Creating Feature Spaces and Autoregressive Models to Forecast Railway Track Deviations
- Authors: Vladova A.Y.1,2
-
Affiliations:
- Trapeznikov Institute of Control Sciences, Russian Academy of Sciences
- Financial University under the Government of the Russian Federation
- Issue: No 2 (2023)
- Pages: 54-64
- Section: Control of Technical Systems and Industrial Processes
- URL: https://bakhtiniada.ru/1819-3161/article/view/291585
- DOI: https://doi.org/10.25728/pu.2023.2.5
- ID: 291585
Cite item
Full Text
Abstract
Diagnosis of railway tracks reveals the deviations of rail parameters in the plan and profile from their nominal values. If the deviations approach the limit values, the speeds of trains must be reduced. Therefore, forecasting changes in the deviations is a topical problem. Despite the significant amount of diagnostic data collected, railway operators underuse machine learning methods to improve the quality of prediction. The proposed approach differs from known counterparts as follows. First, the dimensionality of the feature space is increased by calculating the variation of the amplitudes of deviations from the nominal values and two types of areas (the deviation length multiplied by the amplitude and the deviation length multiplied by the variation of the amplitude); subsequently, this space is represented in the 3D matrix form. Second, a set of control parameters is formed; it includes the time and space discretization step, the type of seasonal fluctuations, the number of trend change points, etc. Third, the deviations are predicted in groups differing in type and position along the track. Forecasting is based on minimizing the empirical risk criterion. As a result, a family of autoregressive models is obtained for each discretization interval along the length of the railway track.
About the authors
A. Yu Vladova
Trapeznikov Institute of Control Sciences, Russian Academy of Sciences; Financial University under the Government of the Russian Federation
Email: avladova@ipu.ru
Moscow, Russia
References
- Kostrzewski, M., Melnik, R. Condition Monitoring of Rail Transport Systems: A Bibliometric Performance Analysis and Systematic Literature Review // Sensors. – 2021. – Vol. 21, no. 14. – Art. no. 4710.
- Tsunashima, H. Condition Monitoring of Railway Tracks from Car-Body Vibration Using a Machine Learning Technique // Applied Sciences. – 2019. – Vol. 9. – Art. no. 2734.
- Liu, X., Markine, V.L. Train Hunting Related Fast Degradation of a Railway Crossing-Condition Monitoring and Numerical Verification // Sensors. – 2020. – Vol. 20, no. 8. – Art. no. 2278.
- Vladova, A.Yu. Identification of the Railway Track Technical State // 2021 14th International Conference Management of large-scale system development (MLSD). – Moscow: IEEE, 2021. – P. 1–5.
- Дубицкий И.С., Енин А.В., Владова А.Ю. Анализ динамики износа железнодорожных путей // Материалы 14-й междунар. конф. «Управление развитием крупномасштабных систем» (MLSD’2021). – Москва, 2021. – C. 979–985. [Dubitskii I.S., Enin A.V., Vladova A.Yu. Analiz dinamiki iznosa zheleznodorozhnykh putei // Materialy 14-i mezhdu-nar. konf. «Upravlenie razvitiem krupnomasshtabnykh sistem» (MLSD’2021). – Moskva, 2021. – C. 979–985. (In Russian)]
- Лукашин Ю.П. Адаптивные методы краткосрочного прогнозирования временных рядов. – М: Финансы и статистика (ФС), 2003. [Lukashin, Yu.P. Adaptivnye metody kratkosrochnogo prognozirovaniya vremennyh ryadov. – M: Finansy i statistika (FS), 2003. (In Russian)]
- Владова А.Ю. Гармонический анализ температур мерзлого грунта полосы отведения линейного объекта // Безопасность труда в промышленности. – 2017. – № 7. – С. 25–30. [Vladova, A.Yu. Garmonicheskij analiz temperatur merzlogo grunta polosy otvedeniya linejnogo ob'ekta // Bezopasnost' truda v promyshlennosti. – 2017. – No. 7. – P. 25–30. (In Russian)]
- Vladova, A.Yu. Remote Geotechnical Monitoring of a Buried Oil Pipeline // Mathematics. – 2022. – Vol. 10, no. 11. – Art. no.. 1813.
- Любушин А.А. Анализ данных систем геофизического и экологического мониторинга. – М.: Наука, 2007. [Lyubushin, A.A. Analiz dannyh sistem geofizicheskogo i ekologicheskogo monitoringa. – M.: Nauka, 2007. (In Russian)]
- Валеев С.Г. Регрессионное моделирование при обработке данных. – Казань: Изд-во ФЭН Академии наук Республики Татарстан, 2001. [Valeev, S.G. Regressionnoe modelirovanie pri obrabotke dannyh. – Kazan’: Izd-vo FEN Akademii nauk Respubliki Tatarstan, 2001. (In Russian)]
- Herzen, J., Lässig, F., Piazetta, S.G., et al. Darts: User-Friendly Modern Machine Learning for Time Series // Journal of Machine Learning Research. – 2022. – Vol. 23. – P. 1–6.
- Hosseini, R., Yang, K., Chen, A., Patra, S. A flexible forecasting model for production systems // ArXiv: 2105.01098v1. – 2021. – DOI: https://doi.org/10.48550/arXiv.2105.01098.
- Taylor, S., Letham, B. Forecasting at scale // The American Statistician. – 2018. – Vol. 72, no. 1. – P. 37-45.
- Vandeput, N. Forecast KPI: RMSE, MAE, MAPE & Bias Towards Data Science. – URL: https://towardsdatascience.com/forecast-kpi-rmse-mae-mape-bias-cdc5703d242d (Дата обращения 04.02.2023) [Accessed February 4, 2023].
- Hartomo, K., Nataliani, Y. A new model for learning-based forecasting procedure by combining k-means clustering and time series forecasting algorithms // PeerJ Computer Science. – 2021. – Vol. 7, no. 2. – Art. no. e534. – DOI: https://doi.org/7717/peerj-cs.534.
- Vivas E., Allende-Cid H., Salas R. A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score // Entropy. – 2020. – Vol. 22, no. 12. – Art. no. 1412.
Supplementary files
