Bachelor-/Masterthesis: Using Artificial Intelligence (AI) (incl. Machine Learning / Computer Vision etc.) for Digital Twin Services
A digital twin of an original is a software that consists of a set of models of the system, a set of digital shadows (data traces), and provides a set of services to use both purposefully with respect to the original system. Artificial intelligence (AI), including computer vision and machine learning, can play a crucial role in enabling these services, for example in the following applications:
- Screw detection in images and point clouds for the disassembly of battery packs
- Microstructure image analysis in material science to predict material properties
Your Tasks
- Apply computer vision and machine learning techniques to research intelligent services for digital twin systems
- Design and implement well-engineered software, including:
- Clean, modular code
- Unit/integration tests
- Documentation
What We Offer
- Creative freedom to contribute your own ideas, preferences, and approaches
- Involvement in interdisciplinary real-world problems with immediate practical applications
- Access to supervision with expertise in:
- Computer vision and machine learning
- Software engineering
- Application-specific domain knowledge (e.g., materials science, mechanical systems)
- Possibility to generate new datasets on top of existing ones if needed for training or fine-tuning machine learning algorithms
- Opportunities for publication may be explored
Your Profile
- Bachelor’s or Master’s student in Computer Science or a closely related field
- Students from:
- Faculty 5 – Georesources and Materials Engineering
-
Faculty 4 – Mechanical Engineering
are also encouraged to apply — strong programming skills are a necessary precondition (e.g. experience in Python, Deep Learning)
- Comfortable working with real-world data
- Motivated, proactive, and independent
- Good communication skills (German or English)
How to Apply
For more information or to apply, please send your application documents to: Henrik Thillmann 📧 thillmann@se-rwth.de