M.A. Ludagovskaya1, N.A. Antonov2, M.A. Kabanov3, S.V. Chernomordov4

1 Russian University of Transport (MIIT) (Moscow, Russia)

2-4 Bunin Yelets State University (Yelets, Russia)

1 m.ludagovskaya@gmail.com; 2 nikolayantonov888@yandex.ru; 3 nicsor2010@yandex.ru; 4 chernomor96@list.ru

The analysis of the prospects for the use of intelligent data processing methods for monitoring of transport systems, the development of neural network modeling and machine learning methods for automated monitoring tools are urgent problems. The article is devoted to the issues related to the improvement of neural network methods for processing data on the technical state of transport infrastructure elements and using artificial intelligence technologies in the development and implementation of monitoring tools. The objectives of the work are to develop an approach to improving intelligent data processing methods for monitoring elements of transport infrastructure based on neural network modeling and machine learning, to develop the structure of an intelligent monitoring system, and to analyze the possibilities of using hybrid neural networks. The aspects of the development and improvement of an intellectual monitoring system of a transport interchange hub within the framework of the functioning of safety control systems and passenger traffic management are considered. A description of the structure of this intelligent system is proposed, the features of the data mining and modeling support unit are presented, a neural network approach to data analysis is described. An approach to data mining in automated dispatch control systems based on the application of a data clustering algorithm taking into account expert knowledge is considered. The possibilities of using hybrid neural networks to assess the state of the upper structure of the railway track are characterized. A model of a hybrid neural network with exponential smoothing is considered, combining the capabilities of recurrent and precise neural networks. The results can be used in the problems of computer modeling of technical systems, in the problems of creating instrumental support for monitoring systems of transport infrastructure elements, as well as in problems related to the use of neural network algorithms and machine learning.

Ludagovskaya M.A., Antonov N.A., Kabanov M.A., Chernomordov S.V. Improvement of intelligent data processing methods for monitoring elements of transport infrastructure. Nonlinear World. 2023. V. 21. № 4. P. 15-23. DOI: https://doi.org/10.18127/j20700970-202304-02 (In Russian)

1. Dulhare U.N., Bin Ahmad K.A., Ahmad K. Machine Learning and Big Data: Concepts, Algorithms, Tools and Applications. Wiley. 2020.
2. Antamoshin A.N, Bliznova O.V., Bobov A.V. Intellektual'nye sistemy upravlenija organizacionno-tehnicheskimi sistemami. M.: RiS. 2016 (In Russian).
3. Kuzhelev P.D. Principy upravlenija transportom megapolisa. Nauka i tehnologii zheleznyh dorog. 2017. № 1(1). S. 27–33 (In Russian).
4. Druzhinina O.V., Masina O.N. Metody analiza ustojchivosti dinamicheskih sitsem intellektnogo upravlenija. M.: Izd. gruppa URSS. 2016 (In Russian).
5. Bajmul'din M.K., Javorskij V.V., Kochetkova L.I. Sovershenstvovanie dispetcherskogo upravlenija na gorodskom passazhirskom transporte s ispol'zovaniem avtomatizirovannyh informacionnyh sistem. Mezhdunarodnyj zhurnal prikladnyh i fundamental'nyh issledovanij. 2015. № 2. S. 214–216 (In Russian).
6. Moroz D.G., Titova S.S., Korotaev A.S. Osobennosti planirovanija i organizacii transportno-peresadochnyh uzlov. Nauka, tehnika i obrazovanie. 2017. №2 (32). S. 39–42 (In Russian).
7. Baranov L.A., Sidorenko V.G., Loginova L.N. Podhody k modelirovaniju passazhiropotokov v ramkah funkcionirovanija intellektual'noj sistemy upravlenija gorodskimi rel'sovymi transportnymi sistemami. Avtomatika na transporte. 2021. № 4.
   S. 539–564 (In Russian).
8. Druzhinina O.V., Ljudagovskaja M.A. Analiz dannyh i nejrosetevoe modelirovanie v diagnostike tehnicheskogo sostojanija zheleznodorozhnogo puti. Transport: nauka, tehnika, upravlenie. 2022. № 6. S. 19–25 (In Russian).
9. Nikitin A.B., Korolev M.Ju. Realizacija kompleksnoj avtomatizirovannoj sistemy dispetcherskogo upravlenija liniej metropolitena. Nauka i transport. Metropoliteny budushhego. Prilozhenie. k zhurnalu «Transport Rossijskoj Federacii». 2010. S. 39–41 (In Russian).
10. Lazarev V.A., Lazarev A.A., Lazareva N.V. Obrabotka dannyh arhivov kompleksnoj avtomatizirovannoj sistemy dispetcherskogo upravlenija. Problemy bezopasnosti i nadezhnosti mikroprocessornyh kompleksov. 2015. № 1. S. 66–69 (In Russian).
11. Druzhinina O.V., Korepanov Je.R., Petrov A.A., Makarenkova I.V., Maksimova V.V. Postroenie modeli generacii dannyh dlja reshenija zadach klassifikacii v diagnostike neispravnostej transportnyh sistem. Nelinejnyj mir. 2023. T. 21. № 3. S.16–26. DOI: https://doi.org/10.18127/j20700970-202303-02 (In Russian).
12. Druzhinina О.V., Masina O.N., Petrov А.А. Up-to-date software and methodological support for studying models of controlled dynamic systems using artificial intelligence. Lecture Notes in Networks and Systems (LNNS). Springer, 2021. V. 228. P. 670–681.
13. 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).
14. Hoseinzade E., Haratizadeh S. CNNpred: CNN-based stock market prediction using a diverse set of variables. Expert Syst Appl. 2019. V. 129. P. 273–285.
15. Platonov E.N., Prosvirin K.V. Prognozirovanie defektov verhnego stroenija zheleznodorozhnogo puti metodami mashinnogo obuchenija. Vestnik komp'juternyh i informacionnyh tehnologij. 2022. T. 19. № 2. S. 8–18 (In Russian).
16. Venkatraman A., Hebert M., Bagnell J.A. Improving multi-step prediction of learned time series models. In AAAI, 2015.
    P. 3024–3030.