A train running on a track in digital environment. (JPG)

Rail4Future

Project Description

The COMET¹ Project Rail4Future² (R4F) aims to enable, for the first time, a fully virtual assessment of the behavior of the railway infrastructure system by deploying large-scale simulations based on hybrid-models enhanced with AI³ capabilities, real-time data input from the railway operations and visual-analytics methods.

A diagram describing the associated processes from the Rail4Future project. (PNG) — © TU Wien MIVP

Process chart of Rail4Future

Methodology

Developing a R4F Platform able to handle different levels of findings, gathered through simulations, machine learning, data analysis.
Virtual integration strategies of heterogeneous data: section information (digitalized rail network information, etc.), context information, sensor data & modelling approaches from simplified analytic calculations, comprehensive FEM⁴ simulations up to machine learning models and etc.
Functions development (surrogate model /model reduction) for specific damage & deterioration analysis of railway sections.
Building a common framework for railway infrastructure reliability assessment.
Development of relevant tests, validation scenarios (KPIs⁵) on real-world data.
Automated integration of models & information with different levels of detail (tool-chains, FMI⁶, etc.)

IT architecture showing the used IT technologies and their relationships with each other in the Rail4Future platform. (PNG) — © TU Wien MIVP

IT-Architecture of the Rail4Future platform

Impact and Effects

Different railway infrastructure assets can be automatically and efficiently integrated.
A continuous flow of reliable and meaningful information throughout the entire life span of different railway infrastructure subsystems can be ensured.
The R4F Platform may also play an essential basis for the design of a virtual assessment platform as a universally applicable solution for digitized railway systems in the future.

Project Partners

Contact Person TU Wien MIVP

Project Manager: Ao. Univ. Prof. Dipl.-Ing. Dr. techn. Manfred Grafinger
Email: manfred.grafinger@tuwien.ac.at
Phone: +43 1 58801 30723

Key Person: Shiyang Zhou M.Sc.
Email: shiyang.zhou@tuwien.ac.at

Key Person: Ozan Kugu M.Sc.
Email: ozan.kugu@tuwien.ac.at
Phone: +43 1 58801 30737

Relevant Webpages

Rail4Future FFG, opens an external URL in a new window

Rail4Future Homepage, opens an external URL in a new window

Key Data Rail4Future

Project start: 01.04.2021

Project end: 30.09.2024

Project duration: 42 months

Time period: 2021 - 2024

Status: completed

Keywords: Large Scale Simulation; Turnout & Track; Bridge & Tunnel; Predictive Analytics; Hybrid Modeling

Publication

Kugu, O., Zhou, S., Reiterer, S. H., Schwaiger, M., Wurth, L., & Grafinger, M. (2024). Pipeline-Based Automated Integration and Delivery Testing of Simulation Assets with FMI/SSP in a Railway Digital Twin. Proceedings of the American Modelica Conference 2024, Storrs, Connecticut, USA, October 14-16, 2024, pp. 189-198. URL: https://doi.org/10.3384/ecp207189, opens an external URL in a new window

Zhou, S., Kugu, O., Wurth, L., & Grafinger, M. (2024). A Reinforcement-Learning-based Parameter Tuning Methodology for Traction Control in the Holistic Railway Digital Twin System. Procedia CIRP, Vol. 128, pp. 828-833. URL: https://doi.org/10.1016/j.procir.2024.06.040, opens an external URL in a new window

Kugu, O., Zhou, S., Nowak, R., Müller, G., Reiterer, S.H., Meierhofer, A., Lachinger, S., Wurth, L. & Grafinger, M. (2023). An FMI- and SSP⁷-based Model Integration Methodology for a Digital Twin Platform of a Holistic Railway Infrastructure System. Proceedings of the 15th International Modelica Conference 2023, Aachen, October 9-11, Vol. 204, pp. 717-726. URL: https://doi.org/10.3384/ecp204717, opens an external URL in a new window

Zhou, S., Meierhofer, A., Kugu, O., Xia, Y., & Grafinger, M. (2023). A Machine-Learning-based Surrogate Modeling Methodology for Submodel Integration in the Holistic Railway Digital Twin Platform. Procedia CIRP, Vol. 119, pp. 345-350. URL: https://doi.org/10.1016/j.procir.2023.02.141, opens an external URL in a new window

Zhou, S., Dumss, S., Nowak, R., Riegler, R., Kugu, O., Krammer, M., & Grafinger, M. (2022). A Conceptual Model-based Digital Twin Platform for Holistic Large-scale Railway Infrastructure Systems. Procedia CIRP, Vol. 109, pp. 362–367. URL: https://doi.org/10.1016/j.procir.2022.05.263, opens an external URL in a new window

Abbreviations

¹ COMET -> Competence Centers for Excellent Technologies

² Rail4Future -> Railways for Future: Resilient Digital Railway Systems to enhance performance

³ AI -> Artificial Intelligence

⁴ FEM -> Finite Element Method

⁵ KPI -> Key Performance Indicator

⁶ FMI -> Functional Mock-up Interface

⁷ SSP -> System Structure and Parameterization