Skip to main content

Synthetic Data Generation for Condition Monitoring of Railway Switches

  • 396 Accesses

Part of the Communications in Computer and Information Science book series (CCIS,volume 1656)

Abstract

The application of AI methods to industry requires a large amount of training data that covers all situations appearing in practice. It is often a challenge to collect a sufficient amount of such data. An alternative is to artificially generate realistic data based on training examples. In this paper we present a method for generating the electric current time series produced by railway switch engines during switch-blades repositioning. In practice, this electrical signal is monitored and can be used to detect unusual behaviour associated to switch faults. The generation method requires a sample of real curves and exploits their systematic temperature dependence to reduce their dimensionality. This is done by extracting the effect of temperature on specific parameters, which are then re-sampled and used to generate new curves. The model is analyzed in different practice-relevant scenarios and shows potential for improving condition monitoring methods.

Keywords

This project has received funding from the Shift2Rail Joint Undertaking (JU) under grant agreement No 881574. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and the Shift2Rail JU members other than the Union. The authors thank Strukton Rail and Wolfgang Riedler for their support on this work.

This is a preview of subscription content, log in via an institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    POSS®: Preventief Onderhoud - en Storingsdiagnosesysteem Strukton, http://www.POSSinfo.com.

References

  1. García Márquez, F.P., Lewis, R.W., Tobias, A.M., Roberts, C.: Life cycle costs for railway condition monitoring. Transp. Res. E Logist. Transp. Rev. 44, 1175–1187 (2008)

    Article  Google Scholar 

  2. Innotrack (2009) Deliverable 3.3.2. Available sensors for railway environments for condition monitoring. https://www.charmec.chalmers.se/innotrack/deliverables/sp3/d332-f3p-available_sensors.pdf. Accessed 3 Jun 2022

  3. Narezo Guzmán, D., et al.: Towards the automation of anomaly detection and integrated fault identification for railway switches in a real operational environment. In: Proceedings World Congress on Railway Research (2022). In press

    Google Scholar 

  4. Narezo Guzman, D., et al.: Anomaly detection and forecasting methods applied to point machine monitoring data for prevention of railway switch failures. In: Ball, A., Gelman, L., Rao, B.K.N. (eds.) Advances in Asset Management and Condition Monitoring. SIST, vol. 166, pp. 307–318. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-57745-2_26

    Chapter  Google Scholar 

  5. Vono, M., Dobigeon, N., Chainais, P.: High-dimensional Gaussian sampling: a review and a unifying approach based on a stochastic proximal point algorithm. SIAM Rev. 64(1), 3–56 (2022)

    Article  MathSciNet  Google Scholar 

  6. Lehmann, E.L., Romano, J.P.: Testing Statistical Hypotheses, vol. 3. Springer, Cham (2005). https://doi.org/10.1007/978-3-030-70578-7

  7. Rockafellar, R.T., Wets, R.J.-B.: Variational Analysis, vol. 317. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-02431-3

  8. Romano, J.P.: A bootstrap revival of some nonparametric distance tests. J. Am. Stat. Assoc. 83(403), 698–708 (1988)

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Miguel del Álamo .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

del Álamo, M., Heusel, J., Narezo Guzmán, D. (2022). Synthetic Data Generation for Condition Monitoring of Railway Switches. In: Marrone, S., et al. Dependable Computing – EDCC 2022 Workshops. EDCC 2022. Communications in Computer and Information Science, vol 1656. Springer, Cham. https://doi.org/10.1007/978-3-031-16245-9_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-16245-9_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-16244-2

  • Online ISBN: 978-3-031-16245-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics