Прогнозування технічного стану гальмівної системи тепловоза із застосуванням Марковського методу аналізу

O. V. Nevedrov; O. M. Gorobchenko; D. O. Zaika; V. S. Tereshchenko

doi:10.15802/stp2025/341685

Authors

O. V. Nevedrov National Transport University, Ukraine https://orcid.org/0000-0001-9347-0973
O. M. Gorobchenko National Transport University, Ukraine https://orcid.org/0000-0002-9868-3852
D. O. Zaika National Transport University, Ukraine https://orcid.org/0000-0003-0693-9580
V. S. Tereshchenko National Transport University, Ukraine https://orcid.org/0009-0006-7906-7284

DOI:

https://doi.org/10.15802/stp2025/341685

Keywords:

Markov chain, Markov process, control, forecasting, railway transport, locomotive, technical state, diagnostics

Abstract

Purpose. The article considers the issue of predicting the technical condition of the brake system of a diesel locomotive using the Markov analysis method. The purpose of the study is to build a mathematical model that allows for high-precision assessment of the current and future technical condition of the system based on statistical data. The proposed model allows for formalizing transitions between the technical states of serviceable, partially faulty, critical, and restored, which allows for effective maintenance planning. Methodology. To solve the problem, we will build
a mathematical model for predicting the technical condition of the brake system of a diesel locomotive based on
a discrete Markov process with four states: «serviceable», «partially faulty», «critical», «restored». This model allows for formalizing the probabilities of transitions between states at discrete points in time and assessing the dynamics of system degradation. The set of system states is represented as «serviceable» (normal functioning, no maintenance required), «partially faulty» (additional diagnostics or maintenance required), «critical state» (failure state requiring repair or replacement of a node – absorbing state), «restored» (after repair, the state is close to the initial state).
The structure of the transition matrix is constructed and the probability of transition from state to state is denoted. Finding. Based on the above data, the vector of the average time to absorption is constructed. Originality. The novelty of the work lies in obtaining the matrix N, which contains information about the expected number of times when the system, starting from a certain initial state, can transition or remain in an acceptable state until it enters an absorbing critical state. This makes it possible to identify weaknesses, namely frequent returns to a partially faulty state. It is also possible to determine the dynamics of the degradation of the brake system and, depending on it, optimize maintenance. Practical value. As part of the research, a formalized mathematical model of the locomotive brake system was constructed in the form of a discrete Markov process with four defined technical states.

References

Kharkivskyi natsionalnyi avtomobilno-dorozhnii universytet (2022). V Mizhnarodna naukovo-praktychna konferentsiia «Bezpeka na transporti – osnova efektyvnoi infrastruktury: problemy ta perspektyvy»: materialy konferentsii. Kharkiv, Ukraine. Retrieved from https://dl2022.khadi-kh.com/course/view.php?id=3829 (in Ukrainian)

Gorobchenko, O., & Zaika, D. (2024). Development of a Mathematical Model for Determining Traction and Energy Performance Indicators of a Maneuvering Locomotive. Collection of Scientific Works of the Ukrainian State University of Railway Transport, 208, 146-162.DOI: https://doi.org/10.18664/1994-7852.208.2024.308485 (in Ukrainian)

Keruvannia ryzykom. Metody zahalnoho otsiniuvannia ryzyku, 80 DSTU IEC/ISO 31010:2013 (2015). (in Ukrainian)

Lobatiuk, Yu. A., Mokin, O. B., & Mokin, B. I. (2018). Metody i zasoby tekhnichnoi diahnostyky halmivnoi systemy elektropoizda : monohrafiia. Vinnytsia: VNTU. (in Ukrainian)

Nevedrov, O. V. (2020). Development of Theoretical Fundamentals of Optimization and Quality Assessment of Traction Rolling Stock Management. Collection of Scientific Works of the State University of Infrastructure and Technologies Series «Transport Systems and Technologies», 36, 24-32.DOI: https://doi.org/10.32703/2617-9040-2020-36-3 (in Ukrainian)

Palchevskyi, B. O. (2019). Classification and Analysis of Technological Machines by the Nature of the Interaction of Their Working and Information Processes. Tekhnolohichni kompleksy, 1, 5-20.Retrieved from http://nbuv.gov.ua/UJRN/Tehkom_2019_1_3 (in Ukrainian)

Bodnar, B., Ochkasov, O., Petrenko, V., & Martishevskij, M. (2023). Implementing Intelligent Monitoring of the Technical Condition of Locomotive Hydraulic Transmissions. TRANSBALTICA XIII: Transportation Science and Technology, 726-736. DOI: https://doi.org/10.1007/978-3-031-25863-3_70 (in English)

Craig, B. A., & Sendi, P. P. (2002). Estimation of the transition matrix of a discrete‐time Markov chain. Health Economics, 11(1), 33-42. DOI: https://doi.org/10.1002/hec.654 (in English)

Dufour, F., & Prieto-Rumeau, T. (2024). Nash Equilibria for Total Expected Reward Absorbing Markov Games: The Constrained and Unconstrained Cases. Applied Mathematics & Optimization, 89(2), 34.DOI: https://doi.org/10.1007/s00245-023-10095-1 (in English)

Gorobchenko, O., Holub, H., & Zaika, D. (2024). Theoretical basics of the self-learning system of intelligent locomotive decision support systems. Archives of Transport, 71(3), 169-186.DOI: https://doi.org/10.61089/aot2024.gaevsp41 (in English)

Gorobchenko, O., Matsiuk, V., Holub, H., Gritsuk, I., & Nevedrov, O. (2024). Increasing the efficiency of opera-tion and management of railroad transport infrastructure based on maximum levels of fault tolerance. Eastern-European Journal of Enterprise Technologies, 5(3 (131)), 55-65.DOI: https://doi.org/10.15587/1729-4061.2024.311829 (in English)

Gorobchenko, O., & Nevedrov, O. (2020). Development of the structure of an intelligent locomotive DSS and assessment of its efectiveness. Archives of Transport, 56(4), 47-58.DOI: https://doi.org/10.5604/01.3001.0014.5517 (in English)

Grussing, M. N., Liu, L. Y., Uzarski, D. R., El-Rayes, K., & El-Gohary, N. (2016). Discrete Markov Approach for Building Component Condition, Reliability, and Service-Life Prediction Modeling. Journal of Performance of Constructed Facilities, 30(5), 04016015.DOI: https://doi.org/10.1061/(asce)cf.1943-5509.0000865 (in English)

He, W., & Sun, Y. (2017). Stationary Markov perfect equilibria in discounted stochastic games. Journal of Economic Theory, 169, 35-61. DOI: https://doi.org/10.1016/j.jet.2017.01.007 (in English)

Hernández-Lerma, O., & Lasserre, J. B. (1996). Discrete-Time Markov Control Processes. Basic Optimality Criteria. New York: Springer. DOI: https://doi.org/10.1007/978-1-4612-0729-0 (in English)

Martins, A., Fonseca, I., Farinha, J., Reis, J., & Cardoso, A. J. M. (2021). Maintenance Prediction through Sensing Using Hidden Markov Models – A Case Study. Applied Sciences, 11(16), 7685.DOI: https://doi.org/10.3390/app11167685 (in English)

Moiseenko, V., Kameniev, O., & Gaievskyi, V. (2017). Predicting a technical condition of railway automation hardware under conditions of limited statistical data. Skhidno-Yevropeiskyi zhurnal peredovykh tekhnolohii, 3(9 (87)), 26-35. DOI: https://doi.org/10.15587/1729-4061.2017.102005 (in English)

Stewart, W. J. (1994). Introduction to the numerical solution of Markov chains. Princeton: Princeton University Press. (in English)

Tang, D., Cao, J., & Yu, J. (2019). Remaining useful life prediction for engineering systems under dynamic operational conditions: A semi-Markov decision process-based approach. Chinese Journal of Aeronautics, 32(3), 627-638. DOI: https://doi.org/10.1016/j.cja.2018.08.015 (in English)

Vale, C., & Simões, M. L. (2022). Prediction of Railway Track Condition for Preventive Maintenance by Using a Data-Driven Approach. Infrastructures, 7(3), 34.DOI: https://doi.org/10.3390/infrastructures7030034 (in English)