance characteristics, thread pitch, mechanical engineering

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

Electrocardiogram signals have unique characteristics and structure that are difficult to fake. This is due to the fact that the electrical activity of the heart is unique for each person. In addition, the main biometric parameters are hidden during ECG authentication, which makes the process more secure and protected from counterfeiting. The purpose of this study is to evaluate the effectiveness of neural networks for ECG authentication for signals with non-periodic cardiac arrhythmias. The Siamese neural network has been developed as a model. The stages of preprocessing of ECG signals taken from the MIT-BIH database are also described. The model presented in the paper has achieved the following results. Accuracy: 99.69%. Sensitivity: 99.43%. Specificity: 99.94%. ROC-AUC: 99.69%. The results allow us to conclude that the proposed model can effectively authenticate users who have non-periodic cardiac arrhythmias, provided at least a small number of registered standards with violations.

Keywords: biometric authentication, ECG, Siamese neural network, convolutional neural network, Euclidean distance, ROC analysis

Constant force supports are used in all gas and oil refineries in cases where it is necessary to provide the mobility of the pipeline at the attachment points. The article discusses the algorithm for calculating the shape of the support profile details, which has a certain design. These details provide the constancy of the pipeline support vertical force when it is transferred from the compression spring to the support point. Analytical and geometrical variations of calculation are given. The article will be useful to specialists involved in the design of pipeline supports.

Keywords: movable joint, geometric calculation, variable stiffness, lisega, import substitution

This article implements an algorithm for recognizing the markings of a freight container based on deep neural networks. The main advantage of the proposed algorithm is the absence of the need for additional image transformations for marking localization and character segmentation. The EAST algorithm was used to solve the localization problem. To recognize the owner code and serial number of the container, Faster R-CNN Resnet 50 neural network models were trained. As a result of assessing the accuracy of the algorithm, appropriate conclusions were made, and possible options for improving the algorithm were formulated.

Keywords: machine learning, algorithm, cargo containers, neural network, image classification, recognition

A structural model of an intelligent classifier of unstructured textual data according to the degree of confidentiality is presented, which is a two-level cascading ensemble of classifier models. The meta-model of a fully connected neural network architecture, which has the greatest impact on the classification efficiency, is highlighted. The multi-criteria task of configuring the intelligent classifier is decomposed into the task of selecting configurable hyperparameters of the meta-model and the task of selecting their values. Taking into account the selected hyperparameters of the neural network meta-model, the multi-criteria task of selecting hyperparameters to be configured is presented in the form of a hierarchy that includes the goal, criteria and alternatives. A method for selecting configurable hyperparameters of an intelligent classifier of unstructured text data by the degree of confidentiality based on the hierarchy analysis method has been developed.

Keywords: DLP system, unstructured text data, intelligent classifier, hyperparameters, hierarchy analysis method

The main characteristics of the building for dynamic calculation are the frequency and forms of natural oscillations. These values are related to the rigidity of the building, the rigidity of the elastic foundation and its mass. To study the effect of the stiffness of the elastic foundation, an equivalent idealized model of free oscillations of a cantilever rod is considered. The calculation takes into account the rigidity of the support. For the considered model, a transcendental equation and its numerical solution is obtained. Solutions for the limiting cases of elastic foundation stiffness are obtained. The obtained results allow us to analyze the effect of the stiffness of the elastic foundation on the frequencies of natural oscillations. It is calculated that with an increase in the stiffness of the elastic foundation, the frequencies of natural oscillations increase. The influence is limited and has an asymptotic character. The rigidity of the elastic foundation can have a significant effect on the natural frequencies of the first five bending forms of natural oscillations and may not be taken into account for higher-order forms.

Keywords: dynamics, natural oscillations, natural frequencies, building, structure, transcendental equation, elastic foundation, elastic support

The paper considers a model problem of a combined thermal and diffusion process in silicon. The mathematical model of this process is an initial-boundary value problem for a system of linear partial differential equations of parabolic type. In this system, one equation describes the process of heat propagation in silicon, and the other describes the process of impurity diffusion in it. In this case, the equations are not independent in the same way that the diffusion coefficient depends on temperature. For each equation in this system, the corresponding initial-boundary conditions are set. An implicit difference scheme and the classical sweep method are used to find an approximate solution to the problem that has arisen. The paper presents a description of a numerical algorithm and exact calculation formulas for solving a discretized parabolic problem.

Keywords: model of thermal diffusion process, numerical simulation, sweep method, implicit difference scheme

The article analyzes the shaping of buildings and structures in modern architectural practice. Form in architecture is primarily a means of expressing and translating concepts. It's also what ultimately fills and divides the space we live in. Form in architecture can have great symbolic and cultural significance and can transform a space for the better or for the worse. The simplest of the forms are known as primary forms. The main shapes include circles, triangles and squares. Each form can be created by a combination of basic forms. When rotated or expanded, basic shapes can create three-dimensional volumes known as basic bodies. In modern architectural practice, it is very common to resort to the use of complex shapes created using spatial curves. The task of the architect is a complete visual representation of such forms in drawings, as well as using modern software graphics packages. The article raises the problem of the correct interpretation of architectural forms formed by such spatial curves (using the Hilbert curve as an example).

Keywords: architecture, spatial curves, axonometric projections, Hilbert curve, modernism, shaping, ornamentation, space

The article presents and substantiates the structure of the original combined pathospecific measuring device for the diagnosis of glaucoma, which will allow for a comprehensive analysis of the hydro- and hemodynamics of the eye and thereby improve the quality of glaucoma diagnosis. Based on this structure, a detailed metrological analysis of this installation as a means of biomedical measurements was given in the work. Brief conclusions on the work are given and prospects for the further development of the project are determined.

Keywords: combined pathospecific measuring device, tonometry, rheography, sphygmography

Methods for determining the position of the center of gravity and the static stability margin of an aircraft in flight are considered. Based on the analysis of the motion of an aircraft as a rigid body, possible methods for determining the position of the center of gravity are determined and their errors are calculated. Comparison of the errors of various methods made it possible to conclude that it is expedient to use a method based on the use of information on the fuel reserve.

Keywords: center of gravity, moments of inertia of the aircraft, free vibrations, fuel consumption

In the article, a mathematical model of the oscillations of an aerodynamic pendulum in the flow of a moving medium is constructed and investigated. As a model of the effect of the medium on the body, the model of quasi-static flow around the plate by the medium is adopted. According to this hypothesis, the aerodynamic forces acting on the body are applied at the center of pressure. In our problem, the pressure center is movable relative to the plate. The equations of motion for the body under consideration are obtained. The transition to new dimensionless variables has been carried out. The violation of uniqueness in determining the angle of attack at points where the air velocity of the pressure center is close to zero is shown. Envelopes for some areas of ambiguity are constructed using multiple solutions of algebraic nonlinear equations derived from kinematic relations. To do this, the coordinates of the return points are determined, the solution of the equations themselves is found, and the boundaries of the areas of ambiguity are depicted. In the mathematical package MATLAB 18, a program is written that.

Keywords: body, ambiguity area, envelopes, return points

The article is devoted to the development of a computer program with the help of which it is possible to simulate the number of flowing and non-flowing cultures of microorganisms for educational purposes. The Mono model is taken as the basic model of biomass growth. The apparatus of ordinary differential equations is used for the mathematical description of cell populations. As a result, the structure and functionality of the electronic learning module with its subsequent implementation in Python has been developed. As a result, the laboratory work "Modeling of flowing and non-flowing cultures of microorganisms" was developed, in the form of a computer program, performed within the framework of mastering the discipline "Biophysics" and consisting in studying the basic principles and methods of modeling the processes of development of microorganisms in flowing and non-flowing cultures. The developed program is implemented in the educational process.

Keywords: computer program, cell population, biophysics, microorganisms, computer modeling, Mono model, Python, biomass, flow conditions, non-flow conditions, system of equations

When erythrocytes move along a narrow capillary, they take an asymmetric shape and roll along the capillary like a tractor caterpillar (tank - treading motion). The shape of the erythrocyte is approximated by a truncated cylinder and is uniquely determined by the diameter of the erythrocyte in the capillary, the volume and surface area of the erythrocyte. Other input parameters are the speed of the erythrocyte in the capillary, the frequency of rotation of the erythrocyte membrane, the charge of the erythrocyte, and the number of closed trajectories along which the charges move. It is assumed that the negative charges located on the membrane are equal in magnitude and distributed evenly over the membrane and move along closed trajectories together with the membrane. From the last parameters, you can find the number of charges on the erythrocyte membrane. According to the Biot-Savart-Laplace law, mobile charges generate a magnetic field in the surrounding space. Using computer calculations, the distributions of the magnetic field strength were obtained both near a single erythrocyte rolling along a narrow capillary, and near a capillary along which several erythrocytes move, at various values of hematocrit. The dependence of the maximum value of the magnetic field strength near the capillary on the hematocrit is found. In particular, it was shown that at a distance from the capillary equal to 8 capillary diameters, the maximum value of the magnetic field strength increases by a factor of 1.29–1.36 (depending on direction) with increasing hematocrit from 12.27% to 18.25%.

Keywords: mathematical model, magnetic field, charge, membrane, erythrocyte, capillary, hematocrit

The relevance of creating a chatbot for advising applicants, promoting the university brand and raising awareness about the university is considered. The basic principles of the chatbot functioning are determined. Modeling of the sequence of processes using IDEF0 and UML is performed. The article contains a description of the chatbot algorithm. Activity and state diagrams are used to visualize this algorithm. The graphical interpretation of the logic of the interaction of the system elements is performed at the IDEF3 documentation level. A physical model for storing the data necessary for consultation is presented; the purpose of the tables obtained is described. The issues of fuzzy search by keywords are considered. The article describes the error correction process using the n-gram distance metric and the Damerau-Levenshtein metric. The functioning of the chatbot in the consultation mode when searching for keywords with errors in the user's message is demonstrated.

Keywords: chatbot, dialog system, messenger, natural language processing, fuzzy search, Damerau-Levenstein distance, n-gram

This article describes training a neural network to recognize the digits of a freight container number. Due to the lack of a dataset containing a cargo container, training was performed on the Street View House Numbers dataset. Before training the model, the dataset was analyzed and histograms were built that reflect general information about the dataset. The neural network was trained in the Python programming language using the Tensorflow library. The obtained results of assessing the accuracy of the model operation allowed us to conclude that it is possible to use a data set and a neural network to solve the problem of recognizing the numbers of a freight container.

Keywords: machine learning, digit recognition, cargo container, neural network, image classification

The work is devoted to ensuring the completeness of mixing of gas coolants into a direct-acting heat exchanger by optimizing the geometry of the mixing chamber, in particular the addition of a funnel. Four funnel configurations in the range of 45°-180° are considered. The problem is solved in a stationary formulation by numerical simulation in the OpenFOAM environment. A 14-fold increase in the uniformity of mixing is shown when using a 45° funnel compared to a cylindrical mixing chamber.

Keywords: heat exchanger, mixing heat exchanger, efficiency improvement, outgoing flue gas, numerical modeling, heat recovery

The bimetallic iron-bronze powder material obtained by wedge hot compaction is considered. A hypothesis is formulated, confirmed by the results of experimental studies, about the determining effect of volumetric deformation of the powder material of the iron base in the process of wedge hot compaction. The concept of an indicator is introduced and a 2D Impulse model of the quality of consolidation of heterogeneous powder layers is constructed from the absolute values of the volumetric deformation of the iron base. As a result of the analysis of the constructed 2D Impulse model for the transition zone of a bimetal obtained by technology including sintering, the absolute value of │0.21│ of the critical volumetric deformation was established, which ensures the transition from satisfactory to good quality of consolidation, taking into account the introduced quality scale. For technology that does not involve sintering, the absolute value of │0.171│ of critical volumetric strain, equal to the parameter "c" of the model, characterizes the transition from unsatisfactory to satisfactory quality of consolidation.

Keywords: diversification of management, production diversification, financial and economic purposes of a diversification, technological purposes of ensuring flexibility of production

In this paper, a mathematical model of a wind generator similar to the Darya rotor has been developed. The fast turbine rotation mode or autorotation mode is considered. Using the averaging method, the value of the steady-state angular velocity of the wind turbine in the autorotation mode is obtained. A set of programs has been written in the matlab computer system and numerical counting results have been obtained. They are compared with analytical estimates. A parametric analysis of the geometric dimensions of the wind turbine was carried out to obtain a given power. The advantages and disadvantages of this design in comparison with other types of wind turbines are shown. As a result of these calculations, it can be concluded that Darye wind turbines will be effective only for obtaining small power and at small sizes. Large devices fail too often and their maintenance is too expensive.Large devices require too expensive maintenance.

Keywords: wind turbine, autorotation mode, stability, geometric dimensions

The article is devoted to the issue of increasing the efficiency of ventilation systems through the use of a new type of air ducts. The main advantage of microperforated textile air ducts is the possibility of supplying fresh air with laminar micro jets to the human breathing zone. The need to adapt the existing methods for calculating the main parameters of jets for the laminar regime is noted. The article presents the results on the development of a mathematical model of a stationary boundary layer for the numerical calculation of the movement and heat and mass transfer of air in a laminar microjet. A discrete analog of the generalized differential equation is derived, on the basis of which a software package is developed that allows one to determine the main parameters of laminar microjets. Verification of the developed software package was carried out, the discrepancy with the known engineering method was less than 3%.

Keywords: mathematical modeling, air exchange, microperforated textile air duct, microperforation, laminar jet, control-volume method, round jet, micro jet

This article discusses the solution to the problem of calculating the processes of crystallization of metal drops in the process of blowing the melt with gas in the production of powders. Calculations of the drop formation process and estimates of the phase transition time and until complete cooling are given depending on the particle size in the range of 50-500 µm with preheating of the gas flow to various temperatures from 0 to 500 degrees C. A technique has been developed for calculating the cooling time of a drop of molten metal in a gas flow during the production of metal powder by the sputtering method, and the ratio of the components of the total drop cooling time has been determined.

Keywords: metal powder, melt spraying, particle cooling, gas flows, heat transfer, additive technologies, technological process, gas dynamic process

The main maintenance of a diversification of production as activity of subjects of managing is considered. being shown in purchase of the operating enterprises, the organizations of the new enterprises, redistribution of investments in interests of the organization and development of new production on available floor spaces. The most important organizational economic targets of a diversification of management are presented by innovative activity of the industrial enterprise.

Keywords: mathematical modeling, fiberglass, composite material, system, numerical simulation, finite element method.