350 rub
Journal Radioengineering №10 for 2018 г.
Article in number:
Basic principles of machine learning methods application for the evaluation of the functioning of radar stations
Type of article: scientific article
DOI: 10.18127/j00338486-201810-02
UDC: 004.942, 004.85
Keywords: radar station the functioning of complex radioelectronic systems machine learning gradient boosting reliability of electronic products.
Authors:

I.A. Kalinov – Project Manager, JSC «Concern «RTI Systems» (Moscow); 

Post-graduate Student, Moscow Institute of Physics and Technology (State University) E-mail: tej@frtk.ru

A.A. Kochkarov – Ph.D.(Phys.-Math.), Associate Professor, Deputy Director of STC-3, JSC «RTI» (Moscow); 

Senior Research Scientist, V.A. Trapeznikov Institute of Control Sciences of RAS (Moscow)

E-mail: akochkar@gmail.com, AKochkarov@oaorti.ru

S.S. Matveeva – Leading Engineer, JSC «A.L. Mints Radiotechnical Institute» (Moscow) E-mail: s.s.matveeva@gmail.com

Abstract:

The paper considers the application of machine learning methods to predict the state of complex structured radio electronic systems. A data model for collecting information on the functioning of a radioelectronic system with the use of an integrated monitoring and monitoring system for the state of its components (blocks) is proposed and justified. The proposed model made it possible to adapt one of the most widespread methods of machine learning, gradient boosting, on a sample of historical data, from the General Designer stand and embedded control system, to solve the problem of forecasting the state of radar stations and its components.

Pages: 18-23
References
  1. Maheshwari A. Data Analytics Made Accessible. Amazon Digital Services. 2018.
  2. Mxitaryan V.S. i dr. Analiz danny’x: Uchebnik dlya akademicheskogo bakalavriata / Pod red. V.S. Mxitaryana. M.: Izd-vo Yurajt. 2016. 490 s.
  3. Das S.R. Bol’shaya sila bol’shix danny’x // Finansy’ i razvitie. 2016. № 9. S. 26−28.
  4. Feldman R., Curry G.G. Manufacturing Systems: Modeling and Analysis. Berlin. Heidelberg: Springer_Verlag. 2011. 335 p.
  5. Kudinov A.V. Informaczionnaya texnologiya dlya resheniya zadach intellektual’nogo analiza proizvodstvenny’x danny’x // Izvestiya Tomskogo politexnicheskogo universiteta. 2012. T. 321. № 5: Upravlenie, vy’chislitel’naya texnika i informatika. S. 66−71.
  6. Sady’xov G.S., Savchenko V.P., Sidnyaev N.I. Modeli i metody’ oczenki ostatochnogo resursa izdelij radioe’lektroniki. M.: Izd-vo MGTU im. N.E’. Baumana. 2015. 382 s.
  7. Shaxanov N.I., Varfolomeev I.A., Ershov E.V., Yudina O.V. Prognozirovanie otkazov oborudovaniya v usloviyax malogo kolichestva polomok // Vestnik Cherepoveczkogo gosudarstvennogo universiteta. 2016. № 6. S. 36−41.
  8. Antonov A.V., Belova K.A., Chepurko V.A. Statisticheskij analiz danny’x ob otkazax oborudovaniya AE’S s uchetom neodnorodnosti potoka otkazov // Izvestiya vuzov. Yadernaya e’nergetika. 2011. № 2. S. 75−87.
  9. Novikov G. Ispol’zovanie metodov poiska patternov v posledovatel’nosti soby’tij dlya prognozirovaniya polomok slozhny’x texnicheskix sistem // Sb. trudov 39-j Mezhdiscziplinarnoj shkoly’-konf. IPPI RAN «Informaczionny’e texnologii i sistemy’ 2015». Institut problem peredachi informaczii im. A.A. Xarkevicha RAN. 2015. S. 1205−1212.
  10. Rusinov M.A. Ob osnovny’x princzipax metodiki analiza redkix soby’tij v diskretny’x slozhny’x sistemax // Vestnik MGTU Stankin. 2015. № 3(34). S. 139−144.
  11. Boev S.F., Savchenko V.P., Stupin D.D., Kochkarov A.A. i dr. Moshhny’e nadgorizontny’e RLS dal’nego obnaruzheniya: razrabotka, ispy’taniya, funkczionirovanie / Pod red. S.F. Boeva. M.: Radiotexnika. 2013. 168 s.
  12. Boev S.F., Logovskij A.S. Upravlenie proczessami sozdaniya RLS DO funkczional’no-blochnoj struktury’ // Zhurnal radioe’lektroniki. 2017. № 7. 12 s. Rezhim dostupa: http://jre.cplire.ru/jre/jul17/11/text.pdf.
  13. Boev S.F., Linkevichius A.P., Logovskij A.S., Yakubovskij S.V. O vozmozhnosti snizheniya srokov i stoimosti sozdaniya RLS DO s ispol’zovaniem stenda glavnogo konstruktora // Zhurnal radioe’lektroniki. 2017. № 9. 22 s. Rezhim dostupa: http://jre.cplire.ru/jre/sep17/10/text.pdf.
  14. Boev S.F., Linkevichius A.P., Matveeva S.S., Timoshenko A.V., Shevczov V.A. Optimizacziya sistemy’ texnicheskogo obsluzhivaniya RLS dal’nego obnaruzheniya na osnove raspoznavaniya otkazov po danny’m vstroennogo kontrolya // E’lektrosvyaz’. 2017. № 10. S. 83−87.
  15. Zaczarinny’j A.A., Garanin A.I., Kozlov S.V. Stend glavnogo konstruktora – organizaczionno-texnicheskaya osnova razrabotki krupnomasshtabny’x informaczionno-telekommunikaczionny’x sistem // Sistemy’ i sredstva informatiki. T. 20. № 3. S. 174−190.
  16. Koe’l’o L.P., Richart V. Postroenie sistem mashinnogo obucheniya na yazy’ke Python. 2016. 302 s.
  17. Friedman J. Greedy Function Approximation: A Gradient Boosting Machine. IMS 1999 Reitz Lecture.
  18. Belyakov R.A., Ignat’ev S.V., Tixonov V.B., Xaritonov A.V. Model’ sistemy’ texnicheskogo obsluzhivaniya radioe’lektronnoj apparatury’ po sostoyaniyu // Uspexi sovremennoj radioe’lektroniki. 2017. № 11. S. 25−29.
  19. Raxmanov A.A., Yakubovskij S.V., Logovskij A.S., Kazanczev A.M. Optimizacziya pusko-naladochny’x rabot RLS DO funkczional’noblochnoj struktury’ na osnove logiko-veroyatnostnoj modeli nadezhnosti i danny’x tekushhego kontrolya // Uspexi sovremennoj radioe’lektroniki. 2017. № 11. S. 30−35.
  20. Hastie T., Tibshirani R., Friedman J.H. «10. Boosting and Additive Trees». The Elements of Statistical Learning. Edition 2nd. New York: Springer. P. 337−384. ISBN 0-387-84857-6. Archived from the original on 2009-11-10.
  21. Cossock, David, Zhang Tong. Statistical Analysis of Bayes Optimal Subset Ranking Archived 2010-08-07 at the Wayback Machine.
Date of receipt: 17 сентября 2018 г.