ISSN 0236-235X (P)
ISSN 2311-2735 (E)

Bookmark

Next issue

4
Publication date:
16 December 2020
-->

Journal articles №3 2020

11. Technical object projection in the image into metric space using deep neural networks for the detection problem [№3 за 2020 год]
Authors: O.V. Tolstel (tolstel.oleg@mail.ru) - Baltic Federal University Immanuel Kant, Institute of Physical and Mathematical Sciences and Infor-mation Technologies (Associate Professor), Ph.D; O.V. Tolstel (shirkin39@mail.ru) - Immanuel Kant Baltic Federal University, Institute of Physical and Mathematical Sciences and Information Technologies (Associate Professor); Kalabin A.L. (alex.ka.86@gmail.com) - Tver State Technical University, Ph.D;
Abstract: The paper presents the image vectorization algorithm containing technical objects. As technical objects are machine-building parts, fasteners, hardware. Vectorization refers to the transformation of an image into a vector for which the Euclidean distance has semantic meaning. This algorithm was created to im-prove the system of assessing the object position, where there is a problem of a variable number of types of objects for recognition. The author proposes an approach to the formation of a metric space for images, where the image transformed into a vector by the metric l2 can be compared with the image by the standard, thereby solving the problem of a non-constant number of classes. To add a new class, it is enough to add a ref-erence image represented as a vector to the system and find the distance to it. If it is smaller than other images, then this reference will represent the type of object that was submitted to the input system. This approach is implemented in deep neural networks, where the last layer is removed and the penultimate layer is left, which represents the upper level of features extracted from the image. Such a neural net-work undergoes a learning process using the Triplet loss function, teaching the neural network to vec-torize the image into metric space. The program implementing the proposed algorithm is developed in Python 3.6 using the Jupyter Lab integrated environment for the Ubuntu 18.04 operating system. The results of the experiment on the use of the proposed algorithm, which consisted in attributing the obtained images to a particular image - standard, are presented. To assess the quality of the algo-rithm, ranking metrics were used for search problems, where only the very first object in the list of nearest objects is evaluated. The developed algorithm can be used for technical vision systems for robotic manipulators, and in the future this algorithm will be used as part of the control system for capturing objects by a robotic manipulator.
Keywords: deep neural networks, metric space, pattern recognition, object capture, robotic arms
Visitors: 958

12. Parallel processing for software system performance optimization [№3 за 2020 год]
Author: I.Yu. Artemov (i_artemov@ak-obs.ru) - Tver State Technical University (Senior Lecturer);
Abstract: The article describes the supposition and working results to improve the operating time of one of the subsystems of the automation system of data harvesting procedure by operators that are out of the of-fice for EPR-system. There is information about the current systems which are dedicated to data har-vesting with mobile devices. The author determines the system weakness which works in the mode of interactive (online) or batch (offline) data exchange between the server part of the system and its mo-bility part, and proposes its remedies for, based on the connection of two ways of exchange data (online and offline). The author devotes the main attention to the mechanism description for generating data necessary and sufficient for the mobile device operation, on the basis of which it was developed software. During the operation of the software, the problems of the proposed scheme were identified, due to the unsatis-factory efficiency of the generated data. The author provides a detailed description of the data pro-cessing options. The author shows their organization’s capability in the instruction pipeline of data processing. The paper gives reasons for the need for work to optimize data processing procedures. The author proposes ways for speeding up existing processing procedures by using the capabilities of modern server systems, which are based on clusters of servers with a large number of CPU cores. The author provides analytical calculations of theoretically possible performance gains when using parallel data processing, as well as the results of testing the developed algorithm based on real data. At the same time, the actual performance increase of the algorithm was 2.38 times, while the theoretically possible 2.51 times.
Keywords: parallel processing, server, mobile terminal, cluster
Visitors: 945

13. Trajectory modeling space object in range Mathcad discovery complexes [№3 за 2020 год]
Authors: T.V. Kalinin (diiimaaarik@mail.ru) - A.F. Mozhaysky Military Space Academy (Professor ), Ph.D; S.V. Kulikov (diiimaaarik@mail.ru) - A.F. Mozhaysky Military Space Academy (Senior Lecturer), Ph.D; D.V. Khrestinin (diiimaaarik@mail.ru) - A.F. Mozhaysky Military Space Academy (Lecturer); A.S. Koznev (diiimaaarik@mail.ru) - A.F. Mozhaysky Military Space Academy (Cadet);
Abstract: In the development of near-Earth space had to face an ever-increasing danger caused by the increase in the number of space debris objects. In view of this, one of the problems of radar and optoelectronic means (NES) for monitoring near-Earth space is the prediction of the trajectory movement of such ob-jects. The paper presents the main provisions of the methodology for modeling the trajectory of a space object in the coverage area of a ground-based radio-technical and optical-electronic complex of space-based monitoring of near-Earth space using the Mathcad medium. The paper substantiates a rather ade-quate and at the same time easily implemented in real time way to obtain trajectory data in modeling the near-Earth space environment. The research object is the trajectory of space debris of artificial origin in the area of the complex of detection of changes in the environment of near-Earth space. The study subject is a model of the trajec-tory of an object of space debris of artificial origin (technogenic) as an integral part of the model of de-tection and tracking by active radio-technical and passive optoelectronic complexes for monitoring near-Earth space. The modeling technique of space object flight in the station coverage area is based on an elliptical theory of motion. The parameters of the coverage area and the technical characteristics of the radio complex are determined by its purpose. In addition to the elliptical theory of motion, the technique of moving an object in a vision of an op-tical-electronic complex takes into account the technical parameters of the complex and the character-istics of its motion in near-Earth orbit. The main result of the study is the proposed modeling techniques that allow, using the limited com-putational and graphic capabilities of a computer mathematics system, it is sufficient to adequately simulate the trajectory of a space object in the coverage area of a ground-based radio complex with specified parameters, as well as generate a vector of trajectory measurements in various coordinate systems, in including passive means of the optoelectronic location. The directions of further improvement of the methods are taking into account disturbing factors act-ing on the space object during its movement, as well as modeling the processes of processing trajectory measurements of maneuvering space objects with various hypotheses about the nature of the accelera-tion of motion.
Keywords: optronic system, trajectory, orbit, coordinate systems, mathcad, radar system, space object, modeling
Visitors: 1008

14. Software for collecting, processing and transmission of technical condition data surface of the electric motor collector [№3 за 2020 год]
Authors: A.L. Zolkin (alzolkin@list.ru) - Povolzhskiy State University of Telecommunications and Informatics (Assistant Professor), Ph.D; V.S. Tormozov (007465@pnu.edu.ru) - Pacific National University (Senior Lecturer); T.N. Bushtruk (btnsam@mail.ru) - Samara State Transport University (Associate Professor), Ph.D; M.V. Petrushova (tyri@yandex.ru) - Samara State University of Economics (Senior Lecturer);
Abstract: The paper explores a complex methodology and presents the results of developing a software product for monitoring the wear of collector plates of electric locomotives in the conditions of repair produc-tion using modern information technologies. The authors offer a software product that allows you to quickly and with a high degree of accuracy to calculate the wear parameters of the collector plates of electric locomotives, depending on their mileage. The low reliability of locomotive electric motors leads to the appearance of failures in the way. At the same time, damage to electric motors leads to the greatest expenditure of time and money for un-scheduled repairs, as well as the greatest downtime of trains on the line. One of the most difficult to manufacture and responsible for the operation of locomotive electric motor units is the collector. Its surface reflects the presence of hidden defects and violations of the operating mode of the electric mo-tor. Thus, the information technologies using in the repair and testing of locomotive electric motors, the electronic database creation, and resource forecasting in order to optimize the terms of trouble-free op-eration are now becoming relevant. When repairing electric motors in locomotive depots, it is proposed to use software that will im-prove control over the quality of this node repair. The introduction of software intended for the collec-tion, processing, and transmission of data on the technical condition of the surface of the electric motor collector in motive-power depots will provide a number of positive, but economically difficult to con-sider factors into the repair industry, including increased discipline and work culture, the need for ac-curate adherence of measurement technology.
Keywords: collector, motive-power unit, electric motor, wearing, software product, parameters measuring, control
Visitors: 958

15. A review of dynamic vehicle routing problems [№3 за 2020 год]
Authors: V.N. Kubil (vksend@gmail.com) - South-Russian State Polytechnical University (Assistant of Software Engineering); Chernyshev Yu.O. (sergeev00765@mail.ru) - Don State Technical University, Ph.D;
Abstract: Vehicle routing problems are strategic point to the optimization of logistics processes and for more than half a century have attracted wide attention of researchers due to their complexity and practical significance. This paper focuses on a relatively new area of research on dynamic vehicle routing prob-lems. The authors give prerequisites for its formation, associated with globalization and the develop-ment of information and communication technologies. A brief history of this sub-class of problems is presented, with references to the works of authors who have contributed significantly to its research. The principal differences between the dynamic ve-hicle routing problems and their static counterparts are shown. As examples of a practical application there are considered sales sphere, emergency rescue and repair service companies, courier services, transport ordering systems, emergency services and taxi services. There is a review of varieties of de-terministic and non-deterministic problems in the paper. Among the main dynamic parameters of the problems, there are considered the requests for export and delivery, the query time, the quantity of demand, the travel time of the vehicle, and others. The main approaches to solving dynamic vehicle routing problems are considered and the most popular methods and algorithms are specified, including tabu search, variable neighborhood search, insertion methods, nearest neighbor search, column generation, genetic algorithms, ant colony optimization and particle swarm optimization. The conclusion is the current trends of research in this area, related to the formulation of complex variants of dynamic vehicle routing problem and the development of effective methods of global opti-mization to solve them.
Keywords: vehicle routing problem, vrp, dynamic, stochastic, combinatorial optimization
Visitors: 914

16. Software for identification and correction of non-standard errors of measuring instruments in the process of induction soldering [№3 за 2020 год]
Authors: A.V. Milov (antnraven@ieee.org) - Reshetnev Siberian State University of Science and Technology, Department of Information and Control Systems (Postgraduate Student); Tynchenko V.S. (vadimond@mail.ru) - Academician M.F. Reshetnev Siberian State Aerospace University (Associate Professor), Ph.D; A.V. Murygin (avm54@mail.ru) - Reshetnev Siberian State University of Science and Technology, Department of Information and Control Systems (Professor, Head of Chair), Ph.D;
Abstract: The paper presents the development of a software module for the identification and correction of non-standard er-rors in the process of induction soldering of spacecraft’s waveguide paths. The paper analyzes the features of the technological process of induction soldering of thin-walled aluminum waveguide paths of spacecraft. Based on this analysis, the authors concluded that it is appropriate to use intelligent methods to identify and correct non-standard errors of measurement tools in the process of induction soldering. The authors also concluded that the chosen method of identifying non-normative errors as a software module for the existing control system for in-duction soldering of spacecraft waveguide paths. The developed module allows us to configure the initial parameters to create and train an artificial neural net-work used to solve the problem of non-standard measurement error correction in the process of induction solder-ing. The module allows us to configure the artificial neural network in terms of activation functions, hidden layers number, artificial neuron number on the layer, and training duration. The resulting neural network model can be uploaded to disk for use in the induction soldering automated control system. The module also implements the functional of generating a control action for the correction of non-standard errors. Using the module allows us to improve the quality of the induction soldering process control by reducing the influence of errors on the course of this process. The software product is an application for the Windows operating system that is compatible with versions of Windows XP/7/8/8.1/10. The application was developed using the Python programming language and the PyQt5 framework. Data from actual technological processes were the basis for checking the effectiveness of the proposed software module The test results showed high efficiency of identification and correction of non-standard errors in the process of induction soldering.
Keywords: artificial neural networks, induction soldering, correction of measurement errors, identification of measurement errors
Visitors: 973

17. Automation of calculation of the tool of final drawing with thinning of whole-drawn cylindrical products [№3 за 2020 год]
Authors: A.I. Sergeev (alexandr_sergeew@mail.ru) - Orenburg State University (Professor), Ph.D; Shegolev A.V. (maxov-1@mail.ru;) - JSC «Mechanical plant» (Director General ); Serdyuk A.I. (sap@mail.osu.ru) - Orenburg State University, Ph.D; M.V. Ivanyuk (spectre_m@list.ru) - Mekhanichesky zavod (Chief Engineer); A.V. Kuzmin (flickerlight@inbox.ru) - Mekhanichesky zavod (Deputy Chief Designer);
Abstract: Modern high-tech press production refers to the high-tech area, which causes a number of features that determine the specifics of the processes of metal flow in the processing of pressure without heating. One of the complex processes is a deep drawing with thinning, which performs the basic forming op-eration of converting a thick-walled cylindrical semi-finished product of the "cup" type with a blind bottom part into a thin-walled one. Errors in the calculations can occur only on the final drawing with thinning, which leads to additional labor costs for re-design, tool manufacturing, and production of a new batch of products. As a result, the cost of the product is significantly increased. Based on the stat-ed automation of calculation of tool geometrical parameters of the final drawing with thinning of the whole-drawn cylindrical products is actual. The paper describes the design problems of the final drawing tool with thinning in the manufacture of whole-drawn cylindrical products. The authors present three main types of whole-drawn cylindrical products with different internal geometry. The paper describes the developed UML diagram of the pro-cess of calculating the final drawing tool with thinning. The features of calculating the punch profile, depending on its geometrical parameters and the type of the axial section, taking into account the spring-back of matrices in the process of manufacturing products, the manufacturing tolerance and wear of the matrix and punch, the tolerance on different-wall, the tolerance on the wall thickness of semi-finished products, the allowance under mechanical processing. The authors give the screen form with the output of the calculation results of the final drawing tool with thinning. The calculation results obtained with high accuracy allow us to minimize the number of errors and they are the input data for the module of automatic construction of three-dimensional mod-els and drawings of punches and matrices in the computer-aided design COMPASS-3D through the use of an application software interface.
Keywords: computer-aided design, matrix, punch, cold deep drawing with thinning, uml activity diagram
Visitors: 874

18. Automated control module for a production process monitoring system [№3 за 2020 год]
Authors: G.M. Solomakha (gsolomakha@yandex.ru) - Tver State University (Professor), Ph.D; S.V. Khizhnyak (stanislav.khizhnyak@gmail.com) - Tver State University;
Abstract: The paper presents the architecture, tools, and technologies used in the implementation of the automat-ed control module of the monitoring system for production processes, which provides the ability to au-tomatically and manually adjust the operating mode of the equipment. The module provides the ability to control geographically distributed production infrastructure remotely manually or automatically. The components of the module, the protocol, and the order of their negotiation, the method, and format of data transfer are oriented to use both in geographically distributed and concentrated industries. The paper substantiates the feasibility of developing the module. The paper describes the require-ments for the module formed during the research, which are necessary to solve the problem set for the module, in particular, the possibility of remote automated and manual control, control from the maxi-mum number of platforms, integration with third-party systems. The paper describes ways to achieve the former requirements. The authors present the main subsystems and components, describe their pur-pose, functions, and principles of operation, give the format and method of data transfer between the module components, as well as the method of storing them. The authors use JSON as the data representation format. WebSocket transmits data. Integrated han-dlers in JavaScript perform data processing. Rhino JavaScript Engine provides the interpretation of these handlers. The module implementation language is Kotlin. The event model is used as a model for data exchange between module components. The authors provide the module architecture diagram and name its components. Based on the results of their research, they draw conclusions. The designed architecture provides a high degree of mobility and allows management in the condi-tions of the geographical distribution of production. When used as part of a production process moni-toring system, it provides a high degree of flexibility and scalability.
Keywords: information system, automated management, information system architecture, system analysis, control module
Visitors: 979

19. The simulation program for thermophysical processes in ore-thermal furnaces when changing the control actions [№3 за 2020 год]
Authors: A.Yu. Puchkov (putchkov63@mail.ru) - Smolensk Branch of the Moscow Power Engineering Institute (Associate Professor), Ph.D; S.V. Panchenko (tan_pan@inbox.ru) - Smolensk Branch of the Moscow Power Engineering Institute (Professor), Ph.D; M.V. Chernovalova (0208margarita@bk.ru ) - National Research University “MPEI” (Postgraduate Student);
Abstract: The authors developed an algorithm and software for modeling the thermophysical processes of the re-actor zone of an ore-thermal furnace in response to changes in control actions. The algorithm is based on two mathematical models that use a hydrodynamic approach to describe the sludge formation in electrothermal processes of the processing of pelleting products of roast machines in ore-thermal fur-naces. The first model describes thermophysical processes and represents the stoichiometry of the re-sponse components and the non-steady states of a phosphoric ore-thermal furnace during the pro-cessing of pelletized industrial waste in the approximation of lumped parameters. The second model describes the sludge formation process and characterizes the particle entrainment. These particles are a source of sludge contaminants of phosphorus at the furnace outlet. The model is based on the fact that the dusting key factor is the melt drip entrainment by bubbling gas. The considered furnaces are used in a multistage process for producing yellow phosphorus from the waste of apatite-nepheline ores, which gather in large quantities in the dumps of mining-and-processing integrated works. Representing industrial deposits of mineral wealth, such dumps need to be recycled, since, in addition to the relatively rich chemical composition, which also needs to be used, they have an appreciable loss to the environment and human health. Therefore, the technological system devel-opment for waste disposal and the software creation that simulates the processes in such systems with the aim of their comprehensive optimization is a relevant research problem. The software for modeling the thermophysical processes of the reactor zone of the ore reduction furnace will be further used as an integral part of the software complex, whose problem is to calculate the optimal (energy-efficient) modes of the technological system, including granulators, conveyor-type calciners, and ore-thermal furnaces in order to ensure environmentally friendly processing apatite-nepheline ore waste.
Keywords: modeling of thermophysical processes, optimization of energy consumption, waste disposal of apatite-nepheline ores
Visitors: 920

20. Development of a problem-oriented system for managing the process parameters of an underground well uranium leaching mine [№3 за 2020 год]
Author: D.R. Podrezov (dpodrezov81@rambler.ru) - National University of Scince Research Technological "MISIS" (Applicant);
Abstract: The management information system is designed to make timely, effective, and well-grounded man-agement decisions in the field of operational and tactical production planning. The problem-oriented management system is based on the productive-economic model of the operation of an enterprise. The main model function is to calculate the production and economic indicators of the enterprise's func-tioning under a given amount of resource expenditure during the implementation of the production program under various scenarios of the development of environmental factors. The prime purpose of the system is to model the enterprise activity and search for a set of economic, production, and techno-logical indicators to achieve production program goals. The purpose of the work is to create a problem-oriented system for managing indicators of techno-logical processes of an underground well leaching mine for implementing information and analytical support of procedures and processes that allow to quickly analyze, model, predict and visualize vari-ous scenarios for the implementation of business processes and the production program of the enter-prise. The study is novel in that it is possible to implement a procedure for modeling performance indica-tors and evaluating reserves of technological blocks of an underground borehole uranium leaching mine in order to determine the resource potential of the Deposit as a whole, based on the analysis of the dynamics of basic technical and economic indicators and scenario conditions for the development of business processes of the enterprise. The system use will make it possible to create targets for the enterprise operation with different planning horizons. For the purposes of operational and tactical production planning, a budget is calcu-lated for material resources, and a portfolio of projects for the production program and consolidation reporting forms are formed according to external environmental development scenarios. The developed procedures make it possible to implement the production planning directly functions on mine individual technological blocks and to form optimal production programs for the technological polygon development as a whole on the basis of the opened reserves obtained model versions and the formed conditions and restrictions system.
Keywords: problem-oriented management system, the hierarchical distributed system, optimum production program, technical and economic indicators modeling, the opened stocks modeling
Visitors: 876

← Preview | 1 | 2 | 3 | Next →