MS062 - Machine Learning and Data-Driven Approaches in Railway Dynamics

Organized by: A. Mosleh (Porto University, Portugal), D. Robeiro (Polytechnic of Porto, Portugal), J. Fink (TU Wien, Austria), A. Stollwitzer (TU Wien, Austria) and A. Meghoe (University of Twente, Netherlands)
Keywords: bridge dynamics, computer vision and image analysis, data science, data-driven approach, machine learning, predictive maintenance, prognostic models, smart mobility, track-bridge interaction, vehicle-bridge interaction, wayside/drive-by condition monitoring, Wind turbines
In 2019, "The European Green Deal" set an ambitious target to make Europe the first climate-neutral continent by 2050. A vital aspect of this transition is the development of sustainable and smart mobility systems, with a specific focus on railway transport [1]. This symposium aims to promote the use of advanced techniques in numerical analyses and experimental field tests to improve railway safety, efficiency, and resilience. By bringing together experts from academia and industry, the symposium will facilitate knowledge exchange, foster collaborations, and encourage the development of adaptive infrastructure systems to achieve the goals set forth by "The European Green Deal". The proposed symposium has the following objectives: i) explore innovative approaches and technologies for enhancing railway safety, efficiency, and resilience; ii) facilitate collaboration and partnership opportunities among researchers, practitioners and industry experts; iii) discuss strategies to address the challenges associated with increasing rail capacity high-speed rail lines and maintenance costs; iv) showcase successful case studies and best practices in railway infrastructure development and management; v) identify future research directions and potential policy interventions to support sustainable and resilient railway systems.