System technologies 2022-05-27T17:15:02+03:00 Селівьорстова Тетяна Віталіївна Open Journal Systems <p>&nbsp;<span style="font-size: small;"><a title="System technologies" href=""><img src="/public/site/images/editor_journals/logo_new_black_font4.png"></a></span></p> <p style="margin-top: 0.00in; margin-bottom: 0.00in; font-weight: normal; line-height: 100%;" align="justify"><span style="font-size: small;"><strong>The journal</strong></span></p> <p style="margin-top: 0.00in; margin-bottom: 0.00in; font-weight: normal; line-height: 100%;" align="justify"><span style="font-size: small;">Regional interuniversity compendium of scientific works "System technologies" was established in January 1997, is published 6 times per year. </span><span style="font-size: small;"><span style="font-weight: normal;"><span class="tlid-translation translation" lang="en"><span class="" title="">According to the order of the Ministry of Education and Science of Ukraine No. 1643 dated December 28, 2019, the regional intercollegiate collection of scientific works "System Technologies" is included in the List of scientific professional publications of Ukraine, category "Б".</span></span></span></span></p> <p style="margin-top: 0.00in; margin-bottom: 0.00in; font-weight: normal; line-height: 100%;" align="justify"><span style="font-size: small;"><span style="font-weight: normal;"><span class="tlid-translation translation" lang="en"><span class="" title="">Knowledge area is technical sciences.</span></span></span></span></p> INVESTIGATION OF THE PARAMETERS INFLUENCE OF A CYLINDRICAL INDUCTOR WITH TWO-LAYER INWALL ON ITS TEMPERATURE 2022-05-17T16:05:59+03:00 К.L. Dukhnevich О.V. Кravets O.V. Spirintseva <p>The thermal state of a cylindrical inductor with a two-layer inwall was investigated: the inwall temperature of the inductor for 12 pairs of heat-insulating materials of the inwall layers was calculated, and the influence of changes in the thicknesses of inner and outer inwall layers for fireclay-asbestos pair on the inwall temperature.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Concept of digital voting based on the Blockchain technology 2022-05-27T16:15:55+03:00 O. Volkovskyi M. Pachevskyi E. Obydennyj <p>Democratic voting is one of the most popular methods of resolving socially important issues in developed countries. The most common method of voting is the paper system. This method has certain disadvantages, including technical (falsifications, calculation errors, lack of transparency), social and economic (high cost to the budget). Electronic voting systems have not become widespread due to security issues, verification of results or incorrect operation of software [1, 2]. Blockchain technology offers new opportunities to develop completely different types of digital services due to the key features of this technology, such as transparency and security of the data transfer process. Developers have the opportunity to bring the voting system to a new information technology level that meets modern requirements. The use of smart contracts in combination with blockchain technology will help solve most of the existing problems of modern voting systems Blockchain technology is based on a transactional model. The principle of operation of blockchain technology is shown in Pic. 1. Each user has his "wallet" with unique public / private keys, which confirm any action of the user. Transactions (agreement, shipment), which are carried out by all users of the system, are stored in successive blocks. Since the hash of the data of the previous block is used when generating the next, the consistency of the data within the blockchain is ensured.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Segmentation of aerospace images using convolutional neural networks 2022-05-27T16:17:59+03:00 V. Hnatushenko I. Gnennyi I. Udovyk O. Shevtsova <p>To solve practical problems, including for the management of territories, monitoring of emergencies, for the development of the ecology of our planet, for the study and ecological research of our planet, effective algorithms for the segmentation of multispectral images are needed. In recent years, image segmentation using convolutional neural networks has become very popular. A significant difference of this approach is the annotation of the assignment of each pixel to a particular class of objects, so that the learning process of such networks is completely controlled. The paper proposes a new method for segmentation of aerospace im-ages of high spatial resolution based on convolutional neural networks and mask generation. Our model is based on a combined U-Net network with MobileNetV2 as the backbone. It trains on ground data and provides a full prediction mask. A network has been implemented, consisting of separate networks of the same class, working on the expansion of segmentation. Semantic features are used to reduce errors at the semantic level of the outline. Since an in-dependent test revealed some shortcomings in certain classes of the earth's surface, further re-search will be devoted to the creation of a catalog of training samples to support successful differentiation of objects. In general, the obtained accuracy estimates demonstrate the modern characteristics of the developed model, as well as the effectiveness of this combination of network and datasets for test regions. The results show that the proposed algorithm can effec-tively improve the overall accuracy of the semantic segmentation of high spatial resolution remote sensing images and reduce the training time and segmentation time.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Mobile face detection algorithm inference traits 2022-05-27T16:20:38+03:00 K. Khabarlak <p>An ever-growing number of applications uses mobile face detection. However, most of the modern research papers focus on increasing detection quality while paying no attention to detection time. This means that many of the state-of-the-art algorithms are inapplicable on mo-bile due to excessively large detection time. The goal of this this paper is to adapt 5 of the face detection algorithms for inference on mobile devices and analyze their performance characteristics. These algorithms include es-tablished methods: Haar Cascades, LBP, HOG, as well as, novel neural-network-based algo-rithms: MTCNN, BlazeFace. The main research material. We conduct the experiments on three scenes typical for mobile face recognition systems: when there are no faces, 1 or 2 faces. For testing we have im-plemented an Android application. 2 widespread processors, namely Snapdragon 800 and 845, were selected for time measurements. Having tested the algorithms, we note that all them can run at real-time speeds for images of size 128x128 and only 2 of them (LBP, HOG) on 256x256 on the faster Snapdragon 845. On the slower Snapdragon 800 only BlazeFace, LBP, HOG can run at resolutions not higher than 128x128. We suggest not using Haar or LBP cascades in practice as their accuracy is quite low. Conclusions. Based on the research conducted, we suggest that for the practical use-cases the best algorithms are: 1) BlazeFace, which has stable and accurate predictions, how-ever, the method accepts only two image resolutions as input, in addition, higher inference time for empty images than for images with faces is untypical; 2) MTCNN, thanks to the cascaded architecture, conserves the resources when input frames have no faces. This algorithm is also the most adaptive and can run at resolutions as low as 32x32 given that the faces are quite large; 3) in case if inference time is of the most importance, we suggest using HOG-based algorithm. In this paper we have also shown that cascaded algorithm architecture dynamically changes execution time depending on image content and its complexity, which follows how we, humans, think. We hope that the novel practical results obtained, will increase the use of the above-described methods in mobile applications and will boost the development of the algorithm modifications.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Formation of a set of informative features when deciding problems of predicting the durability of structures 2022-05-27T16:22:04+03:00 L.I. Korotka <p>The paper proposes a method for extracting informative features for the training sample in the problems of predicting the durability of corroding structures. The work aims to analyze and evaluate the informative features that improve the quality of the data and to structure them. Kendall`s method is used to determine the value of each trait. It is proposed to use the training sample to work with a neural network or to build a fuzzy knowledge base only after the formation of a set of information attributes on their value.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Search engines for video 2022-05-27T16:23:58+03:00 O.O. Linevych T.А. Likhouzova <p>The thermal state of a cylindrical inductor with a two-layer inwall was investigated: the inwall temperature of the inductor for 12 pairs of heat-insulating materials of the inwall layers was calculated, and the influence of changes in the thicknesses of inner and outer inwall layers for fireclay-asbestos pair on the inwall temperature.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 The structure and algorithm of the intelligent decision support system for the identification of cultural values 2022-05-27T16:30:10+03:00 A. Martynenko <p>The article discusses the algorithm of the work of an intelligent decision support system for identifying cultural values and the user with it, the issues of determining the main scenarios of work and restrictions. The author provides the expediency of dividing the software implementation of the system into separate modules, which will make the process of scaling the system less labor-intensive and more efficient. A set of tools for solving the problem is presented, where a decision is made as such. Moreover, for the identification and analysis of different types of cultural property objects, different types of neural networks can be provided. It also notes the complexity and complexity of the approach to solving the problem, certain prospects and ways of further research of this subject area. The use of the system specified in the article, built on the basis of neural networks and modern software and hardware, will allow the user, in conditions of uncertainty and in conditions of limited time, to receive additional help in making decisions in identification and CC, the use of a system of this type is relevant and promising. The approach proposed by the author to the creation of this system is convenient and effective, has a powerful potential for further development and improvement of the system. The combination of databases and knowledge in one system, together with a powerful mathematical and analytical apparatus, will allow reaching a higher level of identification and analysis of objects of cultural property in comparison with conventional databases and catalogs. The conclusions set tasks for solving organizational, legal and technical issues related to the implementation and operation of the system.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Mathematical model of force and deformation interaction of strip and rolls during rolling with intense plastic deformation 2022-05-27T16:33:09+03:00 D. Bohdan V. Balakin M. Shtoda Yu. Nykolayenko <p>The operating conditions of oil and gas pipes determine strict requirements for their structure and properties, in particular, corrosion resistance. It is known that the mechanical properties and corrosion resistance of steels significantly depend on the degree of grinding of the grain and the homogeneity of the structure. One of the ways to form a fine-grained structure, increase mechanical and corrosion properties is intense plastic deformation. In order to determine the effect of intense plastic deformation on the deformation treatment of steel strips, a scheme of a simple rolling process with a blank roller was developed. The possible influence of intense plastic deformation in such a scheme on the structure of the metal required the development of a mathematical model, the purpose of which is to determine the magnitude of the true plastic deformation. Based on the results of mathematical modeling, laboratory experiment in rolling strips and determining their corrosion resistance in the proposed scheme, it is envisaged to develop an industrial installation for processing the inner surface of pipes. The mathematical model of the proposed rolling scheme with a certain value of intense plastic deformation is expected to be described in four stages. The first is to determine the force of pressing the idler roller into the material at a fixed amount of force applied to the lever of the mechanism. The second is to determine the magnitude of the pressure force of the idler roller on the rolled strip and the working roll. The third is to determine the depth of indentation of the roller in the strip at a given load in the absence of rotation of the rolls. Fourth - determining the actual and equivalent degree of deformation of the strip by a blank roller. Conclusion. Comparison of equivalent deformation roller and deformation rollers with a diameter of 180 mm with compression =0,2 мм; =1,15; =0,139 shows an order of magnitude greater deformation of the roller. The mathematical model of the offered way of rolling with intensive plastic deformation is developed, the carried-out calculations give the chance to assume considerable changes of structure of material, reduction of the sizes of grains. The latter should certainly be reflected in the change of physical and mechanical properties of the material, namely the increase of its corrosion resistance and the level of mechanical properties.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Decision support system for the use of metal in multi-stage rolling production 2022-05-27T16:35:09+03:00 T. Zheldak L. Koriashkina D. Haranzha D. Serdiuk <p>The presented system is based on the implementation of a mathematical model of the problem of optimal metal consumption in a two-stage process of its distribution in the produc-tion of rolled products, namely: at the stage of casting steel from a ladle during converter production and during the formation of blanks in machines with continuous casting. The cri-terion of optimality is the minimum loss of metal. This takes into account the type of products produced and possible options for cutting in two rolling stages. The mathematical model is a problem of partial-integer linear programming. For its solving, we use the method of branches and boundaries. An important part of the DSS is the preprocessing of a large order containing various types of products and providing for the execution of several heats. The proposed heuristic algorithm for dividing a large order into parts that can be performed within only one heat with as complete filling of the ladle as possible. Moreover, the received order, measured in tons, is converted into that measured in the bars of the finished product. The presented results of computational experiments confirm the correctness of the mathematical model of the problem of optimal metal distribution when fulfilling the plan for the production of rolled products. The presented calculations also show the possibility of using the developed system at metallurgical enterprises in the production of rolled products to ensure the minimum number of changeovers of the equipment of cutting machines and the rational use of metal.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Models of monitoring of self-like traffic of information and communication networks for attack detection systems 2022-05-27T16:37:11+03:00 V. Korniienko O. Gerasina D. Tymofieiev O. Safarov Y. Kovalova <p>Autoregressive, fractal and multifractal models of network self-similar traffic are con-sidered, which allow to form an adequate reference model (template) of "normal" traffic and to detect traffic anomalies in attack detection and prevention systems. Models of fractal Brownian motion and fractal Gaussian noise were considered as models of fractal motions, because they have self-similarity and long-term dependence properties that correspond to the properties of experimental data, as well as the possibility of their analytical interpretation. When evaluating and identifying processes for the implementation of autoregressive models use adaptive filters-approximators, among which there are neural network and neuro-wavelet. The following were used as multifractal models: a multifractal wavelet model with a beta distribution and a hybrid multifractal wavelet model in which the beta distribution is used on a coarse scale and the dis-tribution of point masses on an accurate scale By modeling as a result of adaptation and learning of models, autocorrelation functions, spectra and variances of model signals qualitatively correspond to the graphs of the experimental signal. In addition, the qualitative and numerical values of the characteristics of the model signals generally correspond to the characteristics of the experimental signal. In this case, beta multifractal wavelet models have a smaller error of determination of characteristics than hybrid multifractal wavelet models, and the relative root mean square error of approximation of the experimental signal using a neural network adaptive filter approximator does not exceed 0.046. Statistical verification by non-parametric criterion of signs allowed to establish the adequacy of experimental and model signals with a significance level of 0.01. Further research should be aimed at developing and using predictive models of self-similar traffic in attack detection and prevention systems, which will increase the efficiency of attack detection.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Automation of solving problems of optimization of parameters of metrological maintenance system of measuring equipment 2022-05-27T16:39:07+03:00 V. Ignatkin S. Alekseyenko M. Gorbiychuk <p>Automation of the metrological service of the enterprise allows to reduce the use of labor to perform tasks of maintenance of measuring equipment and reduce staff errors. At the same time, the process of creating appropriate automated systems requires solving a number of problems related to the need to optimize the parameters of the designed system to ensure its highest efficiency. This article attempts to solve the problem of covering various models in the synthesis and study of simulation computer models that actively use the database of measuring instruments of enterprises. Developed and software implemented a model that allows interactive mode, taking into account the characteristics coming from the calibration laboratories of the service, and given economic and metrological criteria, to determine the values of optimal calibration and repair intervals, the optimal number of inspections in the repair interval and other parameters. The dependence of FTA reliability indicators on the quality of metrological maintenance and repair was investigated by simulation. The influence of inter - repair and inter - calibration intervals on economic efficiency of metrological service is investigated. As a result, the dependences are obtained, which also allow to investigate the influence of service quality parameters on complex reliability indicators. The use of research results allows in the dialog mode of the automated workplace of the metrologist to solve problems of optimization of parameters of metrological service on eco-nomic criteria and restrictions of concrete production on indicators of metrological reliability of measuring instruments, to carry out diagnostics and to forecast metrological reliability of measuring instruments. measurement accuracy and reduce the likelihood of hidden failures.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Program source codes conversion system 2022-05-27T16:40:44+03:00 I. Sokol O. Volkovskyi <p>The growing volume of technologies, the end of actively used development tools support, outdated API etc., entails the need of program codes conversion. In IT companies and not only, often begged the question of deprecated software support, which customers continue to use, or translation of current software to actual technologies. It is more rational for programmers to use the conversion and save most of code base, than rewriting all software by hand, even if manual adjustment is needed. At this moment, there are few high-quality code conversion systems. Largely, conversion systems work well only with similar programming languages. The task of program codes conversion is a deep and complex topic. Programmers are trying to improve translation technologies and facing with many challenges. This article discusses the basic principles of building a system for program codes conversion and some features of its practical implementation.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 On one approach to the development of a simulator of the movement of an autonomous vehicle with training 2022-05-27T16:50:42+03:00 V. Zaytsev Ye. Bulatetskyi <p>The article deals with the use of simulators for controlling the movement of an autono-mous vehicle and development of a new simulator. The approach to creating a simulator of motion of a vehicle in the C# programming language is described. In the development for the implementation of simulation scenes used Unity 3D multi-platform tool is used in the devel-opment. The simulation uses direct propagation neural network that does not have a clear number of input level neurons, having only a constant output level, consisting of two neurons: the first one is responsible for acceleration, the second one is responsible for the ability of the car to turn left or to the right. Also, there is no clearly defined number of hidden levels and neurons located there. All this data in the simulation can be determined by the user. The input to the neural network values received from lasers. The lasers measure the distances to obstacles and feed the values to the input of the neural network. A sigmoidal activation function is implemented. To train the neural network an augmented learning algorithm is used, namely, a genetic algorithm applied to each vehicle, starting with the creation of each vehicle's own list of genes. In the network of each vehicle the number of genes is equal to the number of weights. For the first generation, the weights are set randomly. For the simulation, a generalized neural network with a large number of settings, with it is possible to change its structure: it is possible to change the number input level neurons that depend on the number of lasers at vehicle, their range, the height at which they detect interference, field of their visibility; you can change the number of hidden levels and the number of neurons that will be located there; control the mutation process used in the genetic algorithm; define the value of the mutation and the range of variation at which values can be varied; turn on and off the self-preservation, change vehicle speed, acceleration, set the maximum and minimum speed, edit the parameters responsible for the rotation of the car and its smoothness. Implementation of the project is provided on GitHub. The simulator can be downloaded by any developer from GitHub and can be used to implement and test various neural network training algorithms, including work of your own design.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Web-system for modeling surfaces based on Catmull-Rom patches 2022-05-27T16:59:21+03:00 A. Demchyshyn Y. Burienkov <p>Today, surfaces play an important role in the work of designers, scientists, artists, sur-geons and other professionals involved in creating innovative products. Development of uten-sils, furniture, automobile chassis, phones, clothes, buildings, even human bodies involves geometrical modeling of surfaces. NURBS modeling is the technology of non-uniform rational B-splines creating smooth forms and models that have no sharp edges. The characteristic makes NURBS as the analytical model of choice in Autodesk 3ds Max, Blender, Autodesk Ma-ya, ZBrush, and other modeling systems. A generalizing characteristic of the given software systems is the use of a monolithic architectural style of software development, which is typical for desktop applications. Desktop software systems require installation on a local computer, which in turn binds the user to a specific operating system. NURBS accurately describe conical surfaces. Although each control has its own weight, and each weight has a local effect on the surface, a change in the weight of one vertex leads to a change in the entire surface. One of the main requirements for 3D object modeling software is the ability to change the shape of the surface freely as it passes through all control points. An algorithmic model of the Hermit surface construction under the Catmull-Rom condition and nonzero surface torsion vectors is obtained. It is shown that the Catmull-Rom condition makes it possible to glue individual patches with first-order smoothness, which is a guarantee of ergonomic surfaces. It is shown that a single control point has a local effect on the surface, namely on the 12 sur-rounding patches. The development of a software system for modeling the surfaces of objects with the client part in the form of a web application, which is based on the architectural style of SPA, showed that the user experience of such an application is close to the experience of using a desktop program. At the same time, the SPA application does not require installation and successfully runs on both stationary and mobile devices.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 The design and research of a system for monitoring the movements of goods and resources using blockchain 2022-05-27T17:05:47+03:00 Vik. Hnatushenko R. Sytnyk <p>Recent research and publications. A blockchain is a distributed data structure that is replicated and distributed among network members. The first blockchain specification was proposed together with the digital currency Bitcoin in 2008 by a man under the pseudonym Satoshi Nakamoto to solve the problem of centralizing finances around banks. Today, block-chains are used mainly in the field of decentralized finance (DeFi) in the form of cryptocur-rencies and instruments to them. There are also a few specialized foreign studies on the use of blockchain in the monitoring of supplies, but these studies are more focused on the economic and logistical feasibility of using the blockchain in supply chains, without the exact models of information systems on which such a system should work. The aim of the study. Study of blockchain technology in information systems for moni-toring the movement of goods and resources, which can improve the processes of tracking and automation in supply chains. Main material of the study. The paper develops a prototype of the information system for monitoring the movements of goods in supply chains, which is working above the Ethereum virtual machine. The system is working using two smart-contracts and the paper describes the exact structure and specification of smart-contracts and principles of communication between them for the information system for monitoring the movements of goods. Conclusions. The article presents a prototype of an information system using blockchain technology and smart contracts which are working on the Ethereum network. Based on prototyping of the information system for monitoring the movements of goods, it was concluded that the transparency of the tracking and automation process in supply chains is improved. This work is useful for designing and creating more detailed and sophisticated systems for monitoring and managing the movement of goods and other supplies based on the use of Blockchain technology.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Modeling strategic priorities for thermal modernization of industrial buildings 2022-05-27T17:10:24+03:00 O. Nazarenko I. Nazarenko O. Ishchenko T. Besarab M. Kulik <p>The technology for generating positive ideas is based on human experience, the need to improve the technological process or reduce the operating costs of production and the basic amount of industrial waste. The work examines the audit of industrial buildings and an over-view of advanced technologies for the production of building materials from waste. Current measurements of energy consumption, exceeding the limits and increasing the cost of re-sources require the formation of scientific and technological accents for the development of mixture combinations in the formation of building materials. In the course of the experiments, the thermal properties of polystyrene, ecowool, expanded polystyrene, mineral wool, expanded clay, ecowool with expanded clay were studied. Experiences show that standard insulation technologies do not work productively in the case of industrial buildings with minimal funding. An integrated technology for obtaining a by-product from secondary resources is needed. Waste audit at the enterprise showed the possibility of using primary building materials for the generation of by-products. The available equipment with minimal modifications makes it possible to obtain a new product during the endothermic process of expanded clay swelling. The pressing of cotton wool with a lightweight expanded clay structure allows obtaining sheet materials of the required density up to 1 by 1 m in size. The flexibility of the obtained material allows it to be cut with a cutting tool to the required volume. The possibility of obtaining materials of different densities is convenient for use in any enterprise, when issuing recommendations for increasing the thermal resistance of the shell. The conducted studies of the thermal resistance of the obtained material show the convenience of manufacturing a product to comply with the sanitary conditions of an industrial enterprise. The experiments were carried out according to standard methods. The need to transfer buildings of industrial enterprises to an energy-saving heating mode is caused by the need to reduce the operating costs of enterprises.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022 Features of metal structures digital images containing carbides investigation 2022-05-27T17:15:02+03:00 A. Zakharov T. Selivyorstova V. Selivyorstov V. Balakin L. Kamkina <p>The analysis of microsections requires the involvement of highly qualified experts in the field of materials science, which, in turn, does not exclude the influence of the "human factor". On the other hand, the issues of increasing the objectivity of identifying the properties of metals and alloys require the use of modern data processing methods, for example, artificial intelligence in solving problems of classification and identification of macro and micro structures.The paper presents an overview of studying macro and micro structures containing carbides process, determining the specific features inherent in these images, and proposing an information model for their processing. The article is devoted to the development of an information model intended for the analysis of metal structures digital images with carbide inclusions. The analysis of literary sources is carried out, it is established that the study of metal structures is an important tool for assessing qualitative characteristics. The presence of carbides in the metal structure has a significant impact on its quality. A review of the methodology for studying the structure of a metal is given, and the importance of metal structures image processing stage is determined. The main methods for obtaining digital images of the alloy structure are described. Samples of metal structures with carbides are presented. A procedure for digital processing of metal structures images with kibide inclusions is proposed, which consists of image conversion to grayscale, contrasting, and threshold binarization. An analysis of the results of metal structures processing images made it possible to identify areas with carbide inclusions, however, additional artifacts that were not carbides were found in some images. Balancing by the binarization threshold in this case does not improve the detection of carbide inclusions network due to the lack of contrast. Histograms demonstrate the presence of information features in a wide range of gray colors, so for this class of images, more sophisticated image processing technologies need to be developed. In the course of digital images features study of metals and alloys metal structures containing carbides, it was: an information model for processing metal structures containing carbide inclusions is proposed; the proposed information model is applied to digital images of metal structures; it was found that some images of metal structures are characterized by low contrast, which leads to the selection of background artifacts, except for areas with carbide inclusions; the development of complex mathematical methods for the detection of carbide inclusions in images of metal structures characterized by low contrast is proposed. Thus, the article shows the results of carbide inclusions of the using the digital image processing procedure. The advantages and disadvantages of the approach are shown, the directions for its improvement are determined.</p> 2021-12-10T00:00:00+02:00 Copyright (c) 2022