sustainНадежностьDependability1729-26462500-3909RAMS Journal Limited liability company10.21683/1729-2646-2020-20-2-43-53sustain-371Research ArticleБЕЗОПАСНОСТЬ. ТЕОРИЯ И ПРАКТИКАSAFETY. THEORY AND PRACTICEПрименение методов машинного обучения для прогнозирования опасных отказов объектов железнодорожного путиApplication of machine learning methods for predicting hazardous failures of railway track assetsШубинскийИ. Б.ShubinskyI. B.

Игорь Б. Шубинский – доктор технических наук, профессор, заместитель руководителя

Москвател. +7 (495) 786-68-57 

Igor B. Shubinsky, Doctor of Engineering, Professor, Deputy Director of Integrated Research and Development Unit

Moscowphone: +7 (495) 786 68 57 

igor-shubinsky@yandex.ruЗамышляевА. М.ZamyshliaevA. M.

Алексей М. Замышляев – доктор технических наук, заместитель Генерального директора

Москвател. +7 (495) 967-77-02 

Alexey M. Zamyshliaev, Doctor of Engineering, Deputy Director General

Moscowphone: +7 495 967 77 02 

A.Zamyshlaev@vniias.ruПроневичО. Б.PronevichO. B.

Ольга Б. Проневич – начальник отдела

Москвател.+7 (985) 242-21-62 

Olga B. Pronevich, Head of Unit

Moscowphone: +7 (985) 242 21 62 

oesune@rambler.ruИгнатовА. Н.IgnatovA. N.

Алексей Н. Игнатов – кандидат физико-математических наук, старший преподаватель

Москвател. +7 (906) 059-50-00 

Alexey N. Ignatov, Candidate of Physics and Mathematics, Senior Lecturer

Moscowphone: +7 (906) 059 50 

alexei.ignatov1@gmail.comПлатоновЕ. Н.PlatonovE. N.

Евгений Н. Платонов – кандидат физико-математических наук, доцент, факультет «Прикладной математики и физики»

Москвател. +7 (499) 158-45-60 

en.platonov@gmail.comАО «НИИАС»РоссияJSC NIIASRussian FederationМосковский авиационный институтРоссияMoscow Aviation InstituteRussian Federation2020080620202024353Copyright © Шубинский И.Б., Замышляев А.М., Проневич О.Б., Игнатов А.Н., Платонов Е.Н., 20202020Шубинский И.Б., Замышляев А.М., Проневич О.Б., Игнатов А.Н., Платонов Е.Н.Shubinsky I.B., Zamyshliaev A.M., Pronevich O.B., Ignatov A.N., Platonov E.N.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.dependability.ru/jour/article/view/371

The Aim of the paper is to reduce the number of hazardous events on railway tracks by developing a method of prediction of rare hazardous failures based on processing of large amounts of data on each kilometre of track obtained in real time from diagnostics systems. Hazardous failures are rare events; the set of variate values of the number of such events for an individual kilometre of track per year is: [0, 1]. However, for a railway network as a whole the yearly number of such events is in the dozens and efficient management requires the transition from the estimation of the probability of hazardous failure occurrence to the identification of the most probable location of failure. Methods. The problem of identification of rare, but hazardous possible events out of hundreds of thousands of records of non-critical railway track parameter divergences cannot be solved by conventional means of statistical processing. Hazardous events are predicted using the above statistics and artificial intelligence. Big Data and Data Science technology is used. Such technology includes methods of machine learning that enable item classification based on characteristics (features, predicates) and known cases of undesired event occurrence. The application of various algorithms of machine learning is demonstrated using the example of prediction of track superstructure failures using records collected between 2014 and 2019 on the Kuybyshevskaya Railway. Findings and conclusions. The result of facility ranking is the conclusion regarding the location of the most probable hazardous failure of railway track. That conclusion is based on the correspondence analysis between the actual characteristics of an item and conditions of its operation and the cases of adverse events and cases of their non-occurrence. The practical value of this paper consists in the fact that the proposed set of methods and means can be considered as an integral part of the track maintenance decision-making system. It can be easily adapted for online operation and integrated into the automated measurement system installed on a vehicle.

машинное обучениеотказы объектов железнодорожного путирешающие деревьяmachine learningrailway track facility failuredecision treesРабота выполнена при поддержке РФФИ (проект № 20-07-00046А).ReferencesСуконников Г.В. Применение технологии «интернет вещей» в ОАО «РЖД» [электронный ресурс] // Инновационный Дайджест: [сайт]. [2017]. URL: http://www.rzd-expo.ru/innovation/novosti/1.pdfSukonnikov G.V. [Application of the Internet of Things by JSC RZD]. www.rzd-expo.ru; 2017. Available at: URL: http://www.rzd-expo.ru/innovation/novosti/1.pdf. (in Russ.)Бондаренко Ю.В., Куксо А.А., Маркевич И.Г. Информационные технологии в управлении системой диагностики железнодорожных путей // Сборник докладов IX международной научно-практической конференции студентов, аспирантов и молодых ученых: в 4 томах. 2018. С. 214–215.Bondarenko Yu.V., Kukso A.A., Markevich I.G. [Information technology in railway track diagnostics system management]. Proceedings of the IX international research and practice conference of students, post-graduate students and young scientists in 4 volumes. 2018;214-215. (in Russ.)Назаров Д.Г., Гура Д.А. О системах автоматизированного путеизмерительного контроля / Кубанский государственный технологический институт: Научные труды КУБГТУ. Краснодар, 2019. С. 135–146.Nazarov D.G., Guda D.A. [On systems for automated track measurement]. Krasnodar: Kuban State Technological University: Scientific works of the Kuban State Technological University; 2019:135-146. (in Russ.)Куракина С.Г., Шмакова Е.Г. Автоматизация диагностики и мониторинга участников контактной сети на железных дорогах // Современные инновации. 2017. № 8(22). С. 15–17.Kurakina S.G., Shumakova E.G. [Automation of diagnostics and monitoring of railway catenary sections]. Sovremennye innovatsii. 2017;8(22):15-17. (in Russ.)Замышляев А.М. Предпосылки для создания цифровой системы управления безопасностью движения // Надежность. 2019. № 4(71). С. 45–52.Zamyshliaev A.M. Premises of the creation of a digital traffic safety management system. Dependability. 2019;4(71):45-52.Кузнецов Г.А., Крашенинников С.В., Крайсвитний В.П. и др. Модернизация системы ГИД «УралВНИИЖТ» // Автоматика, связь, информатика. 2016. № 11. С. 15–19.Kuznetsova G.A., Krasheninnikov S.V., Kraysvitny V.P., etc. [Upgrading the GID Ural-VNIIZhT system]. Avtomatika, sviaz, informatika. 2016;11:15-19. (in Russ.)Замышляев А.М., Игнатов А.Н., Кибзун А.И. и др. Построение функциональной зависимости между рядом распределения количества вагонов в сходе и различными факторами движения // Надежность. 2018 . T. 18. № 1. С. 53–60.Zamyshliaev A.M., Ignatov A.N., Kibzun A.I., Novozhilov E.O. Functional dependency between the number of wagons derailed due to wagon or track defects and the traffic factors. Dependability. 2018;18(1):53-60.Liu X., Saat M., Barkan C. Analysis of causes of major train derailment and their effect on accident rates // Transp. Res. Rec. J. Transp. Res. Board. 2012. Vol. 2289. P. 154–163.Liu X., Saat M., Barkan C. Analysis of causes of major train derailment and their effect on accident rates. Transp. Res. Rec. J. Transp. Res. Board. 2012;2289:154–163.Замышляев А.М., Игнатов А.Н., Кибзун А.И. и др. О нарушении безопасности движения, связанном с выходом в габарит соседнего пути подвижных единиц грузового поезда, сошедших с рельсов // Надежность. 2018. T. 18. № 3. С. 39–45.Zamyshliaev A.M., Ignatov A.N., Kibzun A.I., Novozhilov E.O. On traffic safety incidents caused by intrusion of derailed freight cars into the operational space of an adjacent track. Dependability. 2018;18(3):39–45.Lasisi A., Attoh-Okine N. Principal components analysis and track quality index: a machine learning approach // Transp. Res. Part C. Emerg. Technol. 2018. Vol. 91. P. 230–248.Lasisi A., Attoh-Okine N. Principal components analysis and track quality index: a machine learning approach. Transp. Res. Part C. Emerg. Technol;91:230–248.Dr. Allan M. Zarembski Better railroading through Big Data [электронный ресурс] // Railway age: [сайт]. [2018]. URL: https://www.railwayage.com/analytics/betterrailroading-through-big-data/Zarembski A.M. Better railroading through Big Data. www.railwayage.com; 2018. Available at: https://www.railwayage.com/analytics/better-railroadingthrough-big-data.Thaduri A., Galar D., Kumar U. Railway assets: a potential domain for big data analytics // Proc. Comput. Sci. 2015. Vol. 53. P. 457–467.Thaduri A., Galar D., Kumar U. Railway assets: a potential domain for big data analytics. Proc. Comput. Sci. 2015;53:457–467.Li Q., Zhong Z., Liang Z. et al. Rail inspection meets big data: methods and trends. // 18th International Conference on Network-Based Information Systems. 2015. P. 302–308.Li Q., Zhong Z., Liang Z. et al. Rail inspection meets big data: methods and trends. 18th International Conference on Network-Based Information Systems. 2015:302–308.Флах П. Машинное обучение. Наука и искусство построения алгоритмов, которые извлекают знания из данных. М.: ДМК Пресс, 2015. 402 с.Flach P. Machine Learning: the art and science of algorithms that make sense of data. Moscow: BMK Press; 2015.Гудфеллоу Я., Бенджио И., Курвилль А. Глубокое обучение М.: ДМК Пресс, 2018. 652 с.Goodfellow I., Bengio Y., Courville A. Deep Learning. Moscow: DMK Press; 2018.Widodo A., Yang B.S. Support vector machine in machine condition monitoring and fault diagnosis // Mech. Syst. Signal Process. 2007. Vol. 21. P. 2560–2574.Widodo A., Yang B.S. Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process. 2007;21:2560–2574.Sun W., Chen J., Li J. Decision tree and PCA-based fault diagnosis of rotating machinery // Mech. Syst. Signal Process. 2007. Vol. 21. P. 1300–1317.Sun W., Chen J., Li J. Decision tree and PCAbased fault diagnosis of rotating machinery. Mech. Syst. Signal Process. 2007;21:1300–1317.Cerrada M., Zurita G., Cabrera D. et al. Fault diagnosis in spur gears based on genetic algorithm and random forest // Mech. Syst. Signal Process. 2016. Vol. 70–71. P. 87–103.Cerrada M., Zurita G., Cabrera D. et al. Fault diagnosis in spur gears based on genetic algorithm and random forest. Mech. Syst. Signal Process. 2016;7071:87–103.Santur Y., Karakose M., Akin E. Random forest based diagnosis approach for rail fault inspection in railways // National Conference on Electrical, Electronics and Biomedical Engineering. 2016. P. 714–719.Santur Y., Karakose M., Akin E. Random forest based diagnosis approach for rail fault inspection in railways. National Conference on Electrical, Electronics and Biomedical Engineering. 2016:714–719.Чистяков С.П. Случайные леса: обзор // Труды Карельского научного центра РАН. 2013. № 1. С. 117–136.Chistiakov S.P. [Random forests: an overview]. Transactions of Karelian Research Centre of the Russian Academy of Sciences. 2013;1:117-136.Hosmer D., Lemeshov S., Sturdivant R.X. Applied Logistic Regression. New York: John Wiley & Sons, 2013. 528 p.Hosmer D., Lemeshov S., Sturdivant R.X. Applied Logistic Regression. New York: John Wiley & Sons; 2013.Samworth R.J. Optimal weighted nearest neighbour classifiers // Ann. Statist. 2012. Vol. 40. № 5. P. 2733–2763.Samworth R.J. Optimal weighted nearest neighbour classifiers. Ann. Statist. 2012;40(5):2733–2763.Famurewa S.M., Zhang L., Asplund M. Maintenance analytics for railway infrastructure decision support // Journal Qual. Maint. Eng. 2017. № 23. P. 310–325.Famurewa S.M., Zhang L., Asplund M. Maintenance analytics for railway infrastructure decision support. Journal Qual. Maint. Eng. 2017;23:310–325.Hu C., Liu X. Modeling Track Geometry Degradation Using Support Vector Machine Technique // 2016 Joint Rail Conference. 2016.Hu C., Liu X. Modeling Track Geometry Degradation Using Support Vector Machine Technique. Joint Rail Conference; 2016.Бойко П.Ю., Быков Е.М., Соколов Е.И., Яроцкий Д.А. Применение машинного обучения к ранжированию инцидентов на Московской железной дороге // Информационные технологии и вычислительные системы. 2017. № 2. С. 43–53.Boyko P.Yu., Bikov E.M., Sokolov E.U., Yarotsky D.A. Application of Machine Learning to Incident Ranking at Moscow Railway. Journal of Information Technologies and Computing Systems. 2017;2:43-53. (in Russ.)Jiang Y., Wang H., Tian G. et al. Fast classification for rail defect depths using a hybrid intelligent method // Optik (Stuttg). 2019. Vol. 180. P. 455–468.Jiang Y., Wang H., Tian G. et al. Fast classification for rail defect depths using a hybrid intelligent method. Optik (Stuttg). 2019;180:455–468.Gibert X., Patel V.M., Chellappa R. Deep multitask learning for railway track inspection // IEEE Trans. Intell. Transp. Syst. 2017. Vol. 18. P. 153–164.Gibert X., Patel V.M., Chellappa R. Deep multitask learning for railway track inspection. IEEE Trans. Intell. Transp. Syst. 2017;18:153–164.Резницкий М.А., Аршинский Л.В. Программная реализация автоматизированной системы обнаружения дефектов верхнего строения пути на основе технологии свёрточных нейронных сетей // Молодая наука Сибири: электрон. науч. журн. 2018. № 1.Reznitskiy M.A., Arshinskiy L.V. Software implementation of the upper structure of the railway track defects detection automated system based on the technology of the convolutional neural networks. Electronic Scientific Journal “Young Science of Siberia”. 2018;1. (in Russ.)Lee J.S., Hwang S.H., Choi I.Y. et al. Prediction of track deterioration using maintenance data and machine learning schemes // J. Transp. Eng. Part A Syst. 2018. Vol. 144. P. 04018045-1:9.Lee J.S., Hwang S.H., Choi I.Y. et al. Prediction of track deterioration using maintenance data and machine learning schemes. J. Transp. Eng. Part A Syst. 2018;144:04018045-1:9.Nakhaee M.C., Hiemstra D., Stoelinga M. et al. The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey // Lecture Notes in Computer Science. 2019. P. 91–105.Nakhaee M.C., Hiemstra D., Stoelinga M. et al. The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey. Lecture Notes in Computer Science. 2019;91–105.Fawcett T. An introduction to ROC analysis // Pattern Recognition Letters. 2006. Vol. 27. P. 861–874.Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters. 2006;27:861–874.

The authors declare that there are no conflicts of interest present.