Artificial Intelligence Technologies for Evaluation and Prediction of the Technical Condition of Railway Automation and Telemechanic Devices

Vadim Nadezhkin; Snezhana Nadezhkina; Abdulla MUSIN

doi:10.20295/1815-588X-2025-2-484-491

UDC

656.259.12

ARTIFICIAL INTELLIGENCE TECHNOLOGIES FOR EVALUATION AND PREDICTION OF THE TECHNICAL CONDITION OF RAILWAY AUTOMATION AND TELEMECHANIC DEVICES Artificial Intelligence Technologies for Evaluation and Prediction of the Technical Condition of Railway Automation and Telemechanic Devices

АА Аа

Published in Proceedings of Petersburg Transport University · Pages 484–491 · Rubric: PROBLEMATIC OF TRANSPORT SYSTEM

DOI: https://doi.org/10.20295/1815-588X-2025-2-484-491

Received: 18.06.2025 Accepted: 19.06.2025 Published: 19.06.2025

Authors

Vadim Nadezhkin

Snezhana Nadezhkina

Abdulla MUSIN

Vadim Nadezhkin

Academic degree: candidate of technical sciences

Volga State Transport University Associate Professor · Automation, Telemechanics and Communications in Railway Transport · Russian Federation · Samara

Snezhana Nadezhkina

Volga State Transport University Teacher · Department of Automation, Telemechanics and Communication in Railway Transport · Russian Federation · Samara

Abdulla MUSIN

Volga State Transport University Student · Russian Federation · Samara

ABSTRACT

Purpose: To assess the impact of technical diagnostics and monitoring (TDM) systems on the recoverability of railway automation and telemechanic (RAT) devices. To investigate the shortcomings of modern diagnostic technologies with regard to their impact on increased operational costs and transportation safety risks. To justify the necessity of monitoring system modernization based on predictive analytics for transition from scheduled preventive maintenance (SPM) to intelligent methods of equipment condition management. Methods: Analysis of the successful implementation of domestic systems, such as the hardware and software complex of dispatching control (HSC DC), including their functionalities for data collection, pre-failure state detection, and automated fault identification. A study of graphical data reflecting the dynamics of rail circuit parameters for identifying deviations from the standard operation preceding failures. Comparing traditional SPM methods with modern approaches that are based on predictive analytics and machine learning. Results: A number of significant deficiencies in current monitoring systems have been identified. These include the occurrence of false alarms and inadequate performance in handling current workloads. The capacity of predictive analytics to detect subtle parameter changes, such as voltage fluctuations and temperature deviations, has been demonstrated to be indicative of developing pre-failure conditions. As demonstrated by the rail circuit graphs, the typical phases can be observed in the form of steady operation and the appearance of pre-failure anomalies, as well as failure states. Practical significance: The feasibility of enhancing TDM through the implementation of predictive analytics and digital modelling was demonstrated, with the potential to help minimize emergencies, optimize maintenance via targeted repairs, and reduce operational costs. The modernization of RAT systems is imperative for enhancing the reliability and safety of railway infrastructure, particularly in the context of ncreasing freight traffic and operational intensity. The findings of the study can be used to develop early failure warning systems and update regulatory frameworks in technical diagnostics.

KEYWORDS

Technical diagnostics, monitoring of RAT devices, predictive analytics, equipment recoverability, false alarms, railway automation and telemechanics, intelligent monitoring systems, failures of rail circuits

Text

Text (PDF)

Read Download

1. Avtomatika, svyaz', informatika: nauchno-teoreticheskiy i proizvodstvenno-tehnicheskiy zhurnal. — M.: 2008/09.

2. Kaynov V. M. Doklad nachal'nika departamenta avtomatiki i telemehaniki OAO «RZhD» na chetvertoy ISSN 1815-588H. Izvestiya PGUPS 2025/2 Problematika transportnyh sistem 489 mezhdunarodnoy nauchno-prakticheskoy konferencii «Avtomatika i telemehanika na zheleznodorozhnom transporte» / V. M. Kaynov.

3. Tarasov E. M. K voprosu avtomatizacii tehnicheskoy diagnostiki i monitoringa / E. M. Tarasov, A. E. Tarasova, V. A. Nadezhkin // Nauka i obrazovanie transportu. — 2022. — № 1. — S. 362–364.

4. Sepetyy A. A. Tehnologiya diagnostirovaniya i monitoringa ustroystv ZhAT na urovne distanciy avtomatiki i telemehaniki / A. A. Sepetyy, A. E. Fedorchuk // Informatizaciya i svyaz'. — 2013. — № 2. — S. 71–76.

5. Tarasov E. M. Diagnostirovanie v zhiznennom cikle izoliruyuschih stykov rel'sovyh cepey / E. M. Tarasov, V. A. Nadezhkin // Transport: nauka, tehnika, upravlenie. Nauchnyy informacionnyy sbornik. — 2024. — № 2. — S. 45–50. — DOI:https://doi.org/10.36535/0236-1914-2024-02-6.

6. Efanov D. V. Osobennosti informacionnogo sopryazheniya sistem monitoringa inzhenernyh konstrukciy i sooruzheniy s sistemami upravleniya dvizheniem poezdov / D. V. Efanov, E. M. Mihaylyuta // Problemy bezopasnosti na transporte: materialy HIII mezhdunarodnoy nauchno-prakticheskoy konferencii, posvyaschennoy Godu kachestva. V 2-h chastyah, Gomel', 21–22 noyabrya 2024 goda. — Gomel': Belorusskiy gosudarstvennyy universitet transporta, 2024. — S. 211–213.

7. Mashtakov N. S. Prediktivnaya analitika: iz istoricheskih dannyh k strategicheskomu prognozirovaniyu / N. S. Mashtakov, P. S. Chasov // Original'nye issledovaniya. — 2023. — T. 13. — № 12. — S. 61–66.

8. Orlov A. Mashinnoe obuchenie dlya Bol'shih Dannyh / A. Orlov // Otkrytye sistemy. SUBD. — 2016. — № 1. — S. 26–27.

9. Efanov D. V. Funkcional'nyy kontrol' i monitoring ustroystv zheleznodorozhnoy avtomatiki i telemehaniki: monografiya / D. V. Efanov. — SPb.: FGBOU VO PGUPS, 2016. — 171 s.

PDF Text JATS XML

Editor-in-chief

Oleg S. Valinskiy

Deputy Editor-in-chief

Dmitry Kurilkin

It@pgups.ru

Science editor

Andrey Evstaf'ev

elt@pgups.ru

Edition

zhurnala P. Redakciya

izvestia@izvestiapgups.org

2561

downloads

GOST

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 Transport University. 2025. no. 2. pp. 484-491. DOI: https://doi.org/10.20295/1815-588X-2025-2-484-491. (Date of access 09.09.2026).

MLA

Vadim Nadezhkin, 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 Transport University 22.2 (2025): 484-491. DOI: https://doi.org/10.20295/1815-588X-2025-2-484-491.

APA

Nadezhkin V. A., Nadezhkina S. A., MUSIN A. R. (2025). Artificial Intelligence Technologies for Evaluation and Prediction of the Technical Condition of Railway Automation and Telemechanic Devices. Proceedings of Petersburg Transport University, 22(2), 484-491. https://doi.org/10.20295/1815-588X-2025-2-484-491

Chicago

Vadim Nadezhkin, 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 Transport University 22, no. 2 (2025): 484-491. https://doi.org/10.20295/1815-588X-2025-2-484-491.

WIKI

{{cite journal | author = Nadezhkin V. A., Nadezhkina S. A., MUSIN A. R. | title = Artificial Intelligence Technologies for Evaluation and Prediction of the Technical Condition of Railway Automation and Telemechanic Devices | journal = Proceedings of Petersburg Transport University | year = 2025 | volume = 22 | issue = 2 | pages = 484-491 | doi = 10.20295/1815-588X-2025-2-484-491 }}

Copy

Export: BibTeX EndNote RefMan RusMARC

ARTIFICIAL INTELLIGENCE TECHNOLOGIES FOR EVALUATION AND PREDICTION OF THE TECHNICAL CONDITION OF RAILWAY AUTOMATION AND TELEMECHANIC DEVICES Artificial Intelligence Technologies for Evaluation and Prediction of the Technical Condition of Railway Automation and Telemechanic Devices

Confirmation