Master Theses

Model Reduction of Multibody Dynamics in Railways

Supervisors: Dr. Charikleia Stoura and Prof. Dr. Eleni Chatzi (ETH Zürich), Prof. Shobhit Jain (TU Delft),

Content
Multibody models are widely used to simulate railway vehicle dynamics, including the interactions between car bodies, bogies, wheelsets, suspensions, and wheel–rail contact. Despite their relatively limited number of degrees of freedom, repeated simulations can become computationally demanding, particularly for parametric studies, uncertainty quantification, optimization, and real-time applications.

This Master’s thesis aims to investigate and implement model-order-reduction techniques for rigid multibody railway vehicle systems. The objective is to develop computationally efficient reduced-order models (ROMs) that accurately reproduce the dominant vehicle dynamics while retaining the influence of suspension and wheel–rail contact forces across different operating conditions.

Expected project outcomes:

• Review model reduction techniques for rigid multibody dynamical systems.
• Develop a representative railway vehicle model and validate it against specialized software such as SIMPACK.
• Implement suitable reduction techniques to construct reduced-order railway vehicle models.
• Evaluate model accuracy, stability, and computational efficiency against the full-order model.
• Assess robustness under varying vehicle speeds, track irregularities, loading conditions, and suspension parameters.

Suggested Competencies: Linear algebra, numerical methods, MATLAB or Python programming. Background in structural dynamics, multibody systems, or model reduction is beneficial

Collaboration: Delft Institute of Applied Mathematics, TU Delft, and Chair of Structural Mechanics and Monitoring, ETH Zürich.

Graph-Based Reinforcement Learning for Erosion-Safe Operation and Maintenance of Offshore Wind Farms

Supervisors:  Lidiya Kalathiparambil Kennedy (Chair of Structural Mechanics and Monitoring, ETH Zürich), Alessandro Bassalti (Siemens Digital Industries Software, Leuven, and CONSTRUCT, Faculty of Engineering, University of Porto), Prof. Dr. Eleni Chatzi (Chair of Structural Mechanics and Monitoring, ETH Zürich).

Content

 Leading Edge Erosion (LEE), caused by rain and hail impacts on wind turbine blades, reduces energy production and drives costly offshore repairs. Erosion-safe operation (ESO), which means temporarily reducing blade tip speed during adverse weather, can extend blade lifetime at a small cost in energy. Reinforcement learning (RL) has shown promise for learning such strategies for single turbines, but in a wind farm, turbines are coupled through wake effects and shared maintenance logistics.

This thesis develops a graph-based RL framework in which the wind farm is represented as a graph (turbines as nodes, wake interactions as edges). The agent decides how much to derate each turbine during adverse weather and when to dispatch maintenance, balancing energy revenue against erosion damage, repair costs, and the effect of derating on structural fatigue loads.

Expected project outcomes

1. Review literature on leading edge erosion, erosion-safe operation, and graph neural networks for control
2. Extend an existing wind farm simulator (wake effects, fatigue) with erosion progression, aerodynamic degradation for maintenance conditioned erosion safe operations.
3. Define a graph representation of the wind farm suitable for RL controlTrain the agent and compare the learned policy against baseline strategies

Suggested Courses/Background: Structural Dynamics, Structural Identification & Health Monitoring, a course on machine learning, Aerodynamics, Wind Energ

Suggested Competencies: Proficiency in Python; familiarity with PyTorch or willingness to learn; interest in wind energy and structural reliability

Digital Twins and Temperature-Aware Monitoring for Bridge Performance Assessment

Supervisors: Dr. Yves Reuland (irmos technologies AG), Dr. Minas Spyridonakos (irmos technologies AG), Prof. Dr. Eleni Chatzi (ETH Zürich)

Content
Bridges are critical components of modern transport networks and must remain safe and functional well beyond their original design life. Increasing traffic loads, environmental variability, and aging materials challenge traditional assessment approaches based on periodic inspections and conservative safety margins.

Continuous monitoring combined with physics-based and data-driven modeling enables the development of digital twins — dynamic representations of structural behavior under real operating conditions. Such frameworks support safety assessment, help define thresholds for normal behavior, and improve early damage detection.

A central challenge lies in understanding the interaction between operational loads (traffic, wind) and environmental influences, particularly temperature, which induces spatially and temporally varying structural responses. This thesis offers two complementary research directions within this framework.

Possible Direction A: Data-Driven Digital Twin Development

Focus: Understanding how operational and environmental conditions influence structural dynamics and embedding this knowledge into predictive models.

Main tasks:

• Analyze real monitoring data to quantify the influence of traffic and environmental conditions on modal properties and structural response.
• Calibrate and validate a physics-based bridge model using measured data.
• Develop a reduced or surrogate model to predict structural behavior under varying operational scenarios.
• Define data-informed indicators and thresholds for SHM applications.

Possible Direction B: Temperature-Induced Structural Dynamics

Focus: Explicit modeling of temperature effects and their impact on monitoring interpretation

Main tasks:

• Develop a Finite Element model incorporating temperature-dependent material behavior.
• Simulate spatially varying temperature fields and evaluate their effect on modal characteristics.
• Compare simulated temperature-induced dynamics with monitoring data.
• Assess how temperature variations may mask or mimic damage-related signatures.
  

Suggested Courses: Structural Identification and Health Monitoring, course on machine learning methods

Suggested Competencies: Python/MATLAB

Improving the design of rotating parts of wind turbines through metamaterial technology

Supervisors: Dr. Vasilis Dertimanis (), Prof. Dr. Eleni Chatzi

Industry Partners: Dr. Luca Sangiuliano, Phononic Vibes

Content

In the context of novel lightweight materials for noise and vibration reduction, Phononic Vibes Srl (https://phononicvibes.com/) is researching, designing and producing metamaterial technology. Metamaterials are often periodic structures, consisting of a host structure with embedded or added resonant structures, leading to superior vibro-acoustic attenuation performance in some tunable frequency ranges, called stop bands. In the following videos, the metamaterial concept is applied structure-borne (https://www.youtube.com/watch?v=DUee93HcPVQ&t) and airborne noise problems.

The resonant structures often have some small features that control their tuned frequency and the dynamic behavior of the entire metamaterial system. Once these resonant structures are applied to rotating systems, the stop band behaviour can be modulated according to the rotation speed to the entire system thanks to the presence of inertial forces (ref. 1). This interesting phenomenon can give rise to new methods to control the dynamic behavior of rotating systems and to reduce the unwanted dynamics.

Rotating parts of wind-turbines are often subjected to extreme dynamic conditions. To ensure the long service life and optimal design of rotating parts of wind-turbines, thus preventing failures and expensive maintenances, the dynamic behaviour of these parts must be thoroughly designed and controlled.

The goal of this master thesis is then to investigate the potential of metamaterial technology applied to the rotating parts of wind turbines to control and preserve their dynamic behaviour. In particular, the student will explore how to exploit the modulation effect given by the inertial forces to tune the metamaterial system to reduce critical dynamic conditions. Analytical and numerical models will be developed by the student to study the physics and to assess the metamaterial performance applied to such systems. The aim is to propose design guidelines to achieve a robust design solution. 

This thesis is in collaboration with Phononic Vibes Srl and is mainly simulation-based.

Suggested Competencies: Python/MATLAB

Advanced Data-Driven Methods for Infrastructure Monitoring and Maintenance Optimization

Supervisors: Dr. Charikleia Stoura, Prof. Dr. Eleni Chatzi 

Industry Supervisor: Dr. Giulia Aguzzi, KISTLER Instrumente AG

Content

Effective monitoring of civil infrastructure is vital for ensuring long-term safety, serviceability, and cost-efficiency. In recent years, the proliferation of multi-sensor systems and the availability of high-fidelity vibration, acceleration, and Weigh-In-Motion (WIM) data have opened new avenues for developing intelligent monitoring frameworks. These advancements present an opportunity to transition from periodic inspections to predictive maintenance regimes, enhancing asset management strategies in transport infrastructure.

This Master’s thesis aims to develop and benchmark modern AI-assisted methodologies for the analysis of real-world monitoring datasets from bridges and rail infrastructure, with data access supported by KISTLER. The work will focus on synthesizing information from various sources, including vibration signals, tilt measurements, and WIM data, to derive actionable insights into the condition and behavior of structures under operational loading.

The scope includes:

• Developing pipelines for data fusion and pre-processing of multi-sensor time series.
• Performing comparative analyses of existing Structural Health Monitoring (SHM) methods and fault detection strategies.
• Evaluating the added value of WIM data in augmenting structural response interpretation and load estimation.
• Exploring machine learning and signal decomposition techniques (e.g., modal analysis, dictionary learning, supervised/unsupervised ML) for enhanced pattern recognition.
• Investigating tilt estimation through acceleration measurements, with potential use in low-cost sensor deployment scenarios.
• Applying insights to optimize rail surface monitoring and recommend maintenance strategies.
  

This interdisciplinary thesis connects experimental data analysis, system identification, and data-driven modeling with strong industrial relevance. Students will have the opportunity to work with cutting-edge sensing technologies and contribute toward the digital transformation of infrastructure maintenance.