The article deals with the problem of inaccurate allocation of the boundaries of ore pieces after an explosion in a quarry in the photo. In this article, the possibility of using neural networks for segmentation of photographs was investigated, and training, testing and comparison of the pre-trained bases of neural networks were carried out. The family of pre-irradiated bases EfficientNet and SEResNet was tested on the FPN neural network. Neural networks were tested on the same number of learning epochs, and competitively on three, five, seven and ten learning epochs. Training for more than ten epochs was impractical, since almost all networks were undergoing retraining. According to the results of the test and comparison, the result was obtained that the FPN neural network on the pre-trained EfficientNetB2 bases after 7 epochs of training has a segmentation quality of 98.93% in three segmentation classes and 55.1% in the "ore pieces" class.

Keywords: segmentation, neural network, pre-trained foundation, EfficientNet, SEResNet

The article contains a detailed analysis of software systems used in information modeling technologies. The comparative characteristics of the advantages and disadvantages of the software of domestic and foreign developers are presented. Two of the most popular on the Russian market — Revit and Renga - are considered in detail. As a result of the analysis carried out taking into account the needs of the construction market, the conclusion is formulated that the use of the Renga program requires significantly less labor to master. It is also important that the cost of this software is significantly lower than that of competitive analogues. The active implementation of such systems in design organizations can significantly speed up design work and avoid mistakes at many stages of the investment and construction process. In organizations that use TIM technologies in their work, all participants will have the opportunity to act according to a single scenario with the interchangeability of employees, which significantly accelerates the receipt of the final product.

Keywords: information modeling technologies, buildings, model, architecture, design, software package, graphics, digitalization, construction object

The article discusses the development of an automated system for controlling the loading of the gali output mill and scrap of the Lebedinsky GOK processing plant JSC based on the measurement of bearing vibration signals. Gali and scrap output mills are a bottleneck of production, a decrease in their productivity threatens to lose the production of two enrichment workshops. The pur-pose of this system is to conduct the technological process of the mill in maximum load modes with no overloads. The automated ball mill control system proposed in the article will increase the mill's productivity, reduce the specific consumption of electricity, and reduce the time of emergency downtime.

Keywords: production of iron ore concentrate, processing plant, ball mill, mill overload protection, automated bearing vibration monitoring system, automated process control system

The object of the study is the method of evaluating the durability of the cutting tool, which evaluates the rationality of the periodicity of changing the cutting tool during turning on the basis of the indicator of vibration. To form a signal for the analysis the registration of vibroacoustic vibrations during the processing of parts by the device for measuring noise and vibration VShV-003-M2 takes place. To check the transfer function used in the methodology the construction of the model of dynamic system of the lathe is made. The construction of autocorrelation function and amplitude-frequency response of the dynamic system is used to estimate the durability according to the oscillation index. A series of tests to estimate tool life under recommended cutting modes are made, and the results are corrected according to the obtained results. Record of files for the analysis was made in a wave-file format. Analysis of the results made it possible to make recommendations for tool change intervals for better control of tool and labor rationing. Knowledge of the durability of cutting tools is necessary for timely replacement of cutting inserts and control of losses in production.

Keywords: vibration index, catastrophic wear, tool, cutter, tool life, condition monitoring, vibration, lathe, sensor

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

The article discusses the development of an automated monitoring system for the lower position of the crusher cone KKD-1500/180-GWP of the processing plant of JSC Lebedinsky GOK based on a contactless inductive position sensor. The purpose of this system is to inform the technological personnel in a timely manner about the irregular lowering of the crusher cone to the lower level, followed by prompt measures to eliminate or repair the crusher hydraulic unit, as well as the constant maintenance of the crushing ore optimal mode with specified quality characteristics in size. The automated monitoring system for the lower position of the crusher cone will reduce the concentrating plant concentrate losses, increase production efficiency by reducing the electricity specific consumption, as well as improve the personnel working conditions.

Keywords: crushing of ferruginous quartzites, enrichment factory, cone crusher, granulometric composition of ore, automated system for monitoring the position of the cone crusher

The advantages, disadvantages and limitations of the use of thread seams in the technological processes of product assembly are considered, the advantages of replacing thread seams with thread-free joints, ways to obtain them in order to control the competitiveness of the technological process of hot-glue assembly, the production processes of obtaining a flat thread-free connecting seam using modern technological equipment are shown, possible ways of its formation are given.

Keywords: method, control, technological process, thread-free connection, adhesive joint, seam, parts, products, thermal tape, adhesion, technological equipment

The article presents a project for an automated public transport stop, which includes the ability to regulate the lighting and temperature of the room, video surveillance, registering the location of vehicles in real time and displaying it on the display, as well as using wireless Internet and recharging the phone by equipping the stop with the necessary devices. The purpose of the article is to increase the level of comfort and safety of each consumer. Security is ensured by installing a panic button for communication with emergency services and a CCTV camera that transmits real-time video to dispatch services when the panic button is pressed. In addition to technologies previously introduced in the Russian Federation and other countries, it is proposed to additionally equip stops with vending machines for food and drinks. The uniqueness of the work lies in the adaptive temperature control system, which allows you to change parameters and operating strategies depending on current data and environmental conditions. The article selects and describes each component of an adaptive automated system from a technical point of view, provides an equipment diagram and notes the possibility of reducing project costs by including renewable energy sources.

Keywords: automation, adaptive control system, equipment, public transport stops, optimization, innovative technologies, renewable energy sources, city infrastructure

The article is devoted to the issues of accounting for various production disturbances that affect the temperature field in the drying chamber. The nature and nature of disturbances affecting the change in chamber temperature are taken into account using statistical methods for processing temperature curves over time. The temperature field in the plane of sensor installation was considered.In practice, the electrical model of the temperature field of the drying chamber can be represented as a three-dimensional grid, and the nature of the temperature field can be judged from the distribution of potentials at the corresponding grid nodes. By changing the grid parameters, it is possible to determine the appropriate temperature regimes for different materials and types of impregnations.

Keywords: temperature, statistical methods, drying chamber, autocorrelation function, spectral density, amplitude-phase characteristic

Prompt adjustment of the composition of the asphalt concrete mixture is key to achieving high quality asphalt concrete. To enable easy and rapid adjustment of the asphalt concrete mixture formulation, predicting the properties of asphalt concrete (Marshall stability) is critically important. There are many methods for predicting the properties of asphalt concrete, but the choice of one method or another is a very pressing problem. This article proposes two methods for forecasting Marshall stability: forecasting using a multiple linear regression model and forecasting using an autoregressive model. To evaluate the forecasting accuracy of models, we use two metrics: average absolute error (MAE) and average absolute percentage error (MAPE). The results of the study show that the autoregressive model exhibits better forecasting results, especially the second-order autoregressive model.

Keywords: asphalt concrete, control, composition adjustment, forecasting, multiple linear regression model, autoregression model, Marshall stability, forecast accuracy, mean absolute error, mean absolute percentage error

The article discusses the method of recognizing contours in the primary image. An algorithm has been developed for finding the absolute minimum of functionality in an image.

Keywords: contour, algorithm, defect, recognition, cut, reference frame, minimum search

This article discusses the problem of ensuring the control of the state and strength of the device for handling radioactive materials at nuclear power facilities and proposes the development of a remote ultrasonic control system for continuous-periodic monitoring of the state of critical structural elements of the service traverse operating in a radiation hazardous environment. The basic principles of processing the results of ultrasonic flaw detection and obtaining characteristics are given.

Keywords: ultrasonic testing, piezoelectric transducer, defect, strength, monitoring

This work is devoted to the development of a control system for the technological process of extruding a polymer coating of pipes. In the process of work, the existing system for regulating the temperature of the polyethylene extruder zones was analyzed, and the scientific and technical literature was analyzed. The description of the technological process of extruding the outer polymer coating of a steel pipe is given, the selection of automation equipment is carried out. The main difference between a proportional controller over a proportional-integral-derivative controller was described, the optimal tuning coefficients of the PID controller were also determined using experimental methods, graphical transients were given, and the most appropriate method for controlling the temperature of the zones of worm machines was selected, due to which increasing the homogeneity and uniformity of the protective polymer layer.

Keywords: pipe polymer coating extrusion, PID controller, polyethylene, adhesive

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

This paper gives an overview of the main safety problems of modern APCSs and formulates the challenges to overcome them. The aim of the work was to review the safety of modern APCSs. Emergencies associated with consistent erroneous actions of operating personnel must prevent control systems. Until the early 2000s, APCSs were considered to be the safest systems, due to their operation according to a rigid and verified algorithm, the human factor could not affect them. To enable remote control and monitoring, an internet connection became necessary. Due to an increase in the number of cyber-attacks on automated process control systems, an unprotected Internet connection had become insecure, and a new opportunity to influence the system from the outside had appeared. The security and reliability of modern process control systems has become even more important.

Keywords: automated process control system, safety, vulnerability

The article is devoted to the development of training systems for training specialists in automation and informatization. The structure and mathematical model of a training system (TS) were developed to control skills in training these specialists (in particular, in the basics of programming). The parameters of the mathematical model are based on the representation of knowledge about the studied objects and processes in the field of development of automated information systems, which allows using TS to automatically generate and evaluate small practical tasks for students. A prototype of TS software in the form of a web application has been developed. In a practical aspect, the use of TS in the educational process in the disciplines in the field of programming will reduce the proportion of labor-intensive work of the teacher in compiling and checking assignments.

Keywords: information technologies in education, training system, control of knowledge and skills, high-level programming languages

This paper describes the results of modeling thermal processes and air flows occurring in a universal power source (UPS) with a digital control system for output parameters under given operating conditions. The UIP is intended for scientific research in the field of electrochemical copper deposition in order to form through and via holes in printed circuit boards, three-dimensional microassemblies, metallization of epoxy resins, and organic materials. The article discusses the features of the development of a universal power source, presents the key results of the design and study of the thermodynamic characteristics of a prototype sample.

Keywords: universal power supply, microcontroller, computer aided design, printed circuit board, efficiency factor, computational fluid dynamics, mechanical computer aided design, electrical computer aided design, design rule checking, finite element method

The paper presents a study of the problems of organizing the process of designing technical means that are involved in the technological process of production by enterprises. Under the technical means it is proposed to understand both software, hardware, and software and hardware solutions. The main problem is identified - the discrepancy between the functionality of technical means and the technological process. In this regard, a study is being made of the processes of linking the technological process of output of enterprises with the processes of designing and developing technical means. From the results of the study, it was determined that the models of the functional of technical means are constructed by developers, and not by actors. Such models are formally presented not as a description of the procedures for performing the functions of a technological process by actors, but as a model of how the functions of future technical means will be used by actors. The necessity is substantiated and a hypothesis is put forward about the possibility of solving the indicated problem.

Keywords: technological process, actor, developer, functions of the technological process, procedures for performing functions, a model for the formation of a need for a technical means, a model for the use of technical means

The article is devoted to the use of renewable energy sources, namely geothermal energy for home heating. Methods of installation, advantages and disadvantages of geothermal heating are investigated. A comparative analysis of the cost of 1 MJ of heat received from various energy sources was carried out, and the efficiency of using heat pumps for heating buildings was proved. It was noted that in connection with the global problem of greenhouse gas emissions, this decision is relevant and paramount for achieving hydrocarbon neutrality. The introduction of geothermal heating methods can be a huge step towards green energy.

Keywords: system, temperature, geothermal heating, heat pump, compressor, evaporator, condenser, carbon footprint, ecology, green energy

The article solves the problem of determining the influence of the use of gas swirlers with various options for combining the direction of the channels on the velocity and temperature of the plasma flow. A comparative analysis of the use of gas swirlers with channels that are directed in one direction and in the opposite direction is carried out. The problem was solved by conducting a computer experiment by the finite element method using the SolidWorks software package. The results of the calculation experiment were verified by conducting a full-scale experiment using an experimental plasma installation, which is used to obtain powder, apply coatings and modify product surfaces, taking into account its design features. Recommendations for the conduct of these processes are proposed. The results are of practical use for developers and consumers of process equipment. In the case of using gas swirlers in which the channels are directed in one direction, the temperature and velocity of the plasma flow are higher than in the case in which the channels are directed in opposite directions. For the coating process, it is recommended to use the option of orienting the channels of gas swirlers in one direction, since the highest values of the velocity and temperature of the plasma flow are achieved, which favorably affect the properties of the applied coatings. For the production process of powders, it is recommended to use the option of orienting the channels of gas swirlers directed in opposite directions, since a lower plasma flow velocity is important for this process, which has a positive effect on reducing the dimensions of the installation and spheroidization of powder particles. For the surface modification process, the results of the study can be used to determine the rational position of the treated surface.

Keywords: mathematical model, plasma flow, temperature, speed, gas swirler, plasma method, powder production, coating, surface modification

The method of automated diagnostics and control of the technical condition of the electric drive of mining machines, which consists in monitoring the current with subsequent spectral analysis of the received signal, is considered. It allows using the ATmega16 microcontroller to determine with sufficient accuracy the current technical state of the electric drive elements. The aim of the work is to prove the possibility and justify the effectiveness of the use of microprocessor technology in the mining industry to automate the diagnosis of machinery units. The adequacy of the developed methodology for determining the identification frequencies is confirmed by experimental data in the low-frequency region of the spectrum. The conclusion of this article is that a comparative analysis of the calculated and experimentally obtained amplitude-frequency characteristics of individual components of the drive motor and elements of the transmission of the executing body of the KP21 tunnelling machine has confirmed their adequacy.

Keywords: electric drive of a tunneling machine, automated diagnostics and control, current monitoring, spectral analysis, increased reliability of tunneling equipment

The purpose of the study was to find methods to reduce the construction time of special purpose structures. The analysis of the factors influencing the terms of construction of nuclear power plants is carried out. Using the example of calculating the parameters of the ventilation pipe installation of a really erected nuclear power plant, the advantages of replacing the traditionally used for the construction of these structures with the method of "falling arrows" are noted.

Keywords: falling boom, set of machines, installation of structures, scope of work, traction mechanisms, continuity of work, cost, construction period, commissioning period, work cycle

The article deals with the imported used in the educational process controllers replacement problem. There was a need to replace imported products with domestic ones due to the withdrawal of leading import manufacturers from the Russian market, so it seems reasonable to exclude imported equipment from the educational programs of universities. The course "Digital Automation and Control Systems" is based on the study of various industrial controllers. The first place among industrial controllers in SUAI is occupied by Siemens products, which officially left the Russian market. The question of searching for similar controllers of domestic production arose, at the same time, the manufacturer should not depend on the supply of imported components. Controller PR200 by OWEN was chosen as such a manufacturer. The article compares PR200 by OWEN with LOGO! by Siemens and comes to the conclusion about the interchangeability of these controllers in the educational process. The peculiarities, advantages and disadvantages of the development environments of both manufacturers are considered in the article. It also tells about the experience of using the stand based on PR200 in the educational process, therefore, the possibility of a complete replacement of LOGO! has been proved.

Keywords: programmable logic controller, programmable relay, functional block diagrams, specialist training, substitution of imported products, development environment

Due to the intensive development of digital technologies, significant progress is be-ing observe in the creation of automated systems and technologies. One of the most pressing problems at the present stage of industrial development is the presence of cases of oil spills caused because of technological accidents and accidents. With advanced achievements in the field of digital technologies, it seems possible to au-tomate the process of identifying oil spills. The main purpose of the current article is to analyze the possibility of using unmanned aerial vehicles to perform automatic identification of oil spills. The author investigates this issue, and presents an option to increase the use of these systems based on the development of a special image-processing algorithm based on exponential accumulation and the variance method. The results of the work confirm the hypothesis of the effective use of unmanned aerial vehicles for automatic identification of oil spills.

Keywords: automation, unmanned aerial vehicle, oil spill, identification, image processing