Russian Federation
The article is devoted to solving the urgent problem of data fragmentation during the operation of autonomous refrigerated wagons (ARVs) on the Russian Railways railway network. The key task is to develop the architecture of a single digital platform, automate the information field generated by on-board telematics systems (data on temperature, location, equipment operation parameters), and seamlessly integrate it with data from corporate automated control systems JSC Russian Railways and integration with internal systems of operational, commercial and technical accounting. Objective: to develop a unified ARV digital platform that ensures the formation of a common source of reliable data, cargo safety and reliability of ARV equipment. Materials and methods: the paper uses system analysis methods for existing solutions in telematics of refrigerated rolling stock. The imperfections of the information exchange between the systems and the formalization of the platform requirements are revealed. The principles of service-oriented architecture (SOA) were used to design the architecture of a single digital ARB platform. The concepts of the Industrial Internet of Things (IIoT) were applied to collect data from various systems, and the rules of hybrid data management (“single data layer” – Data Fabric) were applied to integrate and process this data. Results: the implementation of the proposed platform will help overcome the problems of information fragmentation and delay, optimize logistics processes, create a single source of reliable data, implement the transition to maintenance based on the actual condition and improve train safety. Practical significance: information from on-board ARV systems and from corporate automated control systems of Russian Railways comes incoherently, which requires manual data comparison and, as a result, delayed response to incidents, which leads to damage to cargo. The results of the work will significantly increase the efficiency of using the refrigerated fleet, ensure the safety of goods, reduce operating costs and strengthen the competitive position of rail transport in the market of transportation of perishable products.
autonomous refrigerated wagon, telematics, data integration, predictive analytics
1. GOST R 58664-2019. Uslugi na zheleznodorozhnom transporte. Perevozka skoroportyaschihsya gruzov. Obschie trebovaniya k kachestvu. URL: https://internet-law.ru/gosts/gost/72246/ (data obrascheniya: 01.12.2025).
2. The International Union of Railways. Best Practices for Perishable Goods Transport by Rail. 3rd ed. Paris, UIC Publications. 2022. 134 p.
3. Pravila perevozok zheleznodorozhnym transportom skoroportyaschihsya gruzov (utv. prikazom Mintransa Rossii ot 04.03.2019 № 66). URL: https://base.garant.ru/72265752/ (data obrascheniya: 30.10.2025).
4. Shevchenko A. V. Sovremennye resheniya dlya avtonomnyh refrizheratornyh vagonov modeli 16- 5213, obespechivayuschie povyshenie ih ekspluatacionnoy nadezhnosti i rabotosposobnosti // Trudy Rostovskogo gosudarstvennogo universiteta putey soobscheniya. 2025. № 1 (70). S. 126–131. EDN AMPSPG
5. Efanov D. V., Smirnov A. A. Sistema monitoringa ustroystv zheleznodorozhnoy avtomatiki na osnove promyshlennogo «Interneta veschey» // Mir transporta. 2020. T. 18, № 6. S. 118–134.
6. Lihova O. A., Kuz'mina K. A., Zholondkovskiy P. S. Tehnologiya blokcheyn v logistike i upravlenii cepyami postavok: opisanie primeneniya i prognoz razvitiya // Novoe slovo v nauke: strategii razvitiya: sbornik materialov V Mezhdunarodnoy nauchno-praktichskoy konferencii Cheboksary, 2018. S. 243–250.
7. Kafka: The Definitive Guide: Real-Time Data and Stream Processing at Scale / G. Shapira [et al.] USA: O’Reilly Media, 2021. Rp. 332–334.
8. Gartner Research. Innovation Insight: Data Fabric Architectures Are Key to Modern Data Management. 2023. URL: https://www.gartner.com/en/ documents/4018889 (data obrascheniya: 01.12.2025).
9. Prediktivnaya analitika v zheleznodorozhnoy logistike: matrica tehnologicheskih resheniy i strategiya vnedreniya / E. S. Gavrilyuk, T. N. Bikmulina, D. A. Popov, O. S. Hamdamov // Estestvenno-gumanitarnye issledovaniya. 2025. № 3 (59). S. 99– 104.
10. Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. 1997. Vol. 9, no. 8. Pp. 1735–1780. 11. Chen T., Guestrin C., Boost X. G. A Scalable Tree Boosting System // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ‘16). 2016. Pp. 785–794.
11. Kachalov D. L., Mishustin A. V., Farhadov M. P. Sovremennye metody obrabotki bol'shih dannyh v krupnomasshtabnyh sistemah. Matematicheskie modeli sovremennyh ekonomicheskih processov, metody analiza i sinteza ekonomicheskih mehanizmov // Aktual'nye problemy i perspektivy menedzhmenta organizaciy v Rossii: materialy XI Vserossiyskoy nauchno-prakticheskoy konferencii (Samara, 24–28 aprelya 2017 goda). Vyp. 11. Samara: Samarskiy nauchnyy centr RAN, 2017. S. 65– 71. EDN YMZHKD
12. Software-Defined Networking: A Comprehensive Survey / D. Kreutz [et al.] // Proceedings of the IEEE. 2015. Vol. 103, no. 1. Pp. 14–76.
13. Blockchain Technology in the Energy Sector: A Systematic Review of Challenges and Opportunities / M. Andoni [et al.] // Renewable and Sustainable Energy Reviews. 2019. Vol. 100. Pp. 143–174.
14. Shinkaruk A. S., Kulikov M. Yu., Baryshnikov A. V. Sovershenstvovanie proizvodstvennyh i upravlencheskih processov pri remonte i tehnicheskom obsluzhivanii passazhirskih vagonov s ispol'zovaniem «cifrovyh dvoynikov» // Transportnoe mashinostroenie. 2024. № 12 (36). S. 70– 77. DOI:https://doi.org/10.30987/2782-5957-2024-12-70-77. EDN ENMKIC
