The article considers the method of approximate determination, analysis and synthesis of the roots of real algebraic equations of high order. The solution of such problems is relevant in the case of designing information-measuring and control systems, studying the dynamics of movement of various mechanisms (industrial robots, quadrocopters, etc.), determining the trajectories of aircraft, etc.

The analytical solution of such problems is limited to equations of the third (sometimes fourth) degree, in other cases it is necessary to use either special sequential algorithms or packages of applied computer programs such as "Wolfram.Matematica", which allow only to find the roots of the equations, but not to synthesize them.

The proposed method is based on the application for the decomposition of the studied polyomial (corresponding to the equation) into the simplest multipliers corresponding to aperiodic and/or oscillatory links, asymptotic logarithmic amplitude and phase-frequency characteristics. The form and values of the roots of the equation are proposed to be judged by the slopes at the fracture points of the logarithmic amplitude and phase-frequency characteristics of the polyparticle under study. The construction of logarithmic amplitude and phase-frequency characteristics is carried out by discarding the "small" terms of the polygamy at separate frequency intervals.

A feature of the method is the possibility of its use both in conjunction with the computer and without it. Manual use of the method assumes that the user has a calculator and a ruler. The method allows to determine not only the roots of real algebraic equations (both real and complex), but also to establish a visual relationship between the coefficients for the terms of the equations with the type and values of the roots and purposefully change the necessary coefficients to change the parameters and type of roots.

The possibilities of the method are not limited to solving real algebraic equations with positive coefficients and integer powers, it shows quite satisfactory results for equations with mixed coefficients and fractional powers.

The method is quite simple, clear, has a small error in the case of far spaced roots, but in the case of closely spaced roots, its error increases, although it remains quite acceptable.

The article presents the substantiation of the method, shows numerous examples of its capabilities, compares the results obtained with the results obtained with the help of the package of applied computer programs "Wolfram.Matematica".

Keywords: algebraic equations, logarithmic amplitude- and phase-frequency characteristics, roots of the equation, vector, addition of vectors, phase shift, circular frequency, module, complex number, imaginary and real part, error, polyomial, polyparticle degree, non-minimal and minimal-phase links, error, Fourier transform.

Vladimir V. Sleptsov (Moscow, Russian Federation) – Dr. Habil. In Engineering, Professor, Departments of Instruments and Information-Measuring Systems, MIREA – Russian Technological University (78, Vernadskogo ave., Moscow, 119454, e-mail: vsleptsov@gmail.com); Chief Researcher, Mechanical Engineering Research Institute of the Russian Academy of Sciences (4, Bardina str., Moscow, 119334, e-mail: vsleptsov@gmail.com).

Anna D. Lagunova (Moscow, Russian Federation) – Ph. D. in Economics Sciences, Associate Professor, Departments of Practical and Applied Informatics, MIREA – Russian Technological University (78, Vernadskogo ave., Moscow, 119454, e-mail: lagunova.ad@gmail. com).

Anna E. Ablaeva (Moscow, Russian Federation) – Senior Lecturer, Departments of Instruments and Information-Measuring Systems, MIREA – Russian Technological University (78, Vernadskogo ave., Moscow, 119454, e-mail: ablaeva@mirea.ru).

1. Korn G., Korn T. Spravochnik po matematike dlia nauchnykh rabotnikov i inzhenerov [Math reference book for scientists and engineers]. Moscow, Nauka, 2003, 832 p.

2. Besekersky V.A., Popov E.P. Teoriia sistem avtomaticheskogo regulirovaniia [Theory of automatic control systems]. Moscow, Nauka, 1972, 768 p.

3. Blaze E.S., Danilov Yu.A., Kazmirenko V.F. et al. Slediashchie privody. Pod red. B.K. Chemodanova; kn. pervaia [Tracking drives / ton. First]. Moscow, Energiya, 1976, 480 p.

4. Entsiklopediia elementarnoi matematiki. Tom 1. Elementarnaia algebra i analiz [Encyclopedia of Elementary Mathematics. Volume 1. Elementary Algebra and Analysis]. Moscow, EE Media, 2012, 638 p.

5. Belyi E.K., Dorofeeva Yu.A. Algebraicheskie uravneniia: uchebnoe posobie [Algebraic equations: textbook]. Petrozavodsk, PetrGU, 2015, 240 p.

6. Panteleev A.V., Yakimova A.S. Teoriia funktsii kompleksnogo peremennogo i operatsionnoe ischislenie v primerakh i zadachakh: uchebnoe posobie [Theory of functions of a complex variable and operational calculus in examples and problems: a textbook]. Moscow, Vysshaia shkola, 2001, 445 p.

7. Akimov V.N., Konovalova I.N. Kompleksnye chisla, kompleksnye vektory i ikh prilozheniia: uchebnoe posobie [Complex numbers, complex vectors and their applications: textbook]. Moscow, GOU VPO Rossiiskii gosudarstvennyi meditsinskii universitet, 2018, 81 p.

8. Arzhantsev I.V. Bazisy Grebnera i sistemy algebraicheskikh uravnenii [Basis of Gröbner and systems of algebraic equations]. Moscow, MTsNMO, 2003, 68 p.

9. Tynkevich M.A. Vvedenie v chislennyi analiz: ucheb. posobie [Introduction to numerical analysis: study. manual]. Kemerovo, KuzSTU, 2017, 176 p.

10. Glukhov M.M., Elizarov V.P., Nechaev A.A. Algebra: uchebnik. V 2-kh t. T. I [Algebra. V 2-kh t. T. I]. Moscow, Gelios ARV, 2003, 336 p.

11. Cormen, Thomas H.; Leiserson, Charles E.; Rivest, Ronald L.; Stein, Clifford. Introduction to Algorithms. 3rd. MIT Press, 2009, 1292 p.

12. Naudin P., Quitte C. Algoritmique algebrique. Masson, 1992, 720 p.

13. Bakhvalov N.S., Zhidkov N.P., Kobelkov G.M. Chislennye metody [Numerical methods]. Moscow, Binom. Laboratoriia znanii, 2003, 640 p.

14. Samarsky A.A. Vvedenie v chislennye metody: uchebnoe posobie [Introduction to numerical methods: textbook]. SPb, Lan', 2005, 288 p.

15. Sleptsov V.V. Metod priblizhennogo resheniia uravnenii [Method of approximate solution of equations]. Rossiyskii elogicheskii zhurnal, 2015, no 3(8), tom 1, pp. 10-16, available at: https://www.mirea.ru/­upload/medialibrary/678/1-03-sleptsov-16.pdf (accessed July 26, 2021).

The formalisation of the task of railway planning, namely, the formation of freight trains and their routes along the railway network of the mining company is considered. The statement of the problem including parameters of the problem, variables, system of constraints and target function is presented. An integer formulation of the problem, taking into account the constraints of a particular mining company, is proposed.

The problem of railroad planning is relevant despite the various approaches and solutions available, since each case encounters different constraints. This formalisation differs from the others because there are different types of locomotives, and hence different capacities, and there are different types of materials to be transported. Four different categories of restrictions are presented.

In addition, the existence of an extensive network of stations, a huge number of non-stationary constraints and other factors significantly increase the dimensionality of such problems, which increases the interest of researchers to them and contributes to the emergence of new and the development of existing methods and approaches to their solution.

In the introduction, a description and features of the considered railway network of a mining company are presented. It then presents the formulation of the problem to be formalised, including parameters, variables, constraint system and target function. Then a numerical example with a solution is given. The integer linear programming method is used as a method for solving this problem. An example of scheduling freight trains for a network including four stations connected by double-track runs and having a star form is considered. The task of constructing routes is not considered in this example, as it is a separate complex task and is not required for this example, as there is a direct path from each departure station to each destination station.

Keywords: graph theory, mathematical modelling, optimisation, linear programming, integer programming, railway planning problems, timetable theory, transport organisation, train management, mining.

Evgeny V. Eletin (Lipetsk, Russian Federation) – Head of NLMK's Centre for Management Systems and Scientific and Technical Information, Corporate Solutions Centre (20, Sovetskaya str., Lipetsk, 398001, e-mail: eletin_ev@cscentr.com)

Galina S. Borovkova (Lipetsk, Russian Federation) – Ph. D. in Engineering Sciences, associate professor, department of applied mathematics, Lipetsk State Technical University (30, Moskovskaya str., Lipetsk, 398055, e-mail: haligh@mail.ru)

Alexander V. Galkin (Lipetsk, Russian Federation) – Ph. D. in Engineering Sciences, Associate Professor, Dean of Automation and Informatics Department, Applied Mathematics Department, Lipetsk State Technical University
(30, Moskovskaya str., Lipetsk, 398055, e-mail: avgalkin82@mail.ru)

1. Lazarev A.A., Musatova E.G., Gafarov E.R., Kvaratskhelia A.G. Schedule Theory. Problems of railway planning. Moscow, IPU RAN, 2012, 92 pp.

2. Lazarev A.A., Musatova E.G. Integral formulation of a task of railway trains formation and its schedule. Control of the big systems. Moscow, IPU RAN, 2012, issue 38, pp. 161–169.

3. Lazarev A.A., Musatova E.G., Kvaratskhelia A.G., Gafarov E.R. Theory of schedules. The tasks of control over transport systems. Moscow, Faculty of Physics of Lomonosov Moscow State University, 2012, pp. 160.

4. Petrov K.V., Nizov A.S. Mathematical justification of the modern concept of planning and management of transport support. Bulletin of the Military Academy of Material and Technical Support named after Army General A.V. Khrulev, 2018, no 1 (13), pp. 15–21.

5. Varichev A.V., Kretov S.I., Ismagilov R.I., Badtiev B.P., Vladimirov D.Y. Complex approach to intelligent control systems of mining production. Mining Industry. 2016, no 3 (127), pp. 4.

6. Gainanov D.N., Rasskazova V.A. Mathematical modelling in a task of optimal assignment and movement of locomotives by methods of graph theory and combinatorial optimisation. Proceedings of MAI, 2017, no 92, pp. 31.

7. Karpukhin V.B., Bilenko G.M. Choice of optimal cargo transportation strategy of a transport enterprise based on solutions of game tasks. Science and Technology of Transport, 2019, no 4, pp. 18–23.

8. Zolkin A.L., Chistyakov M.S., Bushtruk T.N., Lee B. Development of algorithm providing qualitative planning of operative schedule of railway transport movement. Bulletin of Donetsk Academy of Automobile Transport, 2021, no 2,
pp. 10–20.

9. Tereshchenko O.A. Operative planning of local work of railway sections and nodes using dynamic model of transportation process. Transportni sistemi takhnologii perevozhenii, 2016, no 12, pp. 80–89.

10. Antonova E.I., Vasiliev I.A. Tasks of planning in the work of railway transport at the container terminal. Description of solution methods. In the collection: Information technologies in science, education and management. Edited by prof. E.L. Gloriozov, 2015, pp. 108–113.

11. Tereshchenko O.A. A dynamic model of the transportation process for solving the problem of operational planning of local work of railway sections and nodes. Bulletin of the Belarusian State University of Transport: Science and Transport, 2017, no 1 (34), pp. 68–71.

12. Karpukhin V. B., Bilenko G. M. Mathematical model of optimal planning problem of car traffic volume at railway transport enterprise. Science and Technology of Transport, 2016, no 4, pp. 27–30.

13. Eletin E., Borovkova G., Galkin A. Solving the Task of Forming Trains and Their Schedule for Four Stations Using the Algorithm of Vertex Gluing. 3rd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), Lipetsk, 10–12 Nov., 2021, pp. 1013 – 1016.

Some aspects of the analysis of polymer composite materials as complex systems are considered. In this case, the system is presented as a combination of one polymer matrix and several active additives. Within the framework of this work, the composition is assumed to be unchanged, and the properties of the composition are controlled by changing the concentration of the ingredients. In work, a mathematical model was developed that calculates the optimal content of components to improve specific properties of the polymer composition. Obtaining such a model is partly hampered by complex interactions between components, but a solution was obtained within the framework of one specific composition. Nevertheless, it was impossible to transfer these results to other compositions in this case, and it was impossible to obtain a general mathematical model for an arbitrary composition. Therefore, to solve this problem, a black-box model was used in this work. The main methods for studying polymer compositions are presented; their systematization is considered according to the principle of controlling properties at different stages of material synthesis. In this work, a variant of controlling the properties of the polymer composition using active additives was used. The urgency of the problem related to the development of methods for assessing the properties and control of the latter by ranking the concentrations of the ingredients of the polymer matrix has been substantiated. As a result, a mathematical model for optimizing the composition of the polymer composition was obtained. It takes into account the positive and the negative influence of the ingredients on the entire composition of the polymer matrix. Also, computational experiments were carried out to find the optimal concentration of active additives in the composition of the polymer composition under conditions of pair interaction of additives. The model is presented and solved using a quadratic programming problem using a specific example. Different cut-off values were used for the content of the ingredients. The results obtained clearly demonstrate the dependence of the properties of a chemical system on the concentration of specific ingredients. Based on the results of two computational experiments under different boundary conditions, the optimal concentration was calculated for the full manifestation of two properties. The paper also presents a vector of further actions, prospects for improving the model, and possible areas of application of this model.

Keywords: optimization, composite materials, fuzzy numbers, mathematical model, quadratic programming, polymer matrix, active additives, Pareto optimization, polymer compositions, chemical structure.

Ilya V. Germashev (Volgograd, Russian Federation) – Dr. Habil. in Engineering, Professor, Professor of the Department of Mathematical Analysis and Theory of Functions, Volgograd State University (100, Universitetskiy ave., Volgograd, 400062, germashev@volsu.ru).

Egor F. Feoktistov (Volgograd, Russian Federation) – Ph. D. student of the Department of Mathematical Analysis and Theory of Functions, Volgograd State University (100, Universitetskiy ave., Volgograd, 400062, faa-201_193934@volsu.ru).

Vyacheslav E. Derbisher (Volgograd, Russian Federation) – Dr. Habil. in Chemistry, Professor, Professor of the Department of High Molecular and Fibrous Materials Technology, Volgograd State Technical University (28, Lenin ave., Volgograd, 400005, derbisher_ve@vstu.ru).

Evgeniya V. Derbisher (Volgograd, Russian Federation) – Ph. D. in Engineering, Associate Professor, Associate Professor of the Department of Analytical, Physical Chemistry and Physicochemistry of Polymers, Volgograd State Technical University (28, Lenin ave., Volgograd, 400005, derbisher2@vstu.ru).

1. Bobryshev A. N., Yerofeev V. T., Kozomazov V. N. Polymernie Compositsionnie Materialy: Ucheb. Posobie (Polymer composite materials: textbook). ASV, Moscow, 2013, 480 p. (in Russian)

2. Wang G., Wang C., Zhao J. et al. Modelling of thermal transport through a nanocellular polymer foam toward the generation of a new superinsulating material. Nanoscale, 2017, vol. 9, pp. 5996–6009.

3. Rentería-Baltiérrez F. Y., Reyes-Melo M. E., Puente-Córdova J. G., López-Walle B. Correlation between the mechanical and dielectric responses in polymer films by a fractional calculus approach. Journal of Applied Polymer Science, 2021, vol. 138, iss. 7, art. 49853, DOI: 10.1002/app.49853

4. Grigoriev I. V. Chislennoe issledovanie processa polimerizatsii butadiena metodami matematicheskogo modelirovania (Numerical study of the butadiene polymerization process by methods of mathematical modeling). Differencialnie Uravnenia I Smezhnie Problemi (Differential Equations and Related Problems), Bashkir State University, Sterlitamak, June 25-29, 2018 (in Russian)

5. Morita A., Matsuba G., Fujimoto M. Evaluation of hydrophilic cellulose nanofiber dispersions in a hydrophobic isotactic polypropylene composite. Journal of Applied Polymer Science, 2021, vol. 138, iss. 8, art. 49896, DOI: 10.1002/app.49896

6. Patnaik L.M., Rajan K. Target detection through image processing and resilient propagation algorithms. Neurocomputing, 2000, vol. 35, no. 1-4, pp. 123–125.

7. Brząkalski D., Przekop R. E., Dobrosielska M., Sztorch B., Marciniak P., Marciniec B. Highly bulky spherosilicates as functional additives for polyethylene processing–Influence on mechanical and thermal properties. Polymer Composites, 2020, vol. 41, pp. 3389–3402.

8. Abbasi H., Antunes M., Velasco J. I. Enhancing the electrical conductivity of polyetherimide-based foams by simultaneously increasing the porosity and graphene nanoplatelets dispersion. Polymer Composites, 2019, vol. 40, pp. E1416-E1425.

9. Bouknaitir I., Panniello A., Teixeira S. S., Kreit L., Corricelli M., Striccoli M., Costa L. C., Achour M. E. Optical and dielectric properties of PMMA (poly(methyl methacrylate))/carbon dots composites. Polymer Composites, 2019, vol. 40, pp. E1312-E1319.

10. Jiang J., Mei C., Pan M., Cao J. Improved mechanical properties and hydrophobicity on wood flour reinforced composites: Incorporation of silica/montmorillonite nanoparticles in polymers. Polymer Composites, 2020, vol. 41, pp. 1090-1099.

11. Zare Y., Rhee K. Y. Advancement of a model for electrical conductivity of polymer nanocomposites reinforced with carbon nanotubes by a known model for thermal conductivity. Engineering with Computers, 2020, 11 p. DOI: 10.1007/s00366-020-01220-7

12. Goli E et al. Frontal polymerization of unidirectional carbon-fiber-reinforced composites. Composites Part A. Applied Science and Manufacturing, 2020, vol. 130, art. 105689.

13. De Keer L. et al. Benchmarking Stochastic and Deterministic Kinetic Modeling of Bulk and Solution Radical Polymerization Processes by Including Six Types of Factors Two. Macromolecular Theory and Simulations, 2020, vol. 29, no. 6, art. 2000065.

14. López-Domínguez P., Clemente-Montes D. A., Vivaldo-Lima E. Modeling of Reversible Deactivation Radical Polymerization of Vinyl Monomers Promoted by Redox Initiation Using NHPI and Xanthone. Macromolecular Reaction Engineering, 2020, vol. 14, no. 6, art. 2000020.

15. Wendel R., Rosenberg Ph., Wilhelm M., Henning F. Anionic polymerization of ε-caprolactam under the influence of water: 2. Kinetic model. Journal of Composites Science, 2020, vol. 4, no. 1, art. 8, DOI: 10.3390/jcs4010008

16. Akgul Y., Ahlatci H., Turan M. E., Simsir H., Erden M. E., Sun Y., Kilic A. Mechanical, tribological, and biological properties of carbon fiber/hydroxyapatite reinforced hybrid composites. Polymer Composites, 2020,
vol. 41, pp. 2426-2432.

17. Wu M. C. et al. Polymer Additives for Morphology Control in High-Performance Lead-Reduced Perovskite Solar Cells. Solar RRL, 2020, vol. 4, no. 6, art. 2000093.

18. Chen Q. et al. Thermal management of polymer electrolyte membrane fuel cells: A review of cooling methods, material properties, and durability. Applied Energy, 2021, vol. 286, art. 116496.

19. Germashev I.V., Derbisher V.E., Orlova S.A. Evaluation of activity of the fireproofing compounds in elastomer compositions by means of fuzzy sets. Kauchuk i Rezina, 2001, vol. 6, pp. 15-17. (in Russian)

20. Germashev I.V., Derbisher V.E., Vasil'ev P.M. Prediction of the activity of low-molecular organics in polymer compounds using probabilistic methods. Theoretical Foundations of Chemical Engineering, 1998, vol. 32, no. 5, pp. 514-517.

21. Germashev I.V., Derbisher E.V., Derbisher V.E., Mashihina T.P. Model of Paired and Solitary Influence of Ingredients of Polymer Composition. Studies in Systems, Decision and Control, 2021, vol. 342, pp. 205-217.

22. Derbisher E. V., Derbisher V. E. Application of computational methods for the creation and selection of polymer compositions with specified properties. Mathematical Physics and Computer Modeling, 2019, vol. 22, no. 1, pp. 35–53.

This article describes the initial stage of developing an information system for evaluating a sports exercise based on the use of neural networks. The current approach to the evaluation of sports exercises and its shortcomings, as well as the advantages of introducing computer technology, were considered. The analysis of initial data is carried out. Next, the approaches that are used to analyze the position of the athlete's body during the exercise are considered, and an approach is chosen to obtain the position of the athlete's body in space and time. The definition of the concept of key points is given and their location, number on the human body are described. A number of pre-trained neural networks are considered that determine the location of key points on the human body, and the best option for solving the problem posed in this article is selected. The data sets that are used in the training of neural networks, in tasks of determining the position of the human body, are studied. The problem of image analysis is posed and an algorithm for solving the problem is introduced. As a result of the work, a prototype of an information system was developed that is capable of receiving frames from the original video sequence, processing frames using a neural network, recording the position of key points in the image to a text file, and processing data from the file for analysis.

Keywords: image analysis, key points, neural networks, deep learning, exercise assessment, criterion, video analysis, football.

Alexander D. Teryohin (Perm, Russian Federation) – Ph. D. student, Department of Computational mathematics, mechanics and biomechanics, Perm National Research Polytechnic University (29, Komsomolsky ave., Perm, 614990,
e-mail: alex_teryohin@mail.ru)

Oleg R. Ilyalov (Perm, Russian Federation) – Ph. D. in Engineering, Associate Professor Department of Computational mathematics, mechanics and biomechanics, Perm National Research Polytechnic University (29, Komsomolsky ave., Perm, 614990, e-mail: oleg390@mail.ru)

Alexey V. Stepanov (Perm, Russian Federation) – Ph. D. student, Department of Physical Culture, Perm State Humanitarian Pedagogical University; coach of Regional State Budgetary Institution «Sports school «Academy of Game Sports of the Perm Region»» (24, Sibirskaya str., Perm, 614065, e-mail: hideriteo@list.ru)

1. Stepanov, A.V Matematicheskoe modelirovanie pri professional'nom orientirovanii futbolista i progresse razvitiia navykov v dostizhenii top-urovnia [Mathematical modeling with professional orientation of the football player and progress of skills development in reaching the top level]. Scientific theory journal «Uchenye zapiski universiteta imeni P.F. Lesgafta», 2019, no. 8, pp. 210–215.

2. Yasnickiy, L. N. Intellektual'nye sistemy [Intellegent systems]. Laboratoriia znanii, 2016, 221 p.

3. Azevedo D., Player Detection using Deep Learning, available at: https://­medium.com/analytics-vidhya/player-detection-using-deep-learning-492122c3bf9 (accessed 10 January 2022).

4. Neil J.Cronin, Using deep neural networks for kinematic analysis: Challenges and opportunities. Journal of Biomechanics, 2021, vol. 123, pp. 110460, doi: 10.1016/j.jbiomech.2021.110460

5. Kulakov A. How I created the Workout Movement Counting App using Deep Learning and Optical Flow Algorithm, available at: https://­towardsdatascience.com/how-i-created-the-workout-movement-counting-app-using-deep-learning-and-optical-flow-89f9d2e087ac (accessed 10 January 2022).

6. Bazarevsky V., Grishchenko I. On-device, Real-time Body Pose Tracking with MediaPipe BlazePose, available at: https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html (accessed 10 January 2022).

7. Liu H., Liu F., Fan X., Huang D. Polarized Self-Attention: Towards High-quality Pixel-wise Regression, available at: https://arxiv.org/pdf/2107.00782v2.pdf (accessed 10 January 2022).

8. Artacho B., Savakis A. OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation, available at: https://arxiv.org/pdf/2103.10180v1.pdf (accessed 10 January 2022).

9. Khirodkar R.,Chari V., Agrawa A.,Tyagi A. Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation, available at: https://­arxiv.org/pdf/2101.11223v3.pdf (accessed 10 January 2022).

10. Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, Piotr Dollár. Microsoft COCO: Common Objects in Context, available at: https://arxiv.org/abs/1405.0312 (accessed 10 January 2022).

11. Researh Team. An overview of human pose estimation with deep learning, available at: https://beyondminds.ai/blog/an-overview-of-human-pose-estimation-with-deep-learning/ (accessed 10 January 2022).

12. Andriluka M., Pishchulin L., Gehler P., Schiele, Bernt. 2D Human Pose Estimation: New Benchmark and State of the Art Analysis. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, doi: 10.1109/­CVPR.2014.471

13. Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, and Cewu Lu. CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark, available at: https://arxiv.org/pdf/1812.00324.pdf (accessed 10 January 2022).

Rectification and reactive distillation columns are the main of all units in the petrochemical and refining industry. Soft sensors consist of mathematical models that estimate of the quality of an output product in real time are used for technological processes control. In general, changes in the composition of raw materials, catalyst deactivation, etc. result in inconsistency between obtained data and the current state of the technological process. Soft sensor design obtained on such data will loss of accuracy in estimating the necessary parameters of the output product.

An adaptive soft sensor design based on a neural network with a predictive filter in the feedback loop for solve the mismatching obtained data and the current state of the technological process problem is proposed. “Moving window” conception is used for size window adapting to the actual state of the technological process. Parameter estimation based on a neural network using data matching to the technological process. A predictive filter in the feedback loop for improve the estimation accuracy of the quality parameter at the cost of predicting the error of the soft sensor designed is proposed.

A comparative analysis of several adaptive soft sensors based on neural networks using the "moving window" conception for estimation a by-product concentration of in the output product of the reaction-distillation column and the effectiveness of the proposed approach are shown. Application of the predictive filter in the feedback loop allows to improve the accuracy of the soft sensor based on a neural network by 12.94 % (coefficient of determination) and by 39.81 % (mean absolute error) in comparison with that of without predictive filter.

Keywords: soft sensor, predicting, adaptive soft sensor, reaction distillation column, neural network, “moving window” conception, nonlinearity, genetic algorithm, predictive filter, feedback loop.

Sergey V. Stabrov (Vladivostok, Russian Federation) – Master's student, Department of Computer-integrated Production Systems of the Polytechnic Institute (School), Far Eastern Federal University (10, Ajax, Russky Island, Vladivostok, 690922, e-mail: stabrov.sv@gmail.ru).

Denis V. Shtakin (Vladivostok, Russian Federation) – Master's student, Department of Computer-integrated Production Systems of the Polytechnic Institute (School), Far Eastern Federal University (10, Ajax, Russky Island, Vladivostok, 690922, e-mail: dshtakin21@ya.ru).

Svetlana A. Samotylova (Vladivostok, Russian Federation) – Ph. D. in Engineering, Senior Researcher, Process Control Laboratory, Institute of Automation and Control (5, Radio street, Vladivostok, 690041, e-mail: samotylova@dvo.ru); Assistant, Department of Computer-Integrated Manufacturing Systems of the Polytechnic Institute (School), Far Eastern Federal University (10, Ajax, Russky Island, Vladivostok, 690922, e-mail: samotylova.sa@dvfu.ru).

Andrei Yu. Torgashov (Vladivostok, Russian Federation) – Dr. Habil. of Engineering, Associate Professor, Principal Researcher, Process Control Laboratory, Institute of Automation and Control (5, Radio street, Vladivostok, 690041,
e-mail: torgashov@iacp.dvo.ru); Professor, Department of Computer-Integrated Manufacturing Systems of the Polytechnic Institute (School), Far Eastern Federal University (10, Ajax, Russky Island, Vladivostok, 690922, e-mail: torgashov.aiu@dvfu.ru).

1. Mohanta H.K., Pani A.K. Support vector regression modeling in recursive just-in-time learning framework for adaptive soft sensing of naphtha boiling point in crude distillation unit. Petroleum Science, 2021, vol. 18, iss. 4, pp. 1230-1239. DOI: 10.1016/j.petsci.2021.07.001

2. Urhan A., Alakent B. Integrating adaptive moving window and just-in-time learning paradigms for soft-sensor design. Neurocomputing, 2020, vol. 392, pp. 23-37. DOI: 10.1016/j.neucom.2020.01.083

3. Curreri F., Patanè L., Xibilia M.G. Soft sensor transferability: a survey. Applied Sciences, 2021, vol. 11, iss. 16, art. 7710. DOI: 10.3390/app11167710

4. Kadlec P., Gabrys B. Local learning-based adaptive soft sensor for catalyst activation prediction. AIChE Journal, 2011, vol. 57, pp. 1288-1301. DOI: 10.1002/aic.12346

5. Liu Y., Gao Z., Chen J. Development of soft-sensors for online quality prediction of sequential-reactor-multi-grade industrial processes. Chemical Engineering Science, 2013, vol. 102, pp. 602-612. DOI: 10.1016/j.ces.2013.07.002

6. Kneale C., Brown S.D. Small moving window calibration models for soft sensing processes with limited history. Chemometrics and Intelligent Laboratory Systems, 2018, vol. 183, pp. 36-46. DOI: 10.1016/j.chemolab.2018.10.007

7. Kano M., Ogawa M. The state of the art in advanced chemical process control in Japan. IFAC Proceedings, 2009, vol. 42, iss. 11, pp. 10-25. DOI: 10.3182/20090712-4-TR-2008.00005

8. Curreri F., Fiumara G., Xibilia M.G. Input selection methods for soft sensor design: a survey. Future Internet, 2020, vol. 12, iss. 6, art. 97. DOI: 10.3390/fi12060097

9. Yuan X., Zhou J., Wang J. A spatial-temporal LWPLS for adaptive soft sensor modeling and its application for an industrial hydrocracking process. Chemometrics and Intelligent Laboratory Systems, 2020, vol. 197, art. 103921. DOI: 10.1016/j.chemolab.2019.103921

10. Rani A., Singh V., Gupta J.R.P. Development of soft sensor for neural network based control of distillation column. ISA transactions, 2013. vol. 52, iss. 3, pp. 438-449. DOI: 10.1016/j.isatra.2012.12.009

11. Yuan X., Qi S., Wang Y., Xia H. A dynamic CNN for nonlinear dynamic feature learning in soft sensor modeling of industrial process data. Control Engineering Practice, 2020, vol. 104, art. 104614. DOI: 10.1016/­j.conengprac.2020.104614

12. Yuan X., Qi S., Shardt Y.A., Wang Y., Yang C., Gui W. Soft sensor model for dynamic processes based on multichannel convolutional neural network. Chemometrics and Intelligent Laboratory Systems, 2020, vol. 203, art. 104050. DOI: 10.1016/j.chemolab.2020.104050

13. Foresee F.D., Hagan M.T. Gauss-Newton approximation to Bayesian learning. Proceedings of international conference on neural networks (ICNN'97), 1997, vol 3, pp. 1930-1935. DOI: 10.1109/ICNN.1997.614194

14. Nguyen D., Widrow B. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. 1990 IJCNN International Joint Conference on Neural Networks, 1990, pp. 21-26. DOI: 10.1109/IJCNN.1990.137819

15. Hagan M.T., Menhaj M.B. Training feedforward networks with the Marquardt algorithm. IEEE transactions on Neural Networks, 1994, vol. 5, iss. 6, pp. 989-993. DOI: 10.1109/72.329697

16. Warsito B., Santoso R., Yasin H. Cascade forward neural network for time series prediction. Journal of Physics: Conference Series, 2018, vol. 1025,
iss. 1, art. 012097. DOI :10.1088/1742-6596/1025/1/012097

17. Box G.E., Jenkins G.M., Reinsel G.C., Ljung G.M. Time series analysis: forecasting and control. USA, John Wiley & Sons, 2015, 712 p.

18. Hamilton J.D. Time series analysis. New Jersey, Princeton university press, 2020, 816 p.

19. Onnen C., Babuška R., Kaymak U., Sousa J.M., Verbruggen H.B., Isermann R. Genetic algorithms for optimization in predictive control. Control Engineering Practice, 1997, vol. 5, iss. 10. pp. 1363-1372. DOI: 10.1016/S0967-0661(97)00133-0

20. Wang Z., Sobey A. A comparative review between Genetic Algorithm use in composite optimisation and the state-of-the-art in evolutionary computation. Composite Structures, 2020, vol. 233, art. 111739. DOI: 10.1016/­j.compstruct.2019.111739

21. Qu Y., Ma Z., Clausen A., Jørgensen B.N. A Comprehensive Review on Evolutionary Algorithm Solving Multi-Objective Problems. 22nd IEEE International Conference on Industrial Technology (ICIT), 2021, vol. 1, pp. 825-831. DOI: 10.1109/ICIT46573.2021.9453636

22. Ljung L. System identification: Signal analysis and prediction. Boston, MA, 1998, 163-173 pp.

The great majority of currently used cable products contain polymer materials in their construction, which tend to degrade their physical and electrical properties over time. This process is aggravated when the temperature of the product increases. The design of cable lines and the conditions of their collective laying, for example, in cable channels, complicate the thermal control of their operation, while the conditions of an isolated channel contribute to the heating of individual lines at the expense of neighboring ones. The existing engineering methods for calculating the cable temperature specified in IEC 60287-1-1-2009 do not allow taking into account all the features of a particular cable structure. Therefore, the task of a quick and accurate assessment of the thermal state of all polymer elements of the lines laid in the channel is very urgent.

The paper considers the possibility of replacing direct observation of the thermal field of a cable channel with its equivalent mathematical model capable of determining stable stationary temperature distributions at given current loads of lines. Such a model, in addition to the speed of finding the desired parameters, has such an advantage over a real line as the ability to evaluate the internal temperature field of the cable without violating the integrity of its design.

Using a mathematical model, it is proposed to analyze the thermal state of the channel by comparing the temperatures of the elements of cable lines with a predetermined setpoint. When the fact of exceeding the setpoint is detected, an algorithm is started for selecting such a combination of current loads at which the temperatures of the line elements do not exceed the set value. An additional criterion for selecting the mode is the minimum reduction of currents in comparison with their initial value. The algorithms proposed in this paper are universal and can be used for channels of various designs and with different numbers of lines, as well as for analyzing the operation of similar engineering structures, for example, ventilation ducts with transit lines of air conditioning systems, pipelines for hot liquids and gases.

The developed algorithms are functionally suitable for creating specialized software operating in the mode of an adviser to the operator of an electricity distribution node. The software is designed to pre-evaluate any change in line loads, checking for possible overheating and giving the operator either approval of the mode, or offering a safe option for long-term operation.

Keywords: cable channel, thermal field, current loads, heating of lines, mathematical model, load control, permissible mode, algorithm for finding a solution, sampling according to specified criteria, decision-making assistance system.

Irina B. Kukharchuk (Perm, Russian Federation) – senior lecturer of the Department of Designing and technology in electrical equipment, Perm National Research Polytechnic University (29, Komsomolsky ave., Perm, 614990, e-mail: kuharchuk_ib@mail.ru).

1. Anishchenko V.A., Gorokhovik I.V. Vliianie peregruzochnoi sposobnosti maslonapolnennykh transformatorov na propusknuiu sposobnost' elektricheskoi seti [The effect of the overload capacity of oil-filled transformers on the capacity of the electrical network]. Energetika. Izvestiia vysshikh uchebnykh zavedenii i energeticheskikh ob"edinenii SNG, 2018, vol. 61, no. 4, pp. 310–320. DOI 10.21122/1029-7448-2018-61-4-310-320.

2. Bagautdinov I.Z., Kuvshinov N.E. Preimushchestva primeneniia kabelei s izoliatsiei iz sshitogo polietilena [Advantages of using cables with cross-linked polyethylene insulation]. Innovatsionnaia nauka, 2016, no. 3–3, pp. 51–53.

3. Udovichenko O.V. Temperaturnyi monitoring kabel'nykh linii vysokogo napriazheniia na osnove kabelei s izoliatsiei iz sshitogo polietilena [Temperature monitoring of high voltage cable lines based on cables with cross-linked polyethylene insulation]. Linii elektroperedachi 2008: proektirovanie, stroitel'stvo opyt ekspluatatsii i nauchno-tekhnicheskii progress: materialy III Rossiiskoi nauchn.-prakt. konf. s mezhdunarodnym uchastiem. Novosibirsk, 2008, pp. 301–304.

4. Anders G.J., Braun J.-M., Downes John A., Fujimoto N., Luton M-H., Rizzetto S. Real Time Monitoring of Power Cables by Fibre Optic Technologies. Tests, Applications and Outlook . 6th International Conference on Insulated Power Cables (JiCable'03), Paris, 2003.

5. Poluianovich N.K., Dubiago M.N. Algoritm obucheniia iskusstvennoi neironnoi seti faktornogo prognozirovaniia resursa izoliatsionnykh materialov silovykh kabel'nykh linii [Algorithm for training an artificial neural network for factor prediction of the resource of insulating materials of power cable lines]. Izvestiia IuFU. Tekhnicheskie nauk, 2021, no. 2(219), pp. 59–73. DOI 10.18522/2311-3103-2021-2-59-73.

6. Lebedev V.D., Zaitsev E.S. Algoritm otsenki temperatury zhily odnofaznykh vysokovol'tnykh kabelei s SPE izoliatsiei v rezhime real'nogo vremeni [Algorithm for estimating the core temperature of single-phase high-voltage cables with SPE insulation in real time]. Elektroenergetika glazami molodezhi : trudy VI Mezhdunarodnoi nauchno-tekhnicheskoi konferentsii, Ivanovo, 09–13 noiabria 2015, Ivanovo: Ivanovskii gosudarstvennyi energeticheskii universitet im. V.I. Lenina, pp. 95–100.

7. Balametov A.B., Khalilov E.D., Bairamov M.P., Agakhanova K.A. Programma modelirovaniia temperatury provoda i poter' moshchnosti na osnove ucheta rezhimnykh i atmosfernykh faktorov [A program for modeling wire temperature and power losses based on the consideration of regime and atmospheric factors]. Programmnye produkty i sistemy, 2018, vol. 31, no.2, pp. 396–402. DOI: 10.15827/0236-235X.031.2.396-402.

8. Zaliznyi D.I., Shirokov O.G. Adaptivnaia matematicheskaia model' teplovykh protsessov trekhzhil'nogo silovogo kabelia [Adaptive mathematical model of thermal processes of a three-core power cable]. Vestnik Gomel'skogo gosudarstvennogo tekhnicheskogo universiteta im P.O. Sukhogo. Elektrotekhnika i energetika, 2014, no. 2, pp. 51–63.

9. Baazzim M.S., Al-Saud M.S., El-Kady M.A. Comparison of Finite-Element and IEC Methods for Cable Thermal Analysis under Various Operating Environments. International Journal of Electrical, Computer, Energetic, Electronic and Communication Engineering, 2014, vol. 8, no. 3, pp. 484–489.

10. Trufanova N.M., Kukharchuk I.B., Feofilova N.V. Raschet teplovogo polia kabel'nogo kanala s uchetom teplovykh poter' v ekranakh kabelei [Calculation of the thermal field of the cable channel taking into account the heat losses in the cable screens]. Vestnik PNIPU. Elektrotekhnika, 2018, no. 28, pp.179–193.

11. Trufanova N.M., Kukharchuk I.B. Otsenka rabotosposobnosti kabel'nogo kanala na osnove chislennogo modelirovaniia protsessov termodinamiki [Evaluation of cable channel operability based on numerical modeling of thermodynamic processes]. Vestnik PNIPU. Elektrotekhnika, informatsionnye tekhnologii, sistemy upravleniia, 2020, no. 35, pp. 30-42. DOI 10.15593/2224-9397/2020.3.02.

12. Kukharchuk I.B., Terlych A.E., Trufanova N.M. Eksperimental'noe opredelenie toka nagruzki kabelei s bumazhnoi propitannoi izoliatsiei v ustanovivshemsia teplovom rezhime [Experimental determination of the load current of cables with paper impregnated insulation in a steady-state thermal regime]. Elektrotekhnika, 2021,–no.11,–pp. 19–23.

13. Oleksiuk I.V. Starenie izoliatsii iz sshitogo polietilena kabel'nykh linii [Aging of cross-linked polyethylene insulation of cable lines]. Energetika. Izv. vyssh. ucheb. zavedenii i energ. ob"edinenii SNG, 2021, vol. 64, no.2, pp 121–129.

14. Poliakov D.A., Nikitin K.I., Iurchuk D.A., Koshchuk G.A. Issledovanie protsessa stareniia SPE-izoliatsii kabelei pod vozdeistviem temperatury [Investigation of the aging process of SPE insulation of cables under the influence of temperature]. Elektroenergetika glazami molodezhi – 2017: materialy VIII Mezhdunarodnoi nauchno-tekhnicheskoi konferentsii, Samara, 02–06 oktiabria 2017, Samara: Samarskii gosudarstvennyi tekhnicheskii universitet, pp. 261–264.

15. Trufanova N.M., Kazakov A.V., Kukharchuk I.B. Podkhody k predstavleniiu zavisimosti temperatur kabel'nykh linii v kanale ot ikh zagruzki v vide parametricheskoi modeli [Approaches to the representation of the temperature dependence of cable lines in the channel on their loading in the form of a parametric model]. Vestnik PNIPU. Elektrotekhnika, informatsionnye tekhnologii, sistemy upravleniia, 2021, no.40, pp. 61–75.

This article is devoted to the development and research of models and methods for evaluating the information management system of an industrial enterprise (IOPP) as an indicator of the effectiveness of the management of the organizational and economic system.

The importance and significance of the factor of improving the information support system to ensure the competitiveness of modern industrial enterprises and organizations in all spheres of the economy is shown. The industry specifics and the nature of the organization of production processes are analyzed on the basis of expert evaluation.

The sequence of stages of application of the proposed methodological approach to improving the information management system of an industrial enterprise is highlighted. Models and methods are proposed that allow to establish and assess compliance with the requirements for information support and the level of competitive stability, external and internal regulatory documents.

The synthesis of dominant analysis and factor analysis methods was applied to systematize the most significant factors of IOPP that have developed in the information environment, grouped into four groups that make up the content of the corresponding cells of the DETA matrix: I cell – a group of organizational factors (Development); II cell – a group of economic factors (Economic); III cell – a group of technical and technological factors (Technology); IV cell – a group of managerial factors (Administration).

The DETA matrix presents significant factors that enable the management of an industrial enterprise to develop an appropriate methodological approach to improving the IOPP system by evaluating the achieved and expected indicators, together with modern trends in the development of the information environment.

The matrix method of NDV analysis and the method of point estimates are presented and tested, which allowed: to determine the subsystems of the IOPP subject to evaluation procedures and criteria for their evaluation; to distribute evaluation indicators into groups according to NDV criteria (availability, sufficiency, availability, demand); to identify "bottlenecks" on which the managerial impact of the management of an industrial enterprise should be concentrated; to select criteria and indicators based on the specifics of a particular industrial enterprise.

The methodical approach has been consistently tested at JSC "Lysvensky Enameled Ware Factory (LZEP)".

Based on the industry specifics and the nature of the organization of production processes on the basis of expert evaluation, the parameters of the NDV were adopted as criteria, which made it possible to form an array including 16 indicators and build an evaluation classifier.

The evaluation classifier made it possible to construct a conditional diagram of the IOPP management system in the criteria and subsystem sections

Illustrative examples of the use of the proposed models and methods are given.

Based on the results obtained, the author has developed an integral efficiency coefficient of the IOPP management system according to the criteria of the NDV.

According to the information support management system of JSC "LZEP", an imbalance is stated with respect to the subsystem and criteria sections.

Keywords: information support of an industrial enterprise, management efficiency of the organizational and economic system, expert evaluation, information support system, availability, sufficiency, accessibility, demand, DETA-analysis.

Alexey M. Bochkarev (Perm, Russian Federation) – Senior Lecturer of the Department of Automation and Telemechanics, Perm National Research Polytechnic University (29, Komsomolsky ave., Perm, 614990, e-mail: albo-73@mail.ru).

Vladimir I. Freyman (Perm, Russian Federation) – Dr. Habil. in Engineering, Professor, Department of Automatization and Telemechanics, Perm National Research Polytechnic University (29, Komsomolsky ave., Perm, 614990,
e-mail: vfrey@mail.ru).

1. Kvasova, E.Yu., Kudryashova, T.V. Assessment of information security of corporate governance: improvements. Bulletin of the Novgorod State University, 2011, no. 61, pp. 57-61.

2. Bochkarev, A.M. Actualization of improvement of information support systems of an industrial enterprise. Creative Economy, 2019, vol. 13, no. 6, pp. 1205-1214.

3. Mingaleva, Zh.A. Key factors of stimulating technological modernization of industrial production. Vector of Economics, 2018, no. 4 (22), pp. 80-88.

4. Kamshilov, S.G., Prokhorova, L.V. Methodology for assessing the information security of business processes at enterprises. Bulletin of Chelyabinsk State University, 2014, no. 2(331), issue 9, pp. 41-43.

5. Katsuro, D.A. To information support for ensuring economic security at the enterprise. Modern high-tech technologies, 2014, no. 4, pp. 138.

6. Bochkarev, A.M. Features of the structural approach to the system of information support of the production activity of the enterprise. Competitiveness in the global world: economics, science, technology, 2017, no. 11 (58), pp. 570-574.

7. Korshunov G.I., Freyman V.I. Models and methods for assessing the conformity of product quality indicators and the effectiveness of training specialists. Fundamental research, 2015, no. 12-6, pp. 1116-1120.

8. Matveikin, I.V., Izvozchikova, V.V. Methodological and information support of enterprise management during the formation of the information economy. Orenburg State Agrarian University. Orenburg. 2011, 168 p.

9. Fayzrakhmanov, R.A., Polevshchikov S.I., Mordysheva A.S. Features of complex automatic assessment of the quality of exercises on the computer simulator of the operator of the production and technological system. Engineering Bulletin of the Don, 2014, vol. 31, no. 4-1, pp. 119.

10. Methods and models of information management: Studies. Stipend. Edited by A.V. Kostrov. Moscow, Finance and Statistics, 2007, 336 p.

11. Kon E.L., Freyman V.I., Yuzhakov A.A. Implementation of algorithms for decoding the results of unconditional and conditional search when checking the level of mastering elements of disciplinary competencies. Education and Science, 2013, no. 10 (109), pp. 17-36.

12. Freyman V.I., Kon E.L., Yuzhakov A.A. Approach to the development of educational programs for the preparation of masters. Educational resources and technologies, 2014, no. 2 (5), pp. 29-34.

13. Freyman V.I. Implementation of one algorithm for conditional search of competence elements with insufficient level of development. Information and control systems, 2014, no. 2 (69), pp. 93-102.

14. Kon E.L., Freyman V.I., Yuzhakov A.A. New approaches to training specialists in the field of infocommunications. Bulletin of the Volga State Technological University. Series: Radio engineering and infocommunication systems, 2015, no. 1 (25), pp. 73-89.

15. Speshilova, N.V., Mazharova, E.A., Andrienko, D.A. Automation of economic information processing using information technologies. Orenburg, 2018, 224 p.

16. Ivanova, T.E., Zaretsky, A.D. Industrial technologies and innovations. Saint Petersburg, Peter, 2018, 480 p.

17. Milner B.Z. A systematic approach to the organization of management. Moscow, Ekonomika, 1983, 184 p.

18. Lavrishcheva, E.E. On the issue of ensuring the availability of an enterprise information resource. Economics of education, 2012, no. 4, pp.135-139.

19. Lapaeva, O.A. Information support for the management of innovative processes at the enterprise. Bulletin of ChelSU, 2005, no. 1, pp.49-57.

20. Mirolyubova, T.V. World and national markets of information resources: modern features and impact on the economy. Scientific and technical information. Series 1: Organization and methodology of information work, 2015, no. 9, pp. 2-22.

21. Molodchik, A.V., Sevastyanov, V.P. About the possibilities of self-financing of innovative programs of industrial enterprises. Bulletin of Perm National Research Polytechnic University. Socio-economic sciences, 2016, no. 1, pp. 62-77.

22. Saenko V.G., Demidova I.A. Substantiation of the model of information support for sustainable economic development of an industrial enterprise. Project management and production development, 2008, no. 3, pp. 44-51.

23. Sevastyanov, Yu.S. Scientific and organizational bases of information activity. Moscow, Radio and Communications, 1983, 184 p.

24. Speshilova, N.V., Mazharova, E.A., Andrienko, D.A. Automation of economic information processing using information technologies. Orenburg, 2018, 224 p.

25. Fatkhutdinov, R.A. Production management: Textbook for universities. 4th ed. St. Petersburg, Peter, 2003, 491 p.

26. Firsova I.A. Information support as a necessary condition for the implementation of a project approach to enterprise management. Innovative development of the economy, 2012, no. 4(10), pp. 60-65.

Traditionally used methods of machinery and equipment valuation do not take into account the probabilistic nature of the process of their operation. Meanwhile, stochastic models of degradation of technical systems are widely used to solve various problems of the theory of reliability. This article refers to the direction of research in which the models of technical systems degradation used in the reliability theory are applied to the problems of machinery and equipment valuation.

The objects of our research are equipment items subject to degradation and random failures. The subject of research is the service life of equipment and their market value. We define the (pre-tax) benefits from the use of equipment as the market value of the work they perform minus operating costs. The market value of equipment is determined by the sum of discounted benefits from its future use. The process of equipment degradation (deterioration of its technical and economic characteristics) is described by a Poisson random process of failures, and for each failure, the performance of the equipment is multiplied by a random coefficient. Operating costs are divided into a variable part depending on the amount of work performed by the equipment and a fixed part. We accept that equipment that has begun to bring negative benefits is decommissioned.

The constructed model makes it possible to obtain explicit expressions for the market value of a unit of work performed by equipment, the average value and the coefficient of variation of its service life, and also to find the dependence of the equipment market value on its performance.

In some cases, appraiser only knows the age of the equipment being assessed and has no information about its performance. However, equipment of the same age may have different performance. In this situation, he can only estimate the average market value of equipment of a given age.We got an integro-differential equation to calculate this average value. It turned out that in this model it can be expressed as a function of the relative age of the value (the ratio of its age to the average service life) and the coefficient of variation of the service life.

The results obtained are presented as graphs that can be directly used to estimate the market value of used machinery and equipment.

Keywords: machinery and equipment, equipment performance, degradation, failures, valuation, market value, anticipation of benefits principle, age, depreciation, percent good factors.

Sergey A. Smolyak (Moscow, Russian Federation) – Dr. Habil. in Economics, Principal Science Researcher, Central Economics and Mathematics Institute of Russian Academy of Sciences (47, Nakhimovsky ave., Moscow, 117418,
e-mail: smolyak1@yandex.ru).

1. International Valuation Standards. International Valuation Standards Council, 2019.

2. Cantorovich L.V. Economichesky raschyot nailuchshego ispolzovaniya resursov [Economic calculation of the optimal use of resources]. Moscow, USSR Academy of Sciences Publ. 1960.

3. Fedotova M.A. (Ed.). Otsenka mashin i oborudovaniya [Machinery and equipment valuation]. Textbook. Second ed. Moscow, INFRA-M, 2018.

4. Smolyak S.A. Stoimostnaya otsenka mashin i oborudovaniya [Machinery and equipment valuation]. Moscow, Option, 2016.

5. Leifer L.A. (Ed.). Spravochnik otsenshchika mashin i oborudovaniya. Correctiruyushchiye coefficienty i characteristiki rynka mashin i oborudovaniya [Reference book of the appraiser of machinery and equipment. / Corrective factors and characteristics of the machinery and equipment market]. Second ed. Nizhny Novgorod: Volga Region Center for Methodological and Informational Support of Assessment, 2019.

6. 2019 Cost Index & Depreciation Schedules. Raleigh: North Carolina Department of Revenue, available at: https://www.ncdor.gov/documents/2019-cost-index-and-depreciation-schedules (accessed 10 Januari 2022).

7. 2020 Personal Property Manual. Arizona Department of Revenue, available at: https://azdor.gov/sites/default/files/media/PROPERTY_pp-manual.pdf (accessed 10 Januari 2022).

8. AH 582. Assessor’s Handbook, Section 582. The Explanation of the Derivation of Equipment Percent Good Factors. California State Board of Equalization. February 1981. Reprinted August 1997.

9. Leifer L.A., Kashnikova P.M. Opredeleniye ostatochnogo sroka sluzhby mashin i oborudovaniya na osnove veroyatnostnykh modeley [Calculation of residual service life of machinery and equipment based on probabilistic models]. Imushchestvennyye otnosheniya v Rossiyskoy Federatsii, 2008, no 1(76), pp. 66-79.

10. Arkin V.I., Slastnikov A.D. Appraisal of property and business in conditions of indeterminacy (a problem of "tail"and "beginnings"). Audit and financial analysis, 2006, no 1, pp. 73-83.

11. Smolyak S.A. Machinery valuation under uncertainty of their technical and economic characteristics. Audit and financial analysis, 2018, no 5, pp. 52-60.

12. Li W., Pham H. Reliability modeling of multi-state degraded systems with multi-competing failures and random shocks. IEEE Transactions on Reliability, 2005, vol. 54(2), pp. 297-303

13. Nakagawa T. Shock and damage models in reliability theory. Springer, 2007.

14. Wang Z., Huang H.-Z., Li Y., Xiao N.-C. An approach to reliability assessment under degradation and shock process. IEEE Transactions on Reliability, 2011, vol. 60(4), pp. 852-863.

15. Arts, J.J. Maintenance modeling and optimization. (BETA publicatie : working papers; vol. 526). Eindhoven: Technische Universiteit Eindhoven. 2017.

16. Smolyak S.A. Puassonovsky process degradacii mashin: primeneniye k stoimostnoy otsenke [The Poisson process of machinery degradation: Application to valuation]. Journal of the New Economic Association, 2020, no 4(48), pp. 63–84. DOI: 10.31737/2221-2264-2020-48-4-3

17. Osteykovsky V.A. Teoriya nadyozhnosti [Reliability theory]: Textbook for universities. Moscow, Vysshaya shkola, 2003.

18. Grinchar N.G., Chalova M.Yu. Fomin V.I. Osnovy nadyozhnosti mashin [Fundamentals of machinery reliability]. Part 1: Tutorial. Moscow, MGUPS Publs, 2014.

The work is devoted to the actual problem of designing and selecting features in the tasks of constructing predictive models of indicators of foreign economic activity of regions. The aim of the work is to develop a methodology for the use of graph models and dimensionality reduction methods for the selection of features in the construction of predictive analytics models of foreign economic activity of regions.

As an approach to describe the structure of foreign economic relations, graph models were used that implement the possibility of building on the basis of the UMAP dimension reduction algorithm. To build an optimal graph based on the UMAP algorithm, it is necessary to vary the number of nearest neighbors for each vertex and the minimum metric distance to establish a connection between the vertices. It is shown that the clique symmetry coefficient of the graph makes it possible to estimate the local connectivity of points in the constructed graph, forming a generalized idea of the network structure from the position of the presence of clusters in it. The Gini index of the graph allows us to assess the correspondence of the global structure of the graph to real networks. The selection of features is based on the analysis of the graph clicks, which provides maximum mutual information MI with a minimum of features, which maximally reduces distortions in describing the structure of regional foreign economic relations.

The application of the described approach made it possible to eliminate the multicollinearity of features, to select indicators, to expand the possibilities of using the existing data set by including new indicators that introduce new useful information about the subject area into the model. The method of feature selection considered in the paper can be rationally used to construct interpreted predictive models of foreign economic activity indicators and as one of the ways to reduce the dimension of the model feature space.

The results obtained allow us to conclude about the advantages of the considered approach to the implementation of the selection of features in the construction of predictive models of indicators of foreign economic activity of regions.

Keywords: graph theory, feature selection, predictive models, dimension reduction, multicollinearity, mutual information, Gini coefficient, foreign economic relations of regions, mutual information, clustering.

Alexey N. Kislyakov (Vladimir, Russian Federation) – Ph. D. in of Engineering, Associate Professor, Associate Professor of the Department of Information Technology, Russian Academy of National Economy and Public Administration under the President of the Russian Federation, Vladimir branch (59a, Gorky str., Vladimir 600017, e-mail: ankislyakov@mail.ru).

1. James G., Witten D., Hastie T., Tibshirani R. An Introduction to Statistical Learning with Appli-cations in R. Publisher, Springer, 2013, 436 р.

2. Shitikov V. K., Mastitsky S. E. Klassifikaciya, regressiya, algoritmy Data Mining s ispol'zovaniem R [Classification, regression, Data Mining algorithms using R]. 2017, E-book, access address. Available at: https://github.com/­ranalytics/data-mining

3. Hausmann R., Hidalgo C. A., Bustos S. et al. The atlas of economic complexity: Mapping paths to prosperity. Mit Press, 2014.

4. Filimonova M., Kislyakov A., Tikhonyuk N. Structural and Dynamic Modelling of the Regions’ Foreign Trade Profile Based on Graph Cluster Analysis. STRATEGICA: Shaping the Future of Business and Economy. Bucharest, October 2021, p. 34-49.

5. Shitikov V.K. Modeling of correlations in the community using networks. Available at: http://www.ievbras.ru/ecostat/Kiril/R/Blog/14_QGraph.pdf (accessed: 08 September 2020)

6. Yoo W., Mayberry R., Bae S., Singh K., He Q.P., Lillard Jr J.W. A study of effects of multicollinearity in the multivariable analysis. International journal of applied science and technology, 2014, Oct 4(5), pp. 9-19.

7. Kislyakov A., Tikhonuyk N. Principles for Development of Predictive Stability Models of Social and Economic Systems on the basis of DTW. E3S Web of Conferences, 2020, Vol. 208, pp. 08001. DOI: 10.1051/e3sconf/202020808001

8. Federal Customs Service of the Russian Federation: ofic. website – Customs statistics of foreign trade of the Russian Federation, 2022. Available at: http://stat.customs.ru.

9. On approval of the methodology for maintaining statistics of mutual trade in goods of the member States of the Eurasian Economic Union and the methodology for maintaining customs statistics of foreign trade in goods of the member States of the Eurasian Economic Union. Board of the Eurasian Economic Commission. Decision of December 25, 2018, no 210.

10. McInnes L., Healy J., Melville J. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv; 2018. no 1802. pp. 03426.

11. Becht E. et al. Dimensionality reduction for visualizing single-cell data using UMAP. Nature biotechnology, 2019, Vol. 37, no 1, pp. 38-44.

12. Van der Maaten L., Hinton G. Visualizing data using t-SNE. Journal of machine learning research, 2008, Vol. 9, no 11.

13. Franklin J. The elements of statistical learning: data mining, inference and prediction. The Mathematical Intelligencer, 2003, no. 27, pp. 83–85. doi: 10.1007/BF02985802

14. Henniab K., Mezghani N., Gouin-Vallerand C. Unsupervised Graph-Based Feature Selection Via Subspace and PageRank Centrality. Available at: https://bit.ly/2HGON5B (accessed 21 Januari 2022).

15. Dicks W., Dunwoody M.J. Groups Acting on Graphs. Cambridge Studies in Advanced Mathematics, 1989. vol. 17,

16. Strogatz S.H. Syncing: how order arises from chaos in the universe, nature and everyday life. Hachette Books, 2012, 352 p.

17. Kumar P., Sharma, D. A potential energy and mutual information based link prediction approach for bipartite networks. Scientific Reports, 2020, no 10,
pp. 20659.

18. Foreman J. A lot of numbers: Big data analysis using Excel. Moscow, Alpina Publisher, 2016, 464 p.

19. Kislyakov A.N. Structuring advertising campaign costs considering the asymmetry of users’ interests. Business Informatics, 2020, vol. 14, no 4, pp. 7–18. DOI: 10.17323/2587-814X.2020.4.7.18

20. Biró, T. S., Néda, Z. Gintropy: Gini Index Based Generalization of Entropy. Entropy, 2020, vol. 22(8), pp. 879. doi:10.3390/e22080879

21. Tan F., Xia Y., Zhu, B. Link Prediction in Complex Networks: A Mutual Information Perspective. PLOS ONE, 2014, no. 9, pp. e107056.

The article is devoted to discussing topical issues about the formation of the price of plane tickets. The paper analyzes and evaluates the degree of influence of factors on the pricing process using regression analysis methods. At the first stage, a review of the available research sources of foreign and Russian authors was carried out, according to the results of which the main characteristics determining the price level of air tickets were identified and considered. In the course of studying the issue, the experience and conclusions, based on previously performed studies of foreign segments of air transportation, are extended to the selection and analysis of current data on the Russian market. The assessment of the degree of a possible influence of the considered price-forming indicators on air ticket fares was carried out using four econometric models of the dependence of ticket prices on exchange rates, fare/air route characteristics, socio-economic and secondary factors. They are checked for lowcost and economy segments based on information on 15 thousand of air tickets of Russian air carriers for the period from 19.01.2021 to 12.02.2021, presented in the form of a single data set. The data was collected independently by daily monitoring of information from the official websites of airlines, federal websites of Rosstat, and Rosaviation. As a result of the research conducted within the framework of this article, it was revealed that with an increase in the distance of the flight, the cost of the ticket increases proportionally. The average income of the population negatively affects prices in the economy and budget classes. A similar trend can be traced concerning the cost of jet fuel at the airport of departure and nonstop flights. Reducing the number of days between the dates of ticket purchase and flight departure will also affect the increase in ticket prices. With a decrease in the exchange rate of foreign currency, the cost of economy class air tickets changes significantly compared to the budget. The reverse trend is observed in the case of the IATA exchange rate, where the effect falls on the last group of shipments. The listed characteristics are identified as the most significant relative to the considered classes of tariff groups in the Russian aviation industry. The results of the work can be recommended to air carriers for use in the process of forming the cost of tickets to achieve maximum efficiency and profitability of the business, used by consumers of the airline services as a tool for finding and buying air tickets with the best conditions and offers.

Keywords: air transport, air travel, airfares, airline industry, airline tickets, airline, civil aviation, factors in price formation, pricing, statistical estimate.

Aleksandr A. Cheremnykh (Perm, Russian Federation) – Student of the Faculty of Economics, Management, and Business Informatics, National Research University “Higher School of Economics”, Perm branch (38, Studentskaya str., Perm, 614070, e-mail: cherema049@yandex.ru).

1. Rossiiane stali aktivnee pol'zovat'sia aviatransportom, vyiasnili sotsiologi [Russian people became more active in air transport, found sociologists]. Available at: https://ria.ru/20180207/1514130948.html (Accessed 23 November 2021).

2. Aviatsiia b'et rekordy [Aviation breaks records]. Available at: https://www.kommersant.ru/doc/4220601?utm_source=yxnews&utm_medium=desktop (Accessed 23 November 2021).

3. Mantin В., & Koo В. Weekend effect in airfare pricing. Journal of Air Transport Management, 2010, vol. 16, iss. 1, pp. 48-50. DOI: 10.1016/j.jairtraman.2009.07.002.

4. Escobari D. Dynamic pricing, advance sales and aggregate demand learning in airlines. Dynamic pricing, advance sales and aggregate demand learning in airlines. The Journal of Industrial Economics, 2012, vol. 4, iss. 60, pp. 697-724. DOI: 10.1111/joie.2012.60.issue-4.

5. Alderighi M., Cento A., & Piga, C. A. A case study of pricing strategies in European airline markets: The London Amsterdam route. Journal of Air Transport Management, 2011, vol. 17, iss. 6, pp. 369-373. DOI: 10.1016/j.jairtraman.2011.02.009.

6. Malighetti P., Paleari S., Redondi R. Pricing strategies of low-cost airlines: The Ryanair case study. Journal of Air Transport Management, 2009, vol. 15, iss. 4, pp. 195-203. DOI: 10.1016/j.jairtraman.2008.09.017.

7. Domínguez-Menchero J.S., Rivera J., Torres-Manzanera E. Optimal purchase timing in the airline market. Journal of Air Transport Management, 2014, vol. 40, pp. 137-143. DOI: 10.1016/j.jairtraman.2014.06.010.

8. Bilotkach V., Talavera O., Gorodnichenko Y. Are airlines’ price-setting strategies different?. Journal of Air Transport Management, 2010, vol. 16, iss. 1, pp. 1-6. DOI: 10.1016/j.jairtraman.2009.04.004.

9. Ivanova М.О. Tsenoobrazovanie na aviabilety mezhdunarodnykh reisov [Pricing of air tickets for international flights]. Modern Trends in the Development of Science and Technology, 2016, no. 12-10, pp. 44-47.

10. Elagina А.S. Tsenoobrazovanie na aviatsionnye bilety: protivorechiia delovogo oborota i pravil konkurentsii [Air ticket pricing: contradictions of business turnover and competition rules]. New in Science and Education. Proceedings of the Annual International Scientific and Practical Conference, 13 April, Moscow, 2016, pp. 36-42.

11. Nikulin A.V., Sologubova О.V. Rynok passazhirskikh aviaperevozok i tsenoobrazovanie aviabiletov [Air passenger market and air ticket pricing]. International Innovation Research: Proceedings of the 15th International Scientific and Practical Conference, 12 December, Penza, 2018, pp. 147-149.

12. Morrison S.A., Winston C. The Dynamics of Airline Pricing and Competition. American Economic Review, 1990, vol. 80, iss. 2, pp. 389-393.

13. Borenstein., Severin., & Nancy L.Rose. Competition and price dispersion in U.S. Airline industry. Journal of Political Economy, 1994, vol. 102, iss. 4, pp. 395-422. DOI: 10.1086/261950.

14. Stavins J. Price discrimination in the airline market: the effect of market concentration. The Review of Economics and Statistics, 2001, vol. 83, iss. 1, pp. 200-202.

15. Kincaid W.M., & Darling D.A. An inventory pricing problem. An inventory pricing problem. Journal of Mathematical Analysis and Applications, 1963, vol. 7, iss. 2, pp. 183-208.

16. Gallego G., & van Ryzin G.J. Optimal dynamic pricing of inventories with stochastic demand over Finite horizons. Management Science, 1994, vol. 40, iss. 8, pp. 999-1020. DOI: 10.1287/mnsc.40.8.999.

17. Prescott E. Efficiency of the natural rate. Efficiency of the natural rate. Journal of Political Economy, 1975, vol. 83, iss. 6, pp. 1229-1236. DOI: 10.1086/260391.

18. Zhang Y. International arrivals to Australia: Determinants and the role of air transport policy. Journal of Air Transport Management, 2015, vol. 44, pp. 21-24. DOI: 10.1016/j.jairtraman.2015.02.004.

19. Fursova S.S. Formirovanie tseny aviabiletov na perelety po Rossii [Formation of the price of air tickets for flights across Russia]. Modern Technologies in the World Scientific Space: Collection of Articles of the International Scientific and Practical Conference: in 6 Parts, 25 May, Perm, 2017, pp. 225-228.

20. Fedorco L, Hospodka J. Airline pricing strategies in European airline market. Journal of Air Transport Management, 2013, vol. 2, pp. 33-41.

21. Shtin Ya.S. Politika tsenoobrazovaniia rossiiskikh i zarubezhnykh aviatsionnykh kompanii [Pricing policy of Russian and foreign aviation companies]. Economics and Management: Analysis of Trends and Development Prospects, 2013, no. 3, pp. 198-201.

22. Wang K., Zhang А. & Zhang Y. Key determinants of airline pricing and air travel demand in China and India: Policy, ownership, and LCC competition. Transport Policy, 2018, vol. 63, iss. С, pp. 80-89. DOI: 10.1016/­j.tranpol.2017.12.018.

23. Federal'naia sluzhba gosudarstvennoi statistiki [The Federal State Statistics Service]. Available at: https://rosstat.gov.ru (Accessed 23 November 2021).

24. Federal'noe agentstvo vozdushnogo transporta [The Federal Air Transport Agency]. Available at: https://favt.gov.ru (Accessed 23 November 2021).