| Русский Русский | English English |
   
Главная Архив номеров
29 | 03 | 2024
10.14489/vkit.2022.02.pp.008-018

DOI: 10.14489/vkit.2022.02.pp.008-018

Платонов Е. Н., Просвирин К. В.
ПРОГНОЗИРОВАНИЕ ДЕФЕКТОВ ВЕРХНЕГО СТРОЕНИЯ ЖЕЛЕЗНОДОРОЖНОГО ПУТИ МЕТОДАМИ МАШИННОГО ОБУЧЕНИЯ
(pp. 8-18)

Аннотация. Предложены методы предсказания дефектов для объектов верхнего строения железнодорожного пути методами машинного обучения. В железнодорожном секторе большинство работ по техническому обслуживанию выполняются по расписанию, что может привести к отказу системы между двумя соседними проверками. В последние годы много внимания уделяется новым технологиям на основе методов машинного обучения для построения предикативной системы технического обслуживания. Кроме классических методов машинного обучения, таких как градиентный бустинг, использованы рекуррентные нейронные сети различной архитектуры. Полученные результаты позволяют говорить о том, что достигнут практический порог по точности предсказаний модели с учетом зашумленности входных данных. Предлагаемый набор методов можно рассматривать как часть системы принятия решений по техническому обслуживанию пути. Его можно легко адаптировать для функционирования в режиме онлайн и интегрировать с автоматизированной измерительной системой на базе транспортного средства.

Ключевые слова:  задача классификации; несбалансированные данные; дефекты железнодорожного пути; порог бинаризации; градиентный бустинг; рекуррентные нейронные сети.

 

Platonov E. N., Prosvirin K. V.
PREDICTION OF TRACK STRUCTURE DEFECTS BY MACHINE LEARNING METHODS
(pp. 8-18)

Abstract. This paper proposes methods of defect prediction for railroad track superstructure objects using machine learning methods. In the railroad sector, most maintenance work is performed on a schedule, which can lead to system failure between two adjacent checks. In recent years, much attention has been paid to new technologies and “smart” approaches based on machine learning techniques, to build a predictive maintenance system. The problem of defect detection from a machine learning perspective is a classification problem with two classes. The initial observation data for the state of the superstructure of the railway track of the problem are unbalanced. This is due to the fact that one of the classes, on the objects of which a track structure defect has been registered, occurs much less frequently. Therefore, when solving the problem, an important parameter is the binarization threshold for machine learning algorithm responses. Modern methods for solving classification problems for tabular data were used to solve the problem. In addition to classical machine learning methods, such as gradient boosting, recurrent neural networks of different architectures were used.  The results suggest that a practical threshold has been reached for the accuracy of model predictions, taking into account the noisiness of the input data. The practical significance of this work is that the proposed set of methods can be considered as part of a track maintenance decision-making system. It can be easily adapted for online operation and integrated with an automated measuring system based on a track geometry “recording” car.

Keywords: Classification problem; Unbalanced data; Railway track defects; Binarization threshold; Gradient boosting; Recurrent neural networks.

Рус

Е. Н. Платонов (Московский авиационный институт (национальный исследовательский университет), Москва, Россия) E-mail: Этот e-mail адрес защищен от спам-ботов, для его просмотра у Вас должен быть включен Javascript
К. В. Просвирин (Сколковский институт науки и технологий, Москва, Россия)

 

Eng

E. N. Platonov (Moscow Aviation Institute (National Research University), Moscow, Russia) E-mail: Этот e-mail адрес защищен от спам-ботов, для его просмотра у Вас должен быть включен Javascript
K. V. Prosvirin (Skolkovo Institute of Science and Technology, Moscow, Russia)

 

Рус

1. Годовой отчет за 2020 г. ОАО «РЖД»: сайт. URL: https://company.rzd.ru/ru/9471 (дата обращения: 19.01.2022).
2. Lasisi A., Attoh-Okine N. Principal Components Analysis and Track Quality Index: a Machine Learning Approach // Transp. Res. Part C Emerg. Technol. 2018. V. 91. P. 230 – 248.
3. Li Q., Zhong Z., Liang Z., Liang Y. Rail Inspection Meets Big Data: Methods and Trends // 18th International Conference on Network-Based Information Systems. 10.1109/nbis. 2015. P. 302 – 308.
4. Gibert X., Patel V. M., Chellappa R. Deep Multitask Learning for Railway Track Inspection // IEEE Transactions on Intelligent Transportation Systems. V. 18, № 1. 2017. P. 153 – 164.
5. SMaRTЕ: сайт. Smart Maintenance and the Rail Traveller Experience. URL: http://www.smarte-rail.eu/ (дата обращения: 19.01.2022).
6. Fumeo E., Oneto L., Anguita D. Condition Based Maintenance in Railway Transportation Systems Based on Big Data Streaming Analysis // INNS Conference on Big Data. San Francisco, CA, USA, 8 – 10 August 2015. P. 437 – 446.
7. Improving Rail Network Velocity: A Machine Learning Approach to Predictive Maintenance / H. Li, D. Parikh, Q. He et al. // Transportation Research Part C: Emerging Technologies. 2014. V. 45. P. 17 – 26.
8. Fayyaz M. A. B., Alexoulis-Chrysovergis A. C., Southgate M. J., Johnson C. A Review of the Technological Developments for Interlocking at Level Crossing // Proceedings of the Institution of Mechanical Engineers. Part F: Journal of Rail and Rapid Transit. 2020. P. 0954409720941726.
9. Alawad H., Kaewunruen S., An M. A deep learning approach towards railway safety risk assessment // IEEE Access. 2020. V. 8. P. 102811 – 102832.
10. Nakhaee M. C., Hiemstra D., Stoelinga M., Van Noort M. The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey // Lecture Notes in Computer Science. 2019. P. 91 – 105.
11. A Systematic Literature Review of Machine Learning Methods Applied to Predictive Maintenance / T. P. Carvalho, F. Soares, R. Vita et al. // Computers & Industrial Engineering. 2019. V. 137. P. 106024.
12. 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.
13. Резницкий М. А., Аршинский Л. В. Программная реализация автоматизированной системы обнаружения дефектов верхнего строения пути на основе технологии сверточных нейронных сетей // Молодая наука Сибири: 2018. № 1 [Электронный ресурс]. URL: http://mnv.irgups.ru (дата обращения: 19.01.2022).
14. Применение методов машинного обучения для прогнозирования опасных отказов объектов железнодорожного пути / И. Б. Шубинский, А. М. Замышляев, О. Б. Проневич и др. // Надежность. 2020. № 2. С. 44 – 54.
15. RAILS Project Deliverable D1.2: Summary of Existing Relevant Projects and State-of-the-art of AI Application in Railways / Technical Report. Sweden: Linnaeus University. 2021.
16. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. New York: Springer-Verlag, 2017.
17. Luque A., Carrasco A., Martín A., Heras A. The Impact of Class Imbalance in Classification Performance Metrics Based on the Binary Confusion Matrix // Pattern Recognition. 2019. V. 91. P. 216 – 231.
18. García V., Sánchez J. S., Mollineda R. A. On the Effectiveness of Preprocessing Methods when Dealing with DIfferent Levels of Class Imbalance // Knowl.-Based Syst. 2012. V. 25. P. 13 – 21.
19. Dataset Shift in Machine Learning (Neural Information Processing). Massachusetts Institute of Technology Press, 2009. 246 p.
20. LightGBM: A Highly Efficient Gradient Boosting Decision Tree / G. Ke, Meng Qi, T. Finley et al. // Proceedings of the 31nd International Conference on Neural Information Processing Systems (NIPS’17). Long Beach, California, USA. 4 – 9 December 2017. P. 3149 – 3157.
21. Dorogush A. V., Ershov V., Gulin A. CatBoost: gradient boosting with categorical features support // Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS’18). Monreal, Canada. 3 – 8 December. 2018. P. 6639 – 6649.
22. Sill J., Takа́cs G., Mackey L., Lin D. Feature-Weighted Linear Stacking. 3 November 2009. Computer Science. ArXiv:0911.0460.
23. Гудфеллоу Я., Бенджио И., Курвилль А. Глубокое обучение. М.: ДМК Пресс, 2018. 652 с.
24. Chung J., Gulcehre C., Cho K., Bengio Y. Gated Feedback Recurrent Neural Networks // Proceedings of the 32nd International Conference on Machine Learning (ICML 2015). Lille, France. 6 – 11 July 2015. P. 2067 – 2075.

Eng

1. Annual report for 2020 JSC Russian Railways. Available at: https://company.rzd.ru/ru/9471 (Accessed: 19.01.2022). [in Russian language]
2. Lasisi A., Attoh-Okine N. (2018). Principal Components Analysis and Track Quality Index: a Machine Learning Approach. Transportation Research Part C: Emerging Technologies, Vol. 91, pp. 230 – 248.
3. Li Q., Zhong Z., Liang Z., Liang Y. (2015). Rail Inspection Meets Big Data: Methods and Trends. 18th International Conference on Network-Based Information Systems, pp. 302 – 308. 10.1109/nbis.
4. Gibert X., Patel V. M., Chellappa R. (2017). Deep Multitask Learning for Railway Track Inspection. IEEE Transactions on Intelligent Transportation Systems, Vol. 18, (1), pp. 153 – 164.
5. SMaRTЕ. Smart Maintenance and the Rail Traveller Experience. Available at: http://www.smarte-rail.eu/ (Accessed: 19.01.2022).
6. Fumeo E., Oneto L., Anguita D. (2015). Condition Based Maintenance in Railway Transportation Systems Based on Big Data Streaming Analysis. INNS Conference on Big Data, pp. 437 – 446. San Francisco.
7. Li H., Parikh D., He Q. et al. (2014). Improving Rail Network Velocity: A Machine Learning Approach to Predictive Maintenance. Transportation Research Part C: Emerging Technologies, Vol. 45, pp. 17 – 26.
8. Fayyaz M. A. B., Alexoulis-Chrysovergis A. C., Southgate M. J., Johnson C. (2020). A Review of the Technological Developments for Interlocking at Level Crossing. Proceedings of the Institution of Mechanical Engineers. Part F: Journal of Rail and Rapid Transit.
9. Alawad H., Kaewunruen S., An M. (2020). A deep learning approach towards railway safety risk assessment. IEEE Access, Vol. 8, pp. 102811 – 102832.
10. Nakhaee M. C., Hiemstra D., Stoelinga M., Van Noort M. (2019). The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey. Lecture Notes in Computer Science, pp. 91 – 105.
11. Carvalho T. P., Soares F., Vita R. et al. (2019). A Systematic Literature Review of Machine Learning Methods Applied to Predictive Maintenance. Computers & Industrial Engineering, Vol. 137.
12. Boyko P. Yu., Bykov E. M., Sokolov E. I., Yarotskiy D. A. (2017). Application of machine learning to the ranking of incidents on the Moscow Railway. Informatsionnye tekhnologii i vychislitelnye sistemy, (2), pp. 43 – 53. [in Russian language]
13. Reznitskiy M. A., Arshinskiy L. V. (2018). Software implementation of an automated system for detecting defects in the track superstructure based on the technology of convolutional neural networks. Molodaya nauka Sibiri, (1). Available at: http://mnv.irgups.ru (Accessed: 19.01.2022). [in Russian language]
14. Shubinskiy I. B., Zamyshlyaev A. M., Pronevich O. B. et al. (2020). Application of machine learning methods for predicting dangerous failures of railway facilities. Nadezhnost', (2), pp. 44 – 54. [in Russian language]
15. RAILS Project Deliverable D1.2: Summary of Existing Relevant Projects and State-of-the-art of AI Application in Railways. (2021). Technical Report. Sweden: Linnaeus University.
16. Hastie T., Tibshirani R., Friedman J. (2017). The Elements of Statistical Learning. New York: Springer-Verlag.
17. Luque A., Carrasco A., Martín A., Heras A. (2019). The Impact of Class Imbalance in Classification Performance Metrics Based on the Binary Confusion Matrix. Pattern Recognition, Vol. 91, pp. 216 – 231.
18. García V., Sánchez J. S., Mollineda R. A. (2012). On the Effectiveness of Preprocessing Methods when Dealing with DIfferent Levels of Class Imbalance. Knowledge-Based Systems, Vol. 25, pp. 13 – 21.
19. Dataset Shift in Machine Learning (Neural Information Processing). Massachusetts Institute of Technology Press.
20. Ke G., Meng Qi, Finley T. et al. (2017). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the 31nd International Conference on Neural Information Processing Systems (NIPS’17), pp. 3149 – 3157. Long Beach.
21. Dorogush A. V., Ershov V., Gulin A. (2018). CatBoost: gradient boosting with categorical features support. Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS’18), pp. 6639 – 6649. Monreal.
22. Sill J., Takа́cs G., Mackey L., Lin D. (2009). Feature-Weighted Linear Stacking. Computer Science. ArXiv:0911.0460.
23. Gudfellou Ya., Bendzhio I., Kurvill A. (2018). Deep Learning. Moscow: DMK Press. [in Russian language]
24. Chung J., Gulcehre C., Cho K., Bengio Y. (2015). Gated Feedback Recurrent Neural Networks. Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), pp. 2067 – 2075. Lille.

Рус

Статью можно приобрести в электронном виде (PDF формат).

Стоимость статьи 500 руб. (в том числе НДС 18%). После оформления заказа, в течение нескольких дней, на указанный вами e-mail придут счет и квитанция для оплаты в банке.

После поступления денег на счет издательства, вам будет выслан электронный вариант статьи.

Для заказа скопируйте doi статьи:

10.14489/vkit.2022.02.pp.008-018

и заполните  форму 

Отправляя форму вы даете согласие на обработку персональных данных.

.

 

Eng

This article  is available in electronic format (PDF).

The cost of a single article is 450 rubles. (including VAT 18%). After you place an order within a few days, you will receive following documents to your specified e-mail: account on payment and receipt to pay in the bank.

After depositing your payment on our bank account we send you file of the article by e-mail.

To order articles please copy the article doi:

10.14489/vkit.2022.02.pp.008-018

and fill out the  form  

 

.

 

 

 
Поиск
Баннер
Баннер
Rambler's Top100 Яндекс цитирования