Algorithm for Digitalising Technological Schedules of Train Processing Operations at Railway Stations

Changing volumes of cargo transportation necessitate accelerated movement of cargo flows, including by modifying the technology of trains’ transit through the railway infrastructure. In such conditions, it is necessary to create digital models, the purpose of which is to reproduce the work of the original. The results obtained following the operation of the digital model will serve as a rationale for further development of options for operation of the simulated object, aimed at fulfilling the up-and-coming indicators of operation of railway transport.

In this regard, as part of the study, an algorithm for digitalising technological schedules of train processing operations. The purpose of the developed algorithm is to build software conform to its structure that ensures operational automated accounting of the technology of operations of original railway facilities in the conditions of transforming analogue information into its digital type. An algorithm based on a machine learning model was created using program, structural and system methods. The accuracy of determining the input technological operation is assessed by the purity of the information node, and more than 120 technological schedules of train processing operations at various railway stations were digitalised during the experiment.

1. Chigrin, N. S., Borisenkov, E. S., Grefenstein, A. P. Characteristics of the problems of cargo transportation by rail on Eastern direction [In Russian]. Teсhnique and technology of transport, 2023, Iss. 4 (31). EDN: ZKCJKE.

2. Yanev, Zh. About the structure of a digital model of a railway station [IN Russian]. Transport business of Russia, 2024, Iss.3, pp. 186–190. EDN: OJZHAY.

3. Kostenko, V. V., Bogdanovich, D. E. Practical application of a digital model for a railway station reconstruction feasibility study. Bulletin of scientific research results, 2021, Iss. 1, pp. 61–73. DOI: 10.20295/2223-9987-2021-1-61-73.

4. Golovnich, A. K. Determining the concept of «digital twin» in 3D models of railway stations [Determinatsiya ponyatiya «tsifrovoi dvoinik» v SD-modelyakh zhheleznodorozhnykh stantsii]. Transport technician: education and practice, 2023, Iss. 4 (2), pp. 184–192. DOI: https://doi.org/10.46684/2687-1033.2023.2.184-192.

5. Erofeev, A. A. Normative and reference information in the train formation system [Normativno-spravochnaya informatsiya v sisteme poezdoobrazovaniya]. Bulletin of Belarusian State University of Transport: Science and Transport, 2007, Iss. 1–2 (14–15), pp. 54–59. EDN: YSDPLF.

6. Lysikov, M. G., Olshansky, E. N., Rozenberg, E. N., Rozenberg, I. N. Patent No. 2723051 C1 Russian Federation, IPC B61B 1/00. Operational control system for transit train traffic: No. 2019131595: application 08.10.2019: published 08.06.2020. Applicant: Joint-Stock Company «Research and Design Institute of Informatization, Automation and Communications in Railway Transport». EDN: UTJFTN.

7. Kostenko, O. A., Parkhomenko, N. V. Principles of constructing a software digital model of a marshalling yard and its study on a digital computer [Printsipy postroeniya programmnoi tsifrovoi modeli sortirovochnoi stantsii i ee issledovanie na ECVM] [In Russian]. Moscow, Nauka publ., 1967, pp. 118–133.

8. Khomonenko, A., Khalil, M. M. Quantum computing in controlling railroads. In: E3S Web of Conferences: International Scientific Conference Transport Technologies in the 21st Century (TT21C-2023) «Actual problems of Decarbonization of Transport and Power Engineering: Ways of Their Innovative Solution», Rostov-on-Don, Russia, 05–07 April 2023, Vol. 383. A. Bieliatynskyi and A. N. Guda (Eds.). Rostov-on-Don, Russia: EDP Sciences, 2023, art. 01010. DOI: https://doi.org/10.1051/e3sconf/202338301010.

9. Lakemond, N., Holmberg, G., Pettersson A. Digital Transformation in Complex Systems. IEEE Transactions on Engineering Management, 2024, Vol. 71, рр. 192–204. DOI: 10.1109/tem.2021.3118203.

10. Potyupkin, A. Yu., Chechkin, A. V. Artificial intelligence based on information and system redundancy [Iskusstvenniy intellekt na baze informatsionno-sistemnoi izbytochnosti]. Moscow, Scientific and Publishing Center INFRA-M LLC, 2019, 384 p. ISBN 978-5-907064-44-7.

11. Zherdeva, M. V., Artyushenko, V. M. Stemming and lemmatization in lucene.net. Bulletin of the Moscow State Forest University – Forest Bulletin, 2016, Vol. 20, Iss. 3, pp. 131–134. EDN: WKNMTN.

12. Chelyshev, E. A., Otsokov, Sh. A., Raskatova, M. V., Shchegolev, P. Comparing classification methods for news texts in Russian using machine learning algorithms. Proceedings in Cybernetics, 2022, Iss. 1 (45), pp. 63–71. DOI: 10.34822/1999-7604-2022-1-63-71.

13. Oskina, K. A. Optimisation of TF-IDF text classification method by introducing additional weighting coefficients. Bulletin of Moscow State Linguistic University. Humanities, 2016, Iss. 15 (754), pp. 175–187. EDN: OPWIAU.

14. Polyakova, A. S., Lipinsky, L. V., Poplauhina, M. A. [et al.] Certificate of state registration of a computer program No. 2021681722 Russian Federation. An intelligent system for solving natural language analysis problems based on the text vectorization procedure using machine learning models, a genetic algorithm and the TF-IDF method: No. 2021681149: application 17.12.2021: published 24.12.2021; applicant: Federal State Budgetary Educational Institution of Higher Education «Siberian State University of Science and Technology named after Academician M. F. Reshetnev». EDN: GVNFKK.

15. Disha, R. A., Waheed, S. Performance analysis of machine learning models for intrusion detection system using Gini Impurity-based Weighted Random Forest (GIWRF) feature selection technique. Cybersecurity, 2022, Vol. 5, Iss. 1, pp. 1–22. DOI: 10.1186/s42400-021-00103-8.

16. Demetriou, D., Michailides, C., Onoufriou, T., Papanastasiou, G. Coastal zone significant wave height prediction by supervised machine learning classification algorithms. Ocean Engineering, 2021, Vol. 221, art. 108592. DOI: 10.1016/j.oceaneng.2021.108592.