Text mining of the DU-46 inspection log using frequency-based text processing methods
https://doi.org/10.21683/1729-2646-2026-26-1-12-20
Abstract
For making well‑founded decisions on the elimination of failures and malfunctions occurring in railway infrastructure facilities, prompt access to information on previously identified faults and the dynamics of the irresolution is essential. Inspection logs such as DU‑46 contain valuable data on the condition of these facilities (tracks, turnouts, signals, power supply, contact lines, etc.); however, they are hardly used in practice when analyzing the causes of newly emerging failures.
Aim. To develop an algorithm for processing DU‑46 log records that allows operators, up on request, to obtain information on previous malfunctions or maintenance activities on specific infrastructure objects.
Methods. Text preprocessing, lemmatization using M. Korobov’s morphological analyzer, frequency‑based text analysis, TF–IDF, L2 normalization, cosine similarity calculation, and result sorting.
Result. A prototype application has been developed that enables search for relevant records and displays a similarity metric between the query and the retrieved fragments, which, among other things, may serve as a recommendatory function for determining the causes of failures.
Conclusion. The use of operation al inspection logs in combination with text mining methods can form the basis for building recommendation systems and decision support systems in the maintenance of railway infrastructure facilities.
About the Author
V. A. Kanarsky
Far Eastern State Transport University
Russian Federation
Russian Federation
Vadim A. Kanarsky, Candidate of Technical Sciences, Senior Lecturer, Acting Head of the Department of «Automated, Telecommunication and Electrical Engineering Systems»
Khabarovsk
References
1. Papirovskaya L.I., Frantasov D.N., Chasovskikh E.A., Lipatova M.N. [Information technologies in railway transport: a textbook: in 3 parts. Part 2: Information technology in the train traffic management system]. Samara: SamGUPS; 2020. (in Russ.)
2. Nadezhkin V.A., Nadezhkina S.A., Musin A.R. Artificial Intelligence Technologies for Evaluation and Prediction of the Technical Condition of Railway Automation and Telemechanic Devices. Proceedings of Petersburg State Transport University, 2025, vol. 22, iss. 2, pp. 484–491. (In Russian) DOI: 10.20295/1815-588X-2025-2-484-491. (in Russ.)
3. Mintus A.N., Kucherenko S.I., Gerasina I.G. Development of a predictive analytics system for the technical maintenance of signaling, centralization, and blocking devices. Sbornik nauchnykh trudov Donetskogo instituta zheleznodorozhnogo transporta 2025;1(76):59-64. EDN: TBRCBY. (in Russ.)
4. Bushuev S.V., Rozhkin B.V., Bludov A.A., Golochalov N.S. Analysis of the station’s track development load (according to the archives of railway switches and signal centralized systems). Herald of the Ural State University of Railway Transport 2021;2(50):30-44. (in Russ.)
5. Andronov I.A., Sidorenko V.G. Analysis of modern approaches to building electronic document management systems. In: Intelligent Transportation Systems: Proceedings of the IV International Research and Practice Conference. Moscow; May 22, 2025. Moscow: Russian University of Transport (MIIT); 2025. Pp. 42-48. (in Russ.) DOI: 10.30932/9785002587582-2025-42-48 EDN: EWUCGV
6. Sundaram S., Zeid A. Technical language processing for Prognostics and Health Management: applying text similarity and topic modeling to maintenance work orders. Journal of Intelligent Manufacturing 2024;36:1637–1657. DOI: 10.1007/s10845-024-02323-4.
7. [Manual for ensuring train traffic safety in the course of track work operations: JSC RZD manual no. TSH-530: approved by Order of JSC RZD dated 20.09.2011 no. 2055r. (as amended on 18.09.2020)]. (accessed: 22.08.2025). Available at: https://itt-54.ru/wp-content/uploads/2023/12/Инструкция-ОАО-РЖД-Инструкция-по-обеспечению-БД-N-ЦШ-530-11от-20.09.-2011-г.-№-2055р. pdf. (in Russ.)
8. Rusakov A.M., Polyanskaya P.A. Testing software libraries for lemmatization of texts in Python. Naukosfera 2023;11-1:210-218. DOI: 10.5281/zenodo.10136822 EDN: EJFGZF. (in Russ.)
9. Korobov M. Morphological Analyzer and Generator for Russian and Ukrainian Languages. In: International Conference on Analysis of Images, Social Networks and Texts / Communications in Computer and Information Science 2015;320–332. DOI: 10.1007/978-3-319-26123-2_31. (in Russ.)
10. Salton G., Wong A., Yang C.S. A vector space model for automatic indexing. Communications of the ACM 1975;18(11):613–620. DOI:10.1145/361219.361220.
11. TfidfTransformer. scikit-learn developers. (accessed: 23.08.2025). Available at: https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfTransformer.html.
12. [On the approval of the strategic direction in the field of digital transformation of the transportation industry of the Russian Federation to 2030: Decree of the Government of the Russian Federation dated 03.11.2023 no. 3097r. Ministry of Transport of the Russian Federation]. (accessed: 08/26/2025). Available at: https://mintrans.gov.ru/documents/2/12953. (in Russ.)
13. Zudina A. [Another paperless technology]. Gudok: Volzhskaya magistral 2023;9. (accessed 08/24/2025). Available at: https://gudok.ru/zdr/168/?page_print_=Y&ID=1629697. (in Russ.)
Review
For citations:
Kanarsky V.A. Text mining of the DU-46 inspection log using frequency-based text processing methods. Dependability. 2026;26(1):12-20. (In Russ.) https://doi.org/10.21683/1729-2646-2026-26-1-12-20
Views:
246
JATS XML
ISSN 1729-2646 (Print)
ISSN 2500-3909 (Online)
ISSN 2500-3909 (Online)
Email this article 