O.V. Druzhinina1, E.R. Korepanov2, A.A. Petrov3, I.V. Makarenkova4, V.V. Maksimova5

1,2,4,5 FRC «Computer Science and Control» of Russian Academy of Sciences (Moscow, Russia)

3 Bunin Yelets State University (Yelets, Russia)

The problem of generating adequate source data for solving various problems aimed at diagnosing transport system malfunctions is relevant due to the fairly common situation of incomplete information. When developing intelligent systems for monitoring and diagnosing the technical state of transport infrastructure elements, problems arise with the presentation and structuring of large input data for subsequent analysis. One of the effective methods is the construction of fuzzy data generation models with the involvement of expert knowledge. The implementation of data generation models based on fuzzy modeling is a promising direction, involving the use of neural network methods and algorithms for subsequent data processing. Methods and algorithms should focus on the possible use of the domestic hardware and software environment both in the learning process and in the process of application for data processing. The purpose of the work is to develop an approach to constructing a model for generating initial data for solving classification problems in the diagnosis of transport system malfunctions in relation to incomplete information conditions. A fuzzy model for generating a set of estimated data on the technical condition of axle boxes is developed. The rationale for choosing a fuzzy model for generating data on the technical state of axle boxes is given. The features of construction a rule base with the involvement of expert knowledge and regulatory documentation for analyzing the condition of axle boxes are characterized. When constructing the rule base, a set of basic temperature characteristics used in practice in determining the warming boxes is used. The preparation of data in the framework of a fuzzy model for the subsequent solution of the classification problem based on machine learning is described. Software is developed to implement a fuzzy model for generating a set of estimated data on the technical state of axle boxes. The possibilities of using the simulation results for training a neural network designed to diagnose the condition of axle boxes are considered. A test program is implemented on the domestic computing platform Elbrus 801-RS, the prospects of using the domestic electronic component base are characterized. The results can be used to solve problems of diagnostics of transport infrastructure elements, to develop and improve intelligent monitoring systems and digital twin systems in transport.

Druzhinina O.V., Korepanov E.R., Petrov A.A., Makarenkova I.V., Maksimova V.V. Design of a data generation model for solving classification problems in the diagnosis of transport system malfunctions. Nonlinear World. 2023. V. 21. № 3. P. 16-26. DOI: https://doi.org/10.18127/j20700970-202303-02 (In Russian)

1. GOST 20911-89. Tehnicheskaja diagnostika. Terminy i opredelenija [Jelektronnyj resurs]. Rezhim dostupa: https://docs.cntd.ru/document/1200009481 (data obrashhenija: 01.06.2023 (In Russian).
2. Mironov A.A., Obrazcov V.L., Pavljukov A.Je. Teorija i praktika beskontaktnogo teplovogo kontrolja buksovyh uzlov v poezdah. Ekaterinburg: RPF «Assorti». 2012. GOST 20911-89 (In Russian).
3. Mironov A.A., Pavljukov A.Je., Saltykov D.N. Kompleks vychislitel'nyh modelej dlja issledovanija processov kontrolja uzlov podvizhnogo sostava po infrakrasnomu izlucheniju. Mir izmerenij. 2014. № 6. S. 21–27 (In Russian).
4. Belousov V.V., Druzhinina O.V., Korepanov Je.R., Makarenkova I.V., Maksimova V.V. Podhod k ocenke tehnicheskogo sostojanija jelementov i uzlov transportnyh sistem s primeneniem metodov nejrosetevogo modelirovanija i tehnologii cifrovyh dvojnikov. Nejrokomp'jutery: razrabotka, primenenie. 2021. T. 23. № 5. S. 5–20. DOI: https://doi.org/10.18127/j19998554-202105-01 (In Russian).
5. Belousov V.V., Druzhinina O.V., Korepanov Je.R., Makarenkova I.V., Maksimova V.V. Primenenie nejronnyh setej dlja reshenija zadach klassifikacii pri vyjavlenii neispravnostej transportnyh sistem. Nejrokomp'jutery: razrabotka, primenenie. 2022. T. 24. № 4. S. 18–27. DOI: https://doi.org/10.18127/j19998554-202204-02 (In Russian).
6. Jarushkina N.G. Osnovy teorii nechetkih i gibridnyh sistem. M.: Finansy i statistika. 2004 (In Russian).
7. Rabochaja stancija «Jel'brus 801-RS» [Jelektronnyj resurs]. URL= http://www.mcst.ru/elbrus_801-pc/ (data obrashhenija: 01.06.2023) (In Russian).
8. Nejman-zade M.I., Koroljov S.D. Rukovodstvo po jeffektivnomu programmirovaniju na platforme «Jel'brus». Vyp. 1.1 ot 12.05.2021. M.: AO «MCST». 2021 (In Russian).
9. Druzhinina O.V., Korepanov Je.R., Belousov V.V., Masina O.N., Petrov A.A. Razvitie instrumental'nogo obespechenija otechestvennoj vychislitel'noj platformy «Jel'brus 801-PC» v zadachah nejrosetevogo modelirovanija nelinejnyh dinamicheskih sistem. Nelinejnyj mir. 2021. T. 19. №1. S. 19–28 (In Russian).
10. Glova V.I., Anikin I.V., Katasjov A.S, Kriviljov M.A., Nasyrov R.I. Mjagkie vychislenija.  Kazan': Izd-vo Kazanskogo gos. tehn. un-ta. 2010 (In Russian).
11. Rodzina O. N. Problemno-orientirovannye algoritmy mjagkih vychislenij. Cheboksary: ID «Sreda». 2020. (In Russian).
12. Kuvajskova Ju.E. Ispol'zovanie nechetkoj logiki dlja diagnostiki tehnicheskogo sostojanija ob’ekta. Izvestija Samarskogo nauchnogo centra RAN. 2018. № 4(3). S. 487–490 (In Russian).
13. Kuvajskova Ju.E., Aleshina A.A. Tehnicheskaja diagnostika ob’ektov s ispol'zovaniem metodov nechetkoj logiki. Radiotehnika. 2017. № 6. S. 32–34. (In Russian).
14. Kuvayskova Y.E. The Prediction algorithm of the technical state of an object by means of fuzzy logic inference models. Procedia Engineering. 2017. V. 201. P. 767–772.
15. Katasjov A.S., Ahatova Ch.F. Gibridnaja nejronechetkaja model' intellektual'nogo analiza dannyh dlja formirovanija baz znanij mjagkih jekspertnyh diagnosticheskih sistem. Nauka i obrazovanie. Nauchnoe izdanie MGTU im. N.Je. Baumana. Jelektronnyj zhurnal. 2012. № 12. S. 486–504 (In Russian).
16. Katasjov A.S. Matematicheskoe i programmnoe obespechenie formirovanija baz znanij mjagkih jekspertnyh sistem diagnostiki sostojanija slozhnyh ob’ektov. Kazan': GBU «Respublikanskij centr monitoringa kachestva obrazovanija». 2013 (In Russian).
17. Jegov E.N., Jarushkina N.G., Jashin D.V. Nechetkoe modelirovanie i geneticheskaja optimizacija vremennyh rjadov v intellektual'noj sisteme tehnicheskoj diagnostiki. Radiotehnika. 2016. № 9. S. 64–71 (In Russian).
18. Mironov A.A., Pavljukov A.Je. Sredstva realizacii avtomatizirovannoj sistemy kontrolja i monitoringa nagreva buksovyh uzlov. Control Engineering Rossija. 2016. № 3(63). S. 53–59 (In Russian).
19. Cherepov O.V., Pranov V.A. Informacionnye tehnologii i sistemy kompleksnogo kontrolja tehnicheskogo sostojanija vagonov. Metodich. ukazanija. Ekaterinburg: UrGUPS. 2016 (In Russian).
20. Filippov A.A., Moshkin V.S., Gus'kov G.Ju., Jarushkina N.G. Primenenie nechetkoj bazy znanij problemnoj oblasti v zadache poiska arhitekturno podobnyh programmnyh proektov. Nechetkie sistemy i mjagkie vychislenija. 2017. T. 12. Vyp. 2. S. 107–120 (In Russian).