Open semester project and master thesis opportunities for students:
The student will investigate the use of physics-enhanced graph neural networks for electrical distribution system state estimation. The focus will be on sim-to-real transfer from conventional state estimation, defining the physics-enhanced model, and on detecting anomalies based on a designed anomaly score.
Keywords: Multi-variate Time Series, Anomaly Detection, Graph Neural Networks, Complex Industrial Systems, Machine Learning, Artificial Intelligence, Sim-to-real Transfer, Neural State Estimation, Neural Simulation
You can apply via SiROP or directly contact Raffael Theiler
The student will work on the topic of unsupervised domain adaptation on the industrial dataset for anomaly detection. The primary focus will be on using variational autoencoders (VAEs) as a model for anomaly detection and evaluating its transferability using different domain adaptation techniques. The goal of this project is to achieve robust detection on new systems with small datasets by aligning the data distribution through domain adaptation.
Keywords: anomaly detection, domain adaptation, variational autoencoders (VAE), deep learning
You can apply via SiROP or directly contact Han Sun
In this work the student will attempt to adopt the deep operator learning techniques to prepare a surrogate model for shape optimization process.
Keywords: operator learning, DeepONet, shape optimization, level set function
You can apply via SiROP or directly contact Sergei Garmaev.
In this project the student will attempt to embed relevant physics priors in graph neural networks (GNNs) with the goal of developing an inverse modeling framework for the prediction of the underlying material model of a system, given the labeled input (load/excitation) and the output (mechanical response) data.
Keywords: Graph neural networks, Physics prior, finite element method
You can apply via SiROP or directly contact Vinay Sharma.
The student will investigate the use of Graph Neural Networks for anomaly detection in time series data of industrial systems. The focus will be on developing a novel approach that leverages GNNs to infer graph structures from heterogeneous sensor signals and detect anomalies based on a designed anomaly score. The proposed model will be evaluated on benchmark datasets and compared to state-of-the-art methods.
It is not required that the student has worked with GNNs before, but the student should have basic prior knowledge in deep learning and python programming.
You can apply via SiROP or directly contact Mengjie Zhao.
The primary goal of this project is to develop an RL-based solution based on graph grammar for automated robot design, and if possible, combine it with controller design or optimization. To achieve this, the project will involve the following tasks:
- Conduct a comprehensive literature review on robot design optimization and control optimization.
- Develop an RL-based framework for automated robot design and control optimization
- Implement and evaluate the proposed method on a simulated robot platform.
- Document the findings and contribute to research publications on the topic of RL and robotics
You can apply via SiROP or directly contact Yuan Tian.
The goal of this project is to investigate domain adaptation techniques for different dynamics in reinforcement learning, with a specific focus on industrial systems. The project will involve the following tasks:
- Conduct a comprehensive literature review on domain adaptation in reinforcement learning, identifying the key differences and challenges compared to other areas such as computer vision.
- Develop a theoretical framework for domain adaptation in RL, focusing on the adaptation to different dynamics and compared with other methods.
- Implement and evaluate the proposed method on general RL benchmark, and if possible, simulated environment of industrial systems.
- Document the findings and contribute to research publications on the topic of domain adaptation in reinforcement learning.
You can apply via SiROP or directly contact Yuan Tian.
The aim of the master thesis is to investigate novel sensor fusion techniques able to merge multiple sensor modalities in one consistent 3D representation. Getting the data on buildings is the most difficult part of any building evaluation. The current state of the art (e.g., photogrammetry) necessitates a large amount of data covering the whole structure to obtain precise models. Our aim is to simplify data collection without penalizing model quality and to do it in multiple sensor modalities.
The focus will be on thermal and RGB images, but the methods developed should not be limited to that. Our previous research is based on Nerf models which can, from a sparse set of images, generate novel images from unseen points of view. Based on this technology, you will develop state of the art method to understand how to best integrate modalities other than RGB in the model. The results will be used to improve and facilitate building renovations.
Contact: Dr. Malcolm Mielle
malcolm.mielle@schindler.com
+41793672336
The aim of the master thesis is to develop algorithms to do semantic segmentation of building facades and calculate the windows–to–wall ratio (WWR)—an important number since windows are usually the weakest link in energy loss. The WWR is an important number for retrofit consultants as part of their assessment uses this ratio. However, calculating it is time–consuming since experts need to come in person to do the measurements.
The existing state–of–the–art methods to calculate the WWR achieve an F1 score of 0.73 (the benchmark is described in this paper: Touzani, Samir et al. “A machine learning approach to estimate windows–to–wall ratio using drone imagery.” Remote Sensing (2021) and found here and we aim to beat this! Previous work by Schindler achieves a higher F1 score but is cumbersome to use; this master thesis will focus on simplifying the pipeline to segment a facade, perform a more accurate and comprehensive segmentation of the façade, and calculate the WWR. You will work on data collection and model development. The data will be collected on campus using phone and thermal cameras. Since the WWR depends on semantic information about the facade and the geometry of the building, you will be working on both 2D images and 3D point clouds.
Contact: Dr. Malcolm Mielle
malcolm.mielle@schindler.com
+41793672336
In the context of this Master’s thesis, conducted in cooperation with Kistler (https://www.kistler.com/) and supervised by the IMOS lab (https://www.epfl.ch/labs/imos/) at EPFL, the student will have the opportunity to work on solving the challenges related to both the heterogeneity of sensor data and the crucial temporal relationships between sensors in bridge systems. The thesis will explore strategies to effectively handle the diverse sensor data generated by different sensor types, such as accelerometers and strain gauges, which possess distinct signal characteristics. Additionally, the thesis will delve into capturing the crucial temporal relationships by investigating the incorporation of temporal encoders, specifically those found in spatio-temporal Graph Neural Networks (GNNs). These encoders will be used to model and account for the dynamic dependencies within and between sensors. By developing and implementing innovative solutions, the student aims to enhance the accuracy and effectiveness of GNN-based analysis in monitoring bridge structural behavior.
An important aspect of the thesis is sensor anomaly detection, as it plays a vital role in ensuring the reliability and safety of bridge structures. The student will explore techniques within the GNN framework to identify and distinguish abnormal sensor behavior, enabling early detection of potential structural issues. By integrating anomaly detection capabilities into the GNN-based analysis, the thesis aims to improve overall monitoring and maintenance strategies for bridge structural health. Throughout the thesis, the student will have access to both benchmark datasets for method development and real industrial data provided by Kistler. This unique opportunity allows for the evaluation of the proposed model in real-world scenarios and provides valuable insights into the practical application of GNN-based Bridge SHM.
You can apply via SiROP or directly contact Mengjie Zhao.
The main tasks of this research project involve exploring graph construction and graph learning methods in the context of district heating networks. The project will start with a comprehensive literature review to gain insights into the existing methods and techniques used in graph signal processing and their application to district heating networks. This will provide a solid foundation for understanding the underlying principles and approaches. Based on the literature review, the project will propose a novel physics-informed graph construction method tailored specifically for district heating networks. This method will incorporate domain-specific knowledge and physics-based constraints to accurately capture the relationships between different nodes in the network. The proposed graph construction method will be evaluated and compared with existing approaches to assess its effectiveness and advantages.
Next, the project will focus on applying graph signal processing techniques to address common inverse problems encountered in district heating networks, such as denoising, imputation, and interpolation. These tasks are essential for improving the quality of the data, filling in missing values, and enhancing the accuracy of predictions or estimations.
It is not required that the student has worked with GSP before, but the student should have prior knowledge in signal processing, python programming, linear algebra, and mathematical optimization.
You can apply via SiROP or directly contact Keivan Faghih.