Russian Federation
Russian Federation
Purpose: To develop a “Digital Twin”-based simulation model for an electric locomotive electrical part for predicting electric locomotive parameters and scenarios (including emergencies) based on en route measurement system data, as well as to define model-based real-time valid parameters within a prescriptive analytics framework. Methods: Methods of computer simulation modeling in Matlab Simulink environment, C# programming, mathematical statistics and electric traction theory were used to solve the set tasks. Results: The simulation digital model of an electric freight locomotive electrical part in Matlab Simulink based on “Digital Twin” technology has been developed using the on-board measurement system data en route. Validation of the developed simulation model of the 2ES6 electric locomotive electrical part based on retrospective data obtained from processing the RPDA records has been carried out. Fault simulation in the electrical part of the 2ES6 electric locomotive with subsequent fault elimination has been performed, with graphs of calculated and experimental time dependencies obtained and presented. Practical significance: The research results obtained, namely the “Digital Twin”-based simulation models of the electric locomotive electrical part can be used for generating different train movement data for computer learning model to predict the electric locomotive parameters and scenarios (including emergencies) within the framework of the developed prescriptive system of automatic electric locomotive fault prevention en route.
Digital twin, electric locomotive, simulation model, faults, computer learning
1. Pires F. Digital Twin in Industry 4.0: Technologies, Applications and Challenges / F. Pires, A. Cachada, J. Barbosa et al. // IEEE 17th International Conference on Industrial Informatics (INDIN). — Helsinki, Finland, 2019. — Pp. 721–726. — DOI:https://doi.org/10.1109/INDIN41052. 2019.8972134.
2. Errandonea I. Digital twin for maintenance: A literature review / I. Errandonea, S. Beltrán, S. Arrizabalaga // Computers in Industry. — 2020. — Iss. 123. — DOI:https://doi.org/10.1016/j.compind.2020.103316.
3. Ghaboura S. Digital Twin for Rail-way: A Comprehensive Survey / S. Ghaboura, R. Ferdousi, F. Laamarti et al. // IEEE Access. — 2023. — Iss. 11. — Pp. 120237–120257. — DOI:https://doi.org/10.1109/ACCESS.2023.3327042.
4. Donato L. Towards AI-assisted digital twins for smart railways: preliminary guideline and reference architecture / L. De Donato, R. Dirnfeld, A. Somma et. al. // Journal of Reliable Intelligent Environments. — 2023. — Iss. 9. — Pp. 303–317. DOI:https://doi.org/10.1007/s40860-023-00208-6.
5. Lakin I. K. Ispol'zovanie tehnologii «Cifrovoy dvoynik» pri upravlenii remontom lokomotivov / I. K. Lakin, A. P. Semenov // Sovremennye tehnologii. Sistemnyy analiz. Modelirovanie. — 2019. — № 3(63). — S. 89–98. — DOI:https://doi.org/10.26731/1813- 9108.2019.3(63).89–98.
6. Adadurov A. S. Obschee principy postroeniya prediktivnoy sistemy diagnostiki novogo elektropoezda ES2G «Lastochka» i pervye eksperimental'nye dannye / A. S. Adadurov, V. I. Fedorova, A. M. Boyko // Nacional'naya Associaciya Uchenyh. — 2022. — № 75-2. — S. 14–22.
7. Adadurov A. S. Apparatno-programmnyy kompleks preskriptivnoy sistemy diagnostiki dlya elektropoezda «Lastochka» / A. S. Adadurov, V. I. Fedorova, A. A. Perevyazkin // Avtomatika, svyaz', informatika. — 2023. — № 2. — S. 16–19.
8. Abolmasov A. A. Sovershenstvovanie metodov diagnostirovaniya elektricheskih mashin lokomotivov po dannym mikroprocessornyh sistem upravleniya / A. A. Abolmasov, D. O. Lisin, V. A. Mel'nikov // Sovremennye tehnologii. Sistemnyy analiz. Modelirovanie. — 2019. — № 3(63). — S. 69–75. — DOI:https://doi.org/10.26731/1813-9108.2019.3(63).69-75.
9. Habarov R. A. Prediktivnaya diagnostika tehnicheskogo sostoyaniya detaley, agregatov i sistem podvizhnogo sostava / R. A. Habarov, M. M. Raevskiy // Ekspluatacionnaya nadezhnost' lokomotivnogo parka i povyshenie effektivnosti tyagi poezdov: materialy VII Vserossiyskoy nauchno-tehnicheskoy konferencii s mezhdunarodnym uchastiem. — Omsk: Omskiy gos. un-t putey soobscheniya, 2022. — S. 217–227.
10. Repeshko N. A. Principy raboty «Umnogo lokomotiva» / N. A. Repeshko // Transport: nauka, obrazovanie, proizvodstvo: sbornik trudov Mezhdunarodnoy nauchnoprakticheskoy konferencii. — Rostov-na-Donu: Rostovskiy gos. un-t putey soobscheniya, 2018. — T. 2. — S. 171–174.
11. Ivankov D. O. Principy raboty «Umnogo lokomotiva» / D. O. Ivankov, A. A. Ponyatov // Tehnika i tehnologii nazemnogo transporta: materialy IV Mezhdunarodnoy studencheskoy nauchno-prakticheskoy konferencii. — Nizhniy Novgorod: Filial federal'nogo gosdarstvennogo byudzhetnogo obrazovatel'nogo uchrezhdeniya vysshego obrazovaniya «Samarskiy gos. un-t putey soobscheniya» v g. Nizhnem Novgorode, 2022. — S. 282–287.
12. Budaev A. A. K voprosu ob avtomatizacii processov diagnostiki tehnicheskogo sostoyaniya i ekspluatacionnyh pokazateley elektropodvizhnogo sostava na osnove tehnologii «cifrovoy dvoynik» / A. A. Budaev // Innovacionnye proekty i tehnologii v obrazovanii, promyshlennosti i na transporte: materialy nauchnoy konferencii, posvyaschennoy Dnyu rossiyskoy nauki. — Omsk: Omskiy gos. un-t putey soobscheniya, 2024. — S. 94–99.
13. Budaev A. A. Principy postroeniya imitacionnyh modeley elektrovozov po tehnologii «cifrovoy dvoynik» / A. A. Budaev, A. N. Solov'ev // Issledovanie i razvitie rel'sovogo i avtomobil'nogo transporta: cbornik trudov Mezhdunarodnoy nauchno-prakticheskoy konferencii. — Ekaterinburg: Ural'skiy gosudarstvennyy universitet putey soobscheniya, 2024. S. 39–43.
