Using numerical simulation, we carried out studies on the effect of the length of a porous heat exchanger on the deposition of dust particles. The heat exchanger models with lengths of 5, 10, 20 and 30 mm were the subject of the studies. At the boundaries of the computational domain, we set the air velocity at 0.1, 1, and 5 m/s and the diameter of dust particles from 10-7 to 10-4 m. Research results have shown that with increasing length of the porous heat exchanger, the efficiency of dust particle deposition increases. This can lead to a decrease in the thermal and hydraulic characteristics of the heat exchanger.

Keywords: porous media, heat exchanger, numerical simulation, calculation, deposition of dust particles, heat exchanger length, air flow velocity, particle diameter, air cooling, microelectronics

This work is devoted to the research and development of an automated control system for the technological process of leading of long sleeves. Long sleeves are an important and promising direction for the development of industrial and metallurgical industries. Now there is a wide variety of designs and sizes of sleeves. However, there are four main methods of their manufacture: mandrel, half-mandrel, without mandrel and on flexible mandrels. The article presents an analysis of the advantages and disadvantages of each of them. Mastering and improving the technology of manufacturing sleeves on flexible mandrels is the main way to increase the volume and speed of sleeve production. The results of mathematical modeling of the automated system are presented. The simulation was performed using the ViSim software tool. The control object is a lead melting bath. The temperature of lead is accepted as an adjustable technological parameter. The method of passive experiment was used to build an automated control system.

Keywords: automated control system, technological process, long sleeve, lead, temperature, mathematical modeling, control object, transfer function, control parameters

TThe modeling of the process of distribution of profile oil pipes in a well by means of a cone punch is considered and the determination of the force necessary for its pushing is carried out on this basis. The normal force for one protrusion of the pipe profile was found. The change in the deformation resistance and profile geometry during distribution is taken into account. The optimal taper angle is determined and the geometric parameters of the punch are selected, including the largest and smallest diameters and its length. A numerical example of calculation based on the obtained formulas is given, which shows the technical feasibility of the process.

Keywords: distribution, oil profile pipes, protrusion force, equilibrium equation, deformation resistance, tool geometry, numerical example

This article discusses the problems of constructing convolutional neural networks for determining road objects. The general relevance and formulation of the problem of determining road objects is presented. The rationale for the use of artificial neural networks for determining road objects has been formed. The Retinanet network architecture is used as the main architecture of an artificial neural network for determining road objects. The general concept of this architecture and the main subnets are visualized. Error functions for the main subnets of the Retina net network are described. The design description of algorithms for constructing data annotation for training an artificial neural network, as well as algorithms for constructing the neural network architecture of classification, regression and feature pyramid is given. The dynamics of changes in the general error function when determining road objects is determined. The result of training an artificial neural network is presented.

Keywords: convolutional neural networks, classification, regression, convolutional neural networks, deep learning, big data, mathematical modeling, computer science, RetinaNet architecture

The lack of water resources determines the problem of their rationing. Existing water consumption standards provide for a wide range of daily consumption values. This does not take into account possible measures to save water, provided for by the concept of buildings with a zero balance of water consumption. In addition, the technical specifications for the design of water supply systems include, for economic reasons, the smallest possible number of residents. The actual occupancy may exceed the planned one by several times, which requires further investment of additional funds already in the reconstruction of the newly built network. The objective of the study is to develop an analytical model of water consumption, the analysis of which allows us to evaluate the dynamics of changes in the specific water consumption with a variable population.

Keywords: specific water consumption, indifference curves, resource replacement rates, marginal water consumption

In this article discusses the problems of determining traffic signs for driving a motor vehicle using an artificial neural network apparatus. The relevance of research at this point in time is described, as well as the advantages of using neural networks in determining traffic signs. The input data for determining traffic signs for convolutional neural networks are presented. The architecture of the convolutional neural classification network is formed, in particular, the sequence of layers of the image classification network is considered. A mathematical description of the modeling of the error function and the stochastic gradient descent method is given. A mathematical model of the learning process of an artificial neural network, as well as activation functions: linear functions and sigmoids is presented. An algorithm for forming an artificial neural network model is proposed. The learning process of this function is visualized on the graph. The result of the training is presented.

Keywords: artificial neural networks, classification, convolutional neural networks, deep learning, big data, mathematical modeling, informatics

This article discusses the importance of timely defect detecting of automated electronic car control systems for prevention of serious failures. Also the first stage of mathematic modeling mechanism is presented, it includes construction models of the dependence of the number of failures by time with various methods of diagnosting the technical condition of the car.

Keywords: diagnosting, modeling, technical service of the car, failure, automated system, electronic control unit, engine

Mathematical modeling and optimization of the process of controlling the sulfate regime when the apatite load changes on the phosphoric acid extractor is considered. It is shown that the preservation of the "sulfuric acid/apatite" ratio with a sharp change in the apatite consumption leads to a violation of the technological regulations for SO3. The algorithm of correction of this ratio in the transition mode is developed, which minimizes the probability of violation of the regulatory indicators. A variant of implementing the optimal apatite load correction procedure using stand-alone scenarios is proposed. The results were confirmed during the simulation.

Keywords: algorithm, mathematical model, stabilization of the sulfate regime, extraction phosphoric acid, change in the load on the extractor, phosphorus yield coefficient from apatite, optimization, autonomous scripts

Blasting operations are often the only way to prepare the material for the recess for laying roads and railways in the rocks. Explosive loosening is also used to extract stone as a building material. Field testing is costly and often dangerous. Therefore, it is necessary to first conduct a series of experiments on the model and find out the conditions for ensuring good quality loosening of rocks. In order for the results of model tests to be transferred to nature, a similarity between model and specimen is required. The approximate similarity is achieved by the equality of the similarity criteria for the model and specimen. The characteristic similarity criteria are obtained by analyzing the physical quantities inherent in a mechanical system using the theory of dimension and similarity. The received criteria are presented in the classical form. These are the criteria of Strouhal, Froude, Cauchy and Newton.

Keywords: explosive loosening, rock material, deceleration interval, similarity criterion, modeling, rock density, model, specimen, expansion height, dimensionality, physical quantity

A mathematical model of the surface of deformation zones as a set of flat cross-section described on the basis of spline functions for profiling pipes in rollers with subsequent calibration is proposed.

Keywords: Mathematical model, deformation zone surface, flat cross-section, spline functions, рipe profiling

Cementation studies focus almost exclusively on the movement of carbon, described through the diffusion equations, often with constant coefficients and without regard to temperature. This approach does not allow, to take into account the further diffusion of carbon into the workpiece in a lower temperature range at the stage preceding quenching. The paper describes the modeling of the diffusion saturation of steel by carbon in the cementation process, taking into account the influence of temperature on the example of a numerical solution of the gear cementation problem using the COMSOL Multiphysics program. It was shown that the finite element mathematical calculation of the process of saturation of austenite with carbon during cementation gives good agreement with experimental data, and finite element analysis methods can be used for multivariate calculation of the carbon content in austenite after diffusion saturation

Keywords: carbon diffusion, carburization, COMSOL Multiphysics, numerical modeling, carbon distribution, carburization, Fick diffusion law, mass transfer, heat transfer, gear, finite element method

The issues of improving the quality of products produced by predicting the resulting geometric characteristics of the shape of the pipes to be profiled and their accuracy are considered. An objective mathematical model was created that adequately describes the real process. The computational experiment was performed using software packages that allow implementing the ANSIS and DEFORM finite element method. The dependencies of the studied shape parameters on the outer diameter of the workpiece are established. The presented dependencies and the proposed guidelines for the conduct of the process are of practical use and are useful to developers and consumers of process equipment for predicting the results of profiling

Keywords: Pipe profiling, deformation, stress, mathematical model, finite element method, accuracy, quality

This article deals with the problem of determining the cost of renting real estate. The idea of minimizing the absolute error function using artificial neural networks is substantiated. Particular attention is paid to the process of determining the input data of the neural network. In particular, the problems of determining such parameters as the improvement of the region and premises. The article clarifies the features of determining the weight coefficients to determine the technical equipment of the room using a genetic algorithm. A model of neural network architecture is proposed. The model of change of weight coefficients is described. As a result, the model was tested on test data, and the model of data correction taking into account price dynamics was described.

Keywords: neural network, data mining, data analysis, real estate rental, regression, genetic algorithm, Informatics, machine learning, cost estimation, modeling, extrapolation

The article considers the device for experimental and laboratory testing of microclimate systems. The device is an experimental setup in which it is possible to study the microclimate parameters of multi-functional and multi-level buildings by modeling various processes and their location in the total volume of buildings. Accordingly, with the help of this test model, the parameters of the movement of contaminated air masses and convective flows are studied.

Keywords: test model, installation, microclimate, multi-functional multi-level buildings, process modeling, air, convective flows

Nowadays the manufacturers offer a variety of mobile road laboratories, which are equipped with systems for measuring the automobile roads' properties and further assessments of their exploitation conditions. The absence of one or several of these systems in the lab equipment leads to the price reduction for consumers; however, it also lowers the effectiveness of the diagnostic process. This article suggests that preliminary research of the effectiveness of the automobile road diagnostic process be conducted using mobile road laboratories in various implementations by the means of an imitation model design. The main indicators of the effectiveness will be time spent on the road section diagnostics as it constitutes the labour costs, the necessary amount of fuel, and the overall funding. This diagnostic process model is implemented using a computer programme. It calculates and assesses the road conditions that may affect the laboratory's speed, number and duration of stops necessary for manual measuring which depends on the proper equipment. The designed model allows to analyze the duration of time spent on road diagnostics. The results allow for advance assessment of the financial expenses, including the cost of labour, together with diagnostic planning of the automobile roads of a given region and its specifics.

Keywords: automobile road diagnostics, model design, road conditions, effectiveness research