Skip to main content
SpringerLink
Log in

Toward a safe MLOps process for the continuous development and safety assurance of ML-based systems in the railway domain

  • Original Research
  • Published:
AI and Ethics Aims and scope Submit manuscript

Abstract

Traditional automation technologies alone are not sufficient to enable driverless operation of trains (called Grade of Automation (GoA) 4) on non-restricted infrastructure. The required perception tasks are nowadays realized using Machine Learning (ML) and thus need to be developed and deployed reliably and efficiently. One important aspect to achieve this is to use an MLOps process for tackling improved reproducibility, traceability, collaboration, and continuous adaptation of a driverless operation to changing conditions. MLOps mixes ML application development and operation (Ops) and enables high-frequency software releases and continuous innovation based on the feedback from operations. In this paper, we outline a safe MLOps process for the continuous development and safety assurance of ML-based systems in the railway domain. It integrates system engineering, safety assurance, and the ML life-cycle in a comprehensive workflow. We present the individual stages of the process and their interactions. Moreover, we describe relevant challenges to automate the different stages of the safe MLOps process.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

Notes

  1. https://safetrain-projekt.de/en.

  2. https://cloud.google.com/architecture/mlops-continuous-delivery-and-automation-pipelines-in-machine-learning.

References

  1. EASA. European Union Aviation Safety Agency (EASA) Concept Paper: First usable guidance for Level 1 machine learning applications. https://www.easa.europa.eu/en/downloads/134357/en (2021)

  2. EN 50126-1:2018-10. Railway Applications – The Specification and Demonstration of Reliability, Availability, Maintainability and Safety (RAMS) - Part 1: Generic RAMS Process (2018)

  3. EN 50128:2012-02. Railway Applications – Communication, signaling and processing systems – Software for railway control and protection systems (2012)

  4. EN 50129:2019-06. Railway application – Communications, signaling and processing systems – Safety related electronic systems for signaling (2019)

  5. EN 50657:2017-11. Railways Applications - Rolling stock applications - Software on Board Rolling Stock (2017)

  6. Hawkins, R., Paterson, C., Picardi, C., Jia, Y., Calinescu, R., Habli, I.: Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS). arxiv:2102.01564 (2021)

  7. ISO 21448:2022-06. Road vehicles - Safety of the Intended Functionality (2022)

  8. ISO 26262-2:2018-12. Road vehicles – Functional safety – Part 2: Management of functional safety (2018)

  9. Kelly, T., Weaver, R.: The goal structuring notation–a safety argument notation. In Proceedings of the dependable systems and networks 2004 workshop on assurance cases, 6 (2004)

  10. Koopman, P., Ferrell, U., Fratrik, F., Wagner, M.: A safety standard approach for fully autonomous vehicles. In: Romanovsky, A., Troubitsyna, E., Gashi, I., Schoitsch, E., Bitsch, F. (eds.) Computer Safety, Reliability, and Security, pp. 326–332. Springer International Publishing, Springer (2019)

    Chapter  Google Scholar 

  11. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)

    Article  Google Scholar 

  12. Loukides, M.: What is DevOps? O’Reilly Media, Inc (2012)

  13. Radlak, K., Szczepankiewicz, M., Jones, T., Serwa, P.: Organization of machine learning based product development as per ISO 26262 and ISO/PAS 21448. In 2020 IEEE 25th Pacific Rim International Symposium on Dependable Computing (PRDC), 110–119 (2020)

  14. Ritz, F., Phan, T., Sedlmeier, A., Altmann, P., Wieghardt, J., Schmid, R., Sauer, H., Klein, C., Linnhoff-Popien, C., Gabor, T.: Capturing Dependencies Within Machine Learning via a Formal Process Model. In Leveraging Applications of Formal Methods, Verification and Validation. Adaptation and Learning. ISoLA2022. Lecture Notes in Computer Science, vol 13707. Springer, 249–265 (2022)

  15. SAE. ARP 4761: Guidelines and Methods for Conducting the Safety Assessment Process on Civil Airborne Systems and Equipment (1996)

  16. SAE.: ARP 4754A: Guidelines for Development of Civil Aircraft and Systems (2010)

  17. Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.-F., Dennison, D.: Hidden Technical Debt in Machine Learning Systems. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates Inc (2015)

  18. Studer, S., Bui, T.B., Drescher, C., Hanuschkin, A., Winkler, L., Peters, S., Müller, K.-R.: Towards CRISP-ML(Q): a machine learning process model with quality assurance methodology. Mach. Learn. Knowledge Extract. 3(2), 392–413 (2021)

    Article  Google Scholar 

  19. VDE-AR-E 2842-61-2 Anwendungsregel:2021-06. Development and trustworthiness of autonomous/cognitive systems (2021)

  20. Waschulzik, T.: Qualitätsgesicherte effiziente Entwicklung vorwärtsgerichteter künstlicher Neuronaler Netze mit überwachtem Lernen (QUEEN). Dissertation, Technische Universität München, Fachbereich Informatik (1999)

  21. Waschulzik, T., Brauer, W., Castedello, T., Henery, B.: Quality assured efficient engineering of feedforward neural networks with supervised learning (QUEEN) evaluated with the"pima indians diabetes database". In Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, volume 4, 97–102 vol.4 (2000)

  22. Wood, M., Robbel, P., Maass, M., Tebbens, R. D., Meijs, M., Harb, M., Reach, J., Robinson, K., Wittmann, D., Srivastava, T., et al.: Safety first for automated driving. https://newsroom.intel.com/wp-content/uploads/sites/11/2019/07/Intel-Safety-First-for-Automated-Driving.pdf (2019)

  23. Wozniak, E., Putzer, H. J., Cârlan, C.: AI-Blueprint for Deep Neural Networks. In SafeAI AAAI (2021)

  24. Zeller, M.: Component Fault and Deficiency Tree (CFDT): Combining Functional Safety and SOTIF Analysis. In Model-Based Safety and Assessment, 146–152. ISBN 978-3-031-15842-1 (2022)

Download references

Acknowledgements

This research has received funding from the Federal Ministry for Economic Affairs and Climate Action (BMWK) under grant agreements 19I21039A.

Author information

Authors and Affiliations

  1. Siemens AG, Otto-Hahn-Ring 6, 81739, Munich, Germany

    Marc Zeller & Reiner Schmid

  2. Siemens Mobility GmbH, Siemenspromenade 4, 91058, Erlangen, Germany

    Thomas Waschulzik

  3. Siemens Mobility GmbH, Rudower Chaussee 29, 12489, Berlin, Germany

    Claus Bahlmann

Authors
  1. Marc Zeller
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas Waschulzik
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Reiner Schmid
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Claus Bahlmann
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marc Zeller.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zeller, M., Waschulzik, T., Schmid, R. et al. Toward a safe MLOps process for the continuous development and safety assurance of ML-based systems in the railway domain. AI Ethics 4, 123–130 (2024). https://doi.org/10.1007/s43681-023-00392-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s43681-023-00392-4

Keywords

Search

Navigation