Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics最新文献

{"title":"Acoustic Sensor for Assessing the State of Production Equipment","authors":"S. Nekrasov","doi":"10.14529/ctcr210409","DOIUrl":"https://doi.org/10.14529/ctcr210409","url":null,"abstract":"An important trend in the development of industry is the development of digital models of industrial facilities, the work of which is based on information coming from sensors. This allows you to optimize functionality, predict the technical condition of objects, which is especially important, for example, in the field of metallurgical production, where forced stops are accompanied by huge losses. The sensors themselves are also modeling objects, because they need to adapt to rigid production conditions in which their own shortcomings are manifested, while the correct introduction of corrections for environmental conditions, diagnostics and self-diagnostics, which are impossible without building various types of sensor models, is important. The purpose of the work is to deve¬lop a universal discrete model of an acoustic sensor suitable for receiving and emitting acoustic signals. Methods. The work used methods of classical mechanics and mathematics, vibration theory, generalized functions, distributed systems, and mathematical programming methods were used to provide calculations. Results. The main result is a universal discrete model of a sensor with a working element in the form of a round plate, which by choosing parameters can be transformed into a model of a unidirectional dynamic microphone with a flat membrane or a radiator with a focusing spherical element. It is shown that on the basis of the model it is possible to synthesize narrow-directional radiation diagrams and thereby obtain the necessary spatial selectivity and noise immunity of measurements. Conclusion. Calculations made using the proposed model correspond to the known results of acoustics. Verification of the discrete model using a natural sample showed a high accuracy in determining the resonant frequencies and forms of oscillation of the sensor.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134152718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Formalization of Basic Processes and Mathematical Model of the System for Monitoring and Analysis of Publications of Electronic Media","authors":"V. Komarov, S.M. Roschin","doi":"10.14529/ctcr210403","DOIUrl":"https://doi.org/10.14529/ctcr210403","url":null,"abstract":"The article describes an approach to formalizing basic processes and building a mathematical model for a system for collecting and analyzing data from electronic media. The authors, as part of a scientific study, are creating a system, including the development of new algorithms, methods and approaches for collecting and analyzing textual information from Internet news sources. The main direction of the study is the application of methods for the mining of text data based on the technology of artificial neural networks, methods of natural language processing, text mining, machine learning and big data processing. Purpose of the study. To develop a formalized description of the model of the system for monitoring and analyzing the text information of electronic news media using the methods of mathematical modeling. Research methods and tools. The use of the toolkit of the methodology of mathematical modeling, with the methods of system analysis is proposed. To study the system, such methods of system analysis as abstraction, formalization, composition and decomposition, structuring and restructuring, modeling, recognition and identification were used. The system is considered as a formalized model of an automatic classifier and clusterizer for a set of text documents in a natural language in the form of an algebraic system. To solve the problems of classification and clustering of texts, it is proposed to apply machine learning methods based on neural network approaches. The structure of the system and its constituent processes, as well as processes interacting with the system from outside, are presented in the form of a formalized mathematical description. Results. The developed formalized mathematical description of the system model clearly shows the interconnection of the system components with each other, as well as internal processes. The applied approach makes it possible to detail the representation of the system based on its decomposition into subsystems and modules. All this makes it possible to streamline the sequence of stages of creating a system and decompose them into separate stages of work. Conclusion. The results obtained in the course of the study allow us to move on to the next stage of the life cycle of the information system being developed - its software development.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114946455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"To the Question of Determining the Barometric Height by a Mechanical Altimeter and Air Signal System","authors":"V. Panferov, S. Panferov, А.М. Hayutin, N. A. Trenin, K. V. Yatsuk","doi":"10.14529/ctcr210408","DOIUrl":"https://doi.org/10.14529/ctcr210408","url":null,"abstract":"Reliable information on the altitude and speed parameters of the aircraft (AC) is required for safety and increasing the efficiency of flight missions. In this regard, the task of studying the features and improving the characteristics of existing meters for these parameters is quite urgent. Purpose of the study. The features of determining the barometric altitude of an aircraft by a mechanical indicator and an air signal system (SHS) are considered. Materials and methods. The essence of the baro¬metric method for measuring the altitude of the aircraft is analyzed, it is found that to build a clear theory of the method, it is necessary to know the dependence of the temperature of the atmosphere on the altitude. Moreover, it is known that this temperature usually decreases with increasing altitude. However, the rate of decrease unpredictably changes both at different times of the year and day, and at different points and at different heights. Moreover, in some cases, in a certain range of heights, the temperature may not decrease, but, on the contrary, increase. In this regard, there is some problem with the formalization of this dependence. When constructing a theory of the method for mechanical pointers, one proceeds in such a way that the dependence for the International Stan¬dard Atmosphere (ISA) is used, in which temperature and pressure are uniquely related. When developing algorithmic support for SHS, it is considered that the temperature decreases with height as well as in a standard atmosphere, but its actual value at the level of the reference plane can be anything that is not at all related to pressure and altitude in ISA. For this purpose, a temperature control unit is provided in the SHS at the level of the height reference plane. Results. A formula has been obtained that makes it possible to determine the difference between the readings of a mechanical altimeter and SHS. It was found that this difference is a function of pressure and temperature at the level of the plane of the altitude reference plane, as well as the actual pressure at the flight altitude. Numerical studies have been carried out to assess the discrepancy between the readings. It has been established that the relative difference in readings can reach the order of magnitude under ope¬rating conditions, and it practically does not depend on the aircraft altitude and is, in essence, a constant for the indicated initial values of pressure and temperature (at the level of the plane of the altitude reference). Conclusion. The developed algorithms can be used to improve the algorithmic support of the SHS.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126457245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Numerical Method for Processing the Results of Dynamic Measurements","authors":"D. Yaparov, A. Shestakov","doi":"10.14529/ctcr210410","DOIUrl":"https://doi.org/10.14529/ctcr210410","url":null,"abstract":"The problem of processing data obtained during dynamic measurements is one of the central problems in measuring technology. Purpose of the study. The article is devoted to the study of the stability of the method for solving the problem of processing the results of dynamic measurements with respect to the error in the initial data. Therefore, an urgent task is the development of algorithms for processing the results of dynamic measurements. Materials and methods. This article proposes an algorithm for processing the data obtained during dynamic measurements based on the finite-difference approach. The main prerequisites of the mathematical model of the problem of dynamic measurements associated with the processes of restoration of the input signal in conditions of incomplete and noisy initial data are as follows. Initially, the function of the noisy output signal is known. The restoration of the input signal is carried out using the transfer function of the sensor. The transfer function of the sensor is presented in the form of a differential equation. This equation describes the state of a dynamic system in real time. The proposed computational scheme of the method is based on finite-difference analogs of partial derivatives and the Tikhonov regularization method was used to construct a numerical model of the sensor. The problem of stability of the method for solving high-order differential equations is also one of the central problems of data processing in automatic control systems. Based on the approach of the generalized quasi-optimal choice of the regularization parameter in the Lavrent'ev method, the dependence of the regularization parameter, the parameters of the dynamic measuring system, the noise index and the required level of accuracy was found. Results. The main goal of the computational experiment was to construct a numerical solution to the problem under consideration. Standard test functions were considered as input signals. Test signals simulating various physical processes were used as an input signal. The function of the output signal was found using the proposed numerical method, the found function was noisy with an additive noise of 5 %. Conclusion. The input signal was restored from the noisy signal. The deviation of the reconstructed signal from the initial one in all experiments was no more than 0.05, which indicates the stability of this method with respect to noisy data.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131883628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perm Region Natural Resource Potential Forecasting Using Machine Learning Models","authors":"A. Kopoteva, A. A. Maksimov, N. Sirotina","doi":"10.14529/ctcr210411","DOIUrl":"https://doi.org/10.14529/ctcr210411","url":null,"abstract":"In the article we consider a complex indicator of region natural resource potential modeling and forecasting quality improvement using different machine learning models. Problem under consideration importance is determined by the fact that the models traditionally used for these purposes demonstrate either low quality, or high configuration and parameters evaluation difficulty. The aim of the study is determination of machine learning models that provide the optimal values of various modeling quality metrics. Materials and methods. For this study purposes we considered the multiple linear regression, decision tree, random forest, gradient boosting and multilayer perceptron mo¬dels. We used the determination coefficient R2, the root mean square error of modeling RMSE, the average absolute error of modeling MAE, and the relative error of prediction for 1 and 2 time intervals as quality metrics. This study is based on data of the complex indicator of the Perm Region natural resource potential and the system of its determining factors in the time interval from 2001 to 2018. We evaluate models and calculate quality metrics using Pandas and Scikit-learn Python libraries in Jupiter Notebook environment. Results. According to our research the classical multiple linear regression model demonstrates the worst results for all quality metrics under consideration. The decision tree model demonstrates determination coefficient maximum value and minimum root mean square error and mean absolute error. Minimum relative forecasting error for 2017 is provided by the gradient boosting model, for 2018 – by the multilayer perceptron model. Conclusion. Our study allows us to affirm that nonlinear machine learning models for the task of region natural resource potential modeling and forecasting demonstrate better approximating and predictive properties compared to multiple linear regression and thus can be used to improve the quality of natural resource management.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126164714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimum ECG Signal Filtering Based on Wavelet Transformation","authors":"B. Saidov, V. Telezhkin","doi":"10.14529/ctcr210415","DOIUrl":"https://doi.org/10.14529/ctcr210415","url":null,"abstract":"The development of digital signal processing and microprocessor technology creates conditions for improving methods for diagnosing the functional state of organs. Wavelet analysis is a modern and promising method of information processing. In order to determine the effective optimal filtering of the electrocardiography signal based on the wavelet transform, wavelet filtering was performed using wavelets of different families, the efficiency of using different levels of decomposition, me¬thods for calculating the threshold and types of the threshold function was investigated. Aim. Determination of effective optimal filtering of electrocardiography signal based on wavelet transform. Materials and methods. Cardiograms were taken for analysis. Then they were digitized and entered into a computer for processing. A program was written in the Matlab environment that implements continuous and discrete wavelet transform. Results. As a result of the research, 56 combinations of noise reduction parameters were tested for three noise levels. It was found that the maximum degree of signal purification from noise was obtained using the Coiflets 5 wavelet using a rigid thresholding method, with a heuristic method for calculating the threshold value. Wavelet Simlet 8 has lower correlation coefficient values than Coiflets 5, at 35 dB the best result is 97%, the noise level is 40 dB the best result is 98.7%, the noise level is 45 dB the best result is 99.3%, which is generally negligible differs from the correlation coefficients of the wavelet Coiflets 5. Conclusion. As a result of the study, the first and the present work, the following conclusions were made: the optimal level of the wavelet decomposition of the ECG signal N = 2; the maximum degree of signal cleaning from noise was obtained using the Coiflets 5 wavelet using a rigid thresholding method, with a heuristic method for calculating the threshold value; Simlet 8 wavelet using a soft thresholding method with a minimax thresholding method also shows noteworthy results, slightly inferior to Coiflets 5 wavelet results.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131169176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Determination of the Parameters of the La¬mination of a Bimetallic Plate by Means of Active Thermal Non-Destructive Control","authors":"O. Loginovskiy, L.Yu. Kostyleva, A. Maksimov, I. Yachikov","doi":"10.14529/ctcr210404","DOIUrl":"https://doi.org/10.14529/ctcr210404","url":null,"abstract":"Bimetals are in many ways substitutes for scarce metals, while they represent an independent group of materials necessary for the creation of new machines, devices and other various products. The increasing volume of production of bimetals and products made from them requires an increase in their operational characteristics and, accordingly, an increase in the quality of finished products. One of the difficult technological tasks is the connection of aluminum and its alloys with steels of various classes, since there are many problems associated with the quality of the connection of me¬tals with different properties. To improve the reliability and durability of machines and other pro¬ducts made of bimetals, it is necessary to carry out continuous quality control, and the most effective methods are non-destructive testing. Quite promising in terms of simplicity and accessibility is the method of active thermal control, in which the investigated product is subjected to pulsed thermal action by means of a source of thermal loading. The amplitude, shape and time variation of temperature signals serve as informative parameters that allow an operator or an automated system to detect certain defects and evaluate their parameters. With all the availability of pulsed thermal control, the most difficult component is associated with specialized computer programs for processing experimental data and determining the parameters of a delamination defect. The aim of the study is to create a computer model of the thermal state of a bimetallic plate in the presence of an air bubble between the layers and, through computer simulation, to determine the size of defects during active pulse thermal non-destructive testing of steel-aluminum plates. Materials and methods. When performing the work, the methods of mathematical and computer modeling were used. The created software using the development tools of the MATLAB package was based on known methods for obtaining an approximate solution to a boundary value problem on a computer using the finite difference method. Results. A mathematical model has been developed, an algorithm for solving a boundary value problem, and a computer program has been created that allows simulating a pulse thermal control to determine the parameters of a delamination defect in a bimetallic plate. Conclusion. It was found that it is more efficient to measure the temperature difference from the side where the defect is located and the multilayer plate is heated. Heating the plates from the side opposite to the defect and their further cooling showed significantly lower efficiency in terms of obtaining a useful temperature signal. It is shown that in the presence of a defect, the greater the loading heat flux and the defect size, the greater the value of the useful signal determined by the temperature difference on the measured surface.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121834745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Agent Model of Multi-Nomenclature Small Batch Production","authors":"P. A. Russkikh, D. Kapulin","doi":"10.14529/ctcr210406","DOIUrl":"https://doi.org/10.14529/ctcr210406","url":null,"abstract":"Production planning is a key aspect when optimizing production activities. Simulation is one of the most effective methods available for assessing production problems. The principles of adaptive planning consist of making day-to-day operational decisions at the shop floor, predicting equipment availability, assessing performance, and eliminating bottlenecks. Existing research to eliminate bottlenecks has focused on analyzing data from the physical shop, or vice versa, only on the use of simulated data. Convergence between real and simulated data allows, on the one hand, to obtain more information to predict the availability of each workplace, on the other hand, it allows performance assessment for replanning using a simulation model. Aim. Development of optimization tools for production planning using simulation approaches. Materials and methods. This article presents a multi-agent simulation model for each workplace in the workshop, examines the workload of the workshop, and evaluates the productivity of workplaces. Optimization is proposed for optimal utilization of production facilities. As an example illustrating the efficiency and advantage of the proposed model, we took the production process of electronic equipment in the assembly shop. Results. A planning problem and an approach to optimization are formulated. A multi-agent model of multinomenclature small-scale production has been developed. The model provides for the integration of simulation tools with operational planning systems at the data level. Conclusion. The model proposed in the study allows small-scale production to plan the number of jobs and identify bottlenecks in production. The use of a combination of simulation and planning tools ensures enterprise resource management, taking into account dynamic changes in the system.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128139704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Formalism of Writing Out of Manipulators Dynamic Equation","authors":"A. I. Telegin","doi":"10.14529/ctcr210405","DOIUrl":"https://doi.org/10.14529/ctcr210405","url":null,"abstract":"The problem of cumbersome equations of dynamics for manipulation systems of industrial robots (manipulators) with translational and rotational joints is solved. A new formalism for writing out the equations of dynamics of manipulators by using of guide cosines is proposed. Examples of writing out equations of dynamics of manipulators with guid cosines are given. The equations of dynamics in relative angles of rotation of bodies are obtained with the help of these guide cosines by applying their properties. These manipulators have from three to six degrees of freedom. In their equations of dynamics the geometric, kinematic, static and inertial parameters are explicit. The multipliers for accelerations and products of velocities are optimal in the sense of the minimum of arithmetic operations (additions and multiplications) that are needed for their calculations in the written out equations of dynamics. JS-code and method for verification of the equations of dynamics of manipulators written in analytical form are proposed. The problem is that when the equations are written out manually, errors and oversights in the intermediate entries and the final result are possible. Therefore it is necessary to check the results of writing out for absence of errors, i.e. to perform verification of formulas for calculation of constitutive equations of dynamics. To do this, we can use software designed to calculate the generalized driving forces of manipulators, i.e. to solve the first problem of dynamics. Such software is offered as a web-application, in which JS-function is used for verification of the equations of dynamics of manipulators. The method of verification of formulas to calculate the generalized forces of gravity and multipliers (coefficients) for generalized accelerations and products of generalized velocities in the equations of dynamics is developed. An example of verification of the equations of dynamics of the universal manipulator with six degrees of freedom in space is given. Aim. The aim of research is to develop a formalism for writing out the analytical form of the equations of the manipulators’ dynamics in the guide cosines of the principal axes of the coupled body coordinate systems, whose coefficients contain the minimum number of arithmetic operations. Research methods. The methods of research refer to vector and analytic mechanics of absolutely solid systems, to vector algebra, and to systems analysis and programming in scripting languages. Results. The results contain two proved statements, in which there are the formulas and the methodology that allow us to write manually the equations of dynamics of manipulators with three and six degrees of mobility both in guiding cosines and in generalized coordinates. In both cases it is impossible to simplify the obtained equations. Conclusion. The offered analytical types of the equations of dynamics occupy several lines. By the known classical formalisms (Lagrange, Appel, Nielsen, Newton-Eul","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126765003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Possibi¬lities of Using Neural Network Incremental Learning","authors":"E. S. Abramova, A. Orlov, K. Makarov","doi":"10.14529/ctcr210402","DOIUrl":"https://doi.org/10.14529/ctcr210402","url":null,"abstract":"The present time is characterized by unprecedented growth in the volume of information flows. Information processing underlies the solution of many practical problems. The intelligent infor-mation systems applications range is extremely extensive: from managing continuous technological processes in real-time to solving commercial and administrative problems. Intelligent information systems should have such a main property, as the ability to quickly process dynamical incoming da-ta in real-time. Also, intelligent information systems should be extracting knowledge from previously solved problems. Incremental neural network training has become one of the topical issues in ma-chine learning in recent years. Compared to traditional machine learning, incremental learning al-lows assimilating new knowledge that comes in gradually and preserving old knowledge gained from previous tasks. Such training should be useful in intelligent systems where data flows dynamically. Aim. Consider the concepts, problems, and methods of incremental neural network training, as well as assess the possibility of using it in intelligent systems development. Materials and methods. The idea of incremental learning, obtained in the analysis of a person's learning during his life, is consid-ered. The terms used in the literature to describe incremental learning are presented. The obstacles that arise in achieving the goal of incremental learning are described. A description of three scenari-os of incremental learning, among which class-incremental learning is distinguished, is given. An analysis of the methods of incremental learning, grouped into a family of techniques by the solution of the catastrophic forgetting problem, is given. The possibilities offered by incremental learning ver-sus traditional machine learning are presented. Results. The article attempts to assess the current state and the possibility of using incremental neural network learning, to identify differences from traditional machine learning. Conclusion. Incremental learning is useful for future intelligent sys-tems, as it allows to maintain existing knowledge in the process of updating, avoid learning from scratch, and dynamically adjust the model's ability to learn according to new data available.","PeriodicalId":338904,"journal":{"name":"Bulletin of the South Ural State University. Ser. Computer Technologies, Automatic Control & Radioelectronics","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129638401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}