Master Projects
Please submit your topic of choice by filling out the form below:
Stability assessment of lighting poles based on natural frequency
Supervisors: Konstantinos Vlachas (, ETHZ), Fabian Wespi (Schweizer Prüfstelle für Elektrotragwerke GmbH), Prof. Dr. Eleni Chatzi
Content
The Swiss testing laboratory for electrical structures tests the stability of street lamps and sports field masts in Switzerland by means of a natural frequency measurement and a design calculation. In previous bachelor theses, a Python-based calculation tool was created to determine the natural frequencies. In this work, the following hypothesis is to be examined: The comparison of the calculated and measured eigenmodes and their ratios can be used to assess the stability of the masts.
Tasks
- Build a mobile measuring device that can measure the natural vibration of a mast and localize the mast location (e.g. with Rasperry PI or Arduino, ideally with Python programming and with acceleration and GPS sensors).
- Program a recording sequence in which the vibration of the mast is measured for 20 seconds, for example (two measurements are required: x and y direction)
- Calculate the natural frequencies of the mast system from the measured vibration sequence.
- Describe the relationship between the mast restraint and the natural frequencies.
- Describe which parameters influence the ratio of the natural modes.
- Determine whether the input of certain parameters can be dispensed with by measuring the natural frequencies of the mast system, since they can be derived from the natural mode ratios
- Determine whether damage to the mast or foundation can be determined based on knowledge of the measured and calculated natural modes.
- Determine what influence the damping of the natural vibration of the masts has on stability.
Suggested Courses: Structural Identification and Health Monitoring
Possible to select as: obligatorishce Projektarbeit, praktische Projektarbeit, forschungsbezogene Projektarbeit
Limitation of offerings: 2 students (group work is possible)
Real-time control of MIMO force estimation for Model-Experiment Convergence and Visualization using Augmented Reality
Supervisors: Kostas Vlachas (), Prof. Dr. Fernando Moreu (University of New Mexico), Prof. Dr. Eleni Chatzi
Content
Replicating system response in the lab is done by characterizing the system dynamics with multiple inputs and multiple outputs (MIMO). System ID is obtained in terms of a full order FRF matrix with uncorrelated, random inputs at each input location. The FRF matrix is then inverted, using the Moore-Penrose pseudoinverse process with Tikhonov regularization. The desired response, in terms of a spectral density matrix (SDM), is then used in conjunction with the inverted FRF matrix to find an input. The input is applied experimentally, and the difference between the desired SDM and the experimental SDM is used to iteratively update the input. Filling in the cross terms in the response SDM, inverting the FRF matrix, and quantifying error are ongoing challenges in inverse MIMO.
Real-time control of inputs is seldom done in inverse MIMO, with iterations typically being done in separate experiments and without model updates. Visualization of error between the estimation and the actual response is in general the best assessment for a successful experimental framework after System-ID is achieved.
The experimental system currently available is a 3-story frame structure with up to 3 input locations and up to 6 output locations. Inputs are applied with uniaxial electrodynamic actuators, and outputs are collected with uniaxial accelerometers. Although many inputs and outputs are available, results will be validated on a simple case first, with 2 inputs and 2 outputs.
This project will investigate model update based on real-time experimental results and its projection using Augmented Reality for humanin-the-loop investigation. The updated model will be used to update inputs in real-time as well to better match the response SDM with human visualization of the model. This result will be used to achieve faster error convergence, reduce the number of tests needed, and minimize input forces.
Expected outcomes of project:
- Theory development: dynamic simulations of MIMO
- System ID based on multiple inputs and multiple outputs (MIMO)
- Physics-based, reduced order model based on system ID
- Real-time model update based on instantaneous difference between reference and real spectrum
- Augmented Reality programming of dynamics and real-time simulation connection with AR and experiment
- Error quantification (frequency domain, time domain, etc.) and iterative input update process
Suggested Courses: Structural Identification and Health Monitoring
Suggested Competencies: Python/MATLAB, Strong background on programming with an interest on human-in-the-loop and structural dynamics is recommended.
Possible to select as: obligatorishce Projektarbeit, praktische Projektarbeit, forschungsbezogene Projektarbeit
Limitation of offerings: 2 students (group work is possible)
Further open for: master students with background of computer science, electrical engineering, mechanical engineering, civil engineering, or related.
Optimal inspection and intervention planning for maximizing life and minimizing environmental impact of road infrastructure
Supervisors: Dr. Yunus Emre Harmanci (, Empa), Lukas Kramer (Empa), Prof. Dr. Eleni Chatzi
Content
Optimal inspection and maintenance planning of road infrastructure is a challenging process, since decision-making needs to be made on the basis of uncertain observations of various origin. These uncertainties are linked to some level of uncertainty relating to varying environmental and loading conditions, modelling errors, inefficiency of the measuring system and so on. Although this issue spans over several disciplines, including social sciences, it is also quite commonly met within an engineering framework. The goal of this project is to build an optimal inspection/maintenance framework for different bridge materials and typologies, maximizing their service life and minimizing environmental im-pact, and address the challenges of infrastructure management. Thus, the student will work on some of the following objectives depending on their interest:
• Review established and state-of-the-art non-destructive-testing and rehabilitation methods and derive indications on which methods work better for which different bridge typologies/materials
• Utilize existing finite element models (in SoFiSTiK) of various bridge types to simulate various short-and long-term effects.
• Explore decision processes frameworks for modeling decision making in situations with partly random or decision-dependent outcomes.
Suggested Courses: Depending on interest: Method of Finite Elements (or similar) and/or Non Destructive Evaluation & Rehabilitation of Existing Structures
Suggested Competencies: Basic knowledge on MATLAB or Python
Possible to select as: obligatorishce Projektarbeit, praktische Projektarbeit, forschungsbezogene Projektarbeit
Limitation of offerings: 2 students (group work is possible)
Algorithm development for reliable structural health monitoring
Supervisors: Dr. Giulia Aguzzi (Kistler Instrumente AG), Prof. Dr. Eleni Chatzi ()
Content
Structural health monitoring of civil infrastructures relies on accurate and reliable monitoring systems - i.e., sensors, cables, data acquisition systems - to continuously record and store the structure response. The effective operation of such measurement systems is a key factor enabling engineers to draw meaningful insights into a structure's condition. However, multiple factors, such as weather conditions, electromagnetic interference, or mounting errors, can affect the operation of these systems, potentially resulting in device misoperation that ultimately compromises the reliability of the collected data.
In this project, you will contribute to enhancing the reliability of the measurement chain by developing a Machine Learning algorithm specifically designed to monitor real-time signals and promptly identify any abnormal behavior.
If your interest lies more in structural dynamics, there is also the possibility to develop algorithms for the structural dynamic identification of bridges. These will then be validated using a dataset obtained from an infrastructure currently monitored with a Kistler measurement system
Possible to select as: obligatorishce Projektarbeit, praktische Projektarbeit, forschungsbezogene Projektarbeit
Limitation of offerings: 2 students (group work is possible)
Further open for: master students with background in computer science, electrical engineering, mechanical engineering, or related.
Physics-Informed Neural Networks for System Identification: Predicting Acceleration Time Series from Electrical Inputs in End-of-Production-Line Actuator Testing
Supervisors: Dr. Roman Klis (Johnson Electric), Prof. Dr. Eleni Chatzi ()
Content
This master thesis aims to employ physics-informed neural networks (PINNs) to enhance the predictive capabilities of end-of-production-line actuator testing. The testing station currently captures both electrical and vibration time series data during various tests stages. The focus of this research is on utilizing PINNs to predict acceleration time series responses using the available electrical input readings. The study incorporates system identification techniques to improve the accuracy and interpretability of the neural network predictions.
Objective:
The primary objective of this research is to investigate the application of physics-informed neural networks in the context of end-of-production-line actuator testing. Specifically, the study aims to:
- Explore the existing challenges in predicting acceleration responses in the actuator testing process using traditional methods.
- Develop a physics-informed neural network model capable of predicting acceleration time series data from electrical input readings and observed outputs.
- Incorporate system identification techniques to enhance the interpretability and understanding of the neural network model.
- Evaluate the performance of the proposed model in terms of accuracy, efficiency, and robustness under various testing conditions.
- Provide insights into the practical implementation of physics-informed neural networks for predictive modeling in industrial testing scenarios.
Methodology:
The research will involve a combination of literature review, data preprocessing, model development, and empirical analysis. The study will begin with a thorough review of existing literature on predictive modeling, physics-informed neural networks, and system identification. Subsequently, a physics-informed neural network model will be developed and trained using the available electrical and vibration time series data from the end-of-production-line actuator testing. System identification techniques will be integrated to improve the model's interpretability. The model's performance will be rigorously evaluated and compared against traditional methods.
Johnson Electric (JE) and ETH are working together to develop a proof-of-concept tool that would solve the described problem.
Possible to select as: obligatorishce Projektarbeit, praktische Projektarbeit, forschungsbezogene Projektarbeit
Limitation of offerings: 2 students (group work is possible)
Further open for: master students with background of material science, computer science, electrical engineering, mechanical engineering, civil engineering, or related.
