Using extreme value theory to identify railcar asymmetric wheel wear and its benefit analysis

    Yu Cui Affiliation
    ; Qing He Affiliation
    ; Zhenhua Zhang Affiliation
    ; Zhiguo Li Affiliation


Railcar asymmetric wheel wear leads to severe wear on one wheel but mild wear on the other wheel. The consequences of the asymmetric wheel include accelerated wear, mechanical failure and downtime, and high financial penalties. Therefore, identifying the asymmetric wheel wear is critical not only for cost effective maintenance but also for safe operations. Fortunately, the increasing amount of various wayside detectors is instrumented along the railway that can monitor the health of railcar components and log plenty of detailed information about railroad operations. One can use this information to identify the asymmetric wheel wear in the early stage. However, most elliptically contoured distributions are effective in describing normal events but not in dealing with the outliers, which mainly locate in the tails of the distribution. Asymmetric wheel wear requires effective anomaly detection that mainly focuses on the extreme values in the tail of a right-skewed distribution. In this paper, we employ the Extreme Value Theory (EVT), which handles the unusually high or low data in the distribution, to derive an extreme value score to identify asymmetric wheel wear. Experiment results show that identification of asymmetric wheel wear can generate huge monetary benefit in terms of reducing average maintenance times of railcars.

Keyword : railcar, asymmetric wheel wear, wayside detectors, railway maintenance, extreme value theory, anomaly detection

How to Cite
Cui, Y., He, Q., Zhang, Z., & Li, Z. (2019). Using extreme value theory to identify railcar asymmetric wheel wear and its benefit analysis. Transport, 34(5), 569-578.
Published in Issue
Dec 9, 2019
Abstract Views
PDF Downloads
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.


AAR. 2016. Economic and Public Benefits. Association of American Railroads (AAR). Available from Internet:

Akoglu, L.; Tong, H.; Vreeken, J.; Faloutsos, C. 2012. Fast and reliable anomaly detection in categorical data, in CIKM’12: Proceedings of the 21st ACM International Conference on Information and Knowledge Management, 29 October – 2 November 2012, Maui, Hawaii, US, 415–424.

Bogdevičius, M.; Žygienė, R.; Dailydka, S.; Bartulis, V.; Skrickij, V.; Pukalskas, S. 2015. The dynamic behaviour of a wheel flat of a railway vehicle and rail irregularities, Transport 30(2): 217–232.

Braghin, F.; Lewis, R.; Dwyer-Joyce, R. S.; Bruni, S. 2006. A mathematical model to predict railway wheel profile evolution due to wear, Wear 261(11–12): 1253–1264.

Broadwater, J. B.; Chellappa, R. 2010. Adaptive threshold estimation via extreme value theory, IEEE Transactions on Signal Processing 58(2): 490–500.

Caires, S.; Groeneweg, J.; Sterl, A. 2009. Past and future changes in the North Sea extreme waves, in Proceedings of the 31st International Conference on Coastal Engineering, 31 August – 5 September 2008, Hamburg, Germany, 547–559.

Camargo, L. F. M.; Resendiz, E.; Hart, J.; Edwards, J. R.; Ahuja, N.; Barkan, C. P. L. 2011. Machine Vision Inspection of Railroad Track. USDOT Region V Regional University Transportation Center Final Report. NEXTRANS Project No 0281Y02. 46 p.

Dailydka, S.; Lingaitis, L. P.; Myamlin, S.; Prichodko, V. 2008. Modelling the interaction between railway wheel and rail, Transport 23(3): 236–239.

Durham, A. 1997. Case study: the coal line wheel and rail interaction strategy, in Proceedings of the Sixth International Heavy Haul Railway Conference, 6–10 April 1997, Cape Town, South Africa, 405–415.

Dykes, S. G. 2012. An extreme value theory approach to anomaly detection (EVT-AD). Poster, in IEEE Symposium on Security & Privacy, 20–23 May 2012, San Francisco, CA, US, 1–2.

Ellis, B. A. 2009. The Challenges of Condition Based Maintenance. The Jethro Project Consulting Group. 4 p.

Fröhling, R. D. 2006. Analysis of asymmetric wheel profile wear and its consequences, Vehicle System Dynamics: International Journal of Vehicle Mechanics and Mobility 44: 590–600.

Jardine, A. K. S.; Lin, D.; Banjevic, D. 2006. A review on machinery diagnostics and prognostics implementing condition-based maintenance, Mechanical Systems and Signal Processing 20(7): 1483–1510.

Kunkel, K. E.; Karl, T. R.; Brooks, H.; Kossin, J.; Lawrimore, J. H.; Arndt, D.; Bosart, L.; Changnon, D.; Cutter, S. L.; Doesken, N.; Emanuel, K.; Groisman, P. Y.; Katz, R. W.; Knutson, T.; O’Brien, J.; Paciorek, C. J.; Peterson, T. C.; Redmond, K.; Robinson, D.; Trapp, J.; Vose, R.; Weaver, S.; Wehner, M.; Wolter, K.; Wuebbles, D. 2013. Monitoring and understanding trends in extreme storms: state of knowledge, Bulletin of the American Meteorological Society 94(4): 499–514.

Lewis, R.; Braghin, F.; Ward, A.; Bruni, S.; Dwyer-Joyce, R. S.; Bel Knani, K.; Bologna, P. 2003. Integrating dynamics and wear modelling to predict railway wheel profile evolution, in 6th International Conference on Contact Mechanics and Wear of Rail/Wheel Systems (CM2003), 10–13 June 2003, Gothenburg, Sweden, 1–11.

Li, H.; Parikh, D.; He, Q.; Qian, B.; Li, Z.; Fang, D.; Hampapur, A. 2014. Improving rail network velocity: a machine learning approach to predictive maintenance, Transportation Research Part C: Emerging Technologies 45: 17–26.

Li, X.; Jin, X.; Wen, Z.; Cui, D.; Zhang, W. 2011. A new integrated model to predict wheel profile evolution due to wear, Wear 271(1–2): 227–237.

Li, Z.; He, Q. 2015. Prediction of railcar remaining useful life by multiple data source fusion, IEEE Transactions on Intelligent Transportation Systems 16(4): 2226–2235.

Markou, M.; Singh, S. 2003. Novelty detection: a review – part 1: statistical approaches, Signal Processing 83(12): 2481–2497.

Mikaliūnas, Š.; Lingaitis, L. P.; Subačius, R. 2002. Analysis of locomotive wheel sets wearing, Transport 17(1): 3–7.

Min, S.-K.; Zhang, X.; Zwiers, F.; Shiogama, H.; Tung, Y.-S.; Wehner, M. 2013. Multimodel detection and attribution of extreme temperature changes, Journal of Climate 26(19): 7430–7451.

Ortiz, E.; Babbar, A.; Syrmos, V. L. 2009. Extreme Value Theory for engine health monitoring and diagnosis, in 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC), 8–10 July 2009, St. Petersburg, Russia, 1069–1074.

Ouyang, Y.; Li, X.; Barkan, C. P. L.; Kawprasert, A.; Lai, Y.-C. 2009. Optimal locations of railroad wayside defect detection installations, Computer‐Aided Civil and Infrastructure Engineering 24(5): 309–319.

Roberts, S. J. 1999. Novelty detection using extreme value statistics, IEE Proceedings – Vision, Image and Signal Processing 146(3): 124–129.

Schlake, B. 2010. Impact of Automated Condition Monitoring Technologies on Railroad Safety and Efficiency. MSc Thesis. University of Illinois at Urbana-Champaign, Champaign, IL, US 143 p.

Singh, S.; Tu, H.; Donat, W.; Pattipati, K.; Willett, P. 2009. Anomaly detection via feature-aided tracking and hidden Markov models, IEEE Transactions on Systems, Man, and Cybernetics – Part A: Systems and Humans 39(1): 144–159.

Tournay, H. 2011. Integrated freight car truck design concept, in WCRR 2011: 9th World Congress on Railway Research, 22–26 May 2011, Lille, France, 1–11.

Tournay, H. 2008. The development of algorithms to detect poorly performing vehicles at wayside detectors, in WCRR 2008: 8th World Congress on Railway Research, 18–22 May 2008, Seoul, Korea, 1–11.

Ye, N.; Emran, S. M.; Chen, Q.; Vilbert, S. 2002. Multivariate statistical analysis of audit trails for host-based intrusion detection, IEEE Transactions on Computers 51(7): 810–820.