Bachelor’s / Master’s Thesis: Development of surrogate models for describing oil flow in rolling bearings

Website Institute of Machine Elements and System Engineering
The Institute for Machine Elements and System Development researches the fundamental structural and tribological behavior of machine elements and represents this behavior in experimentally validated model descriptions. These models are used to analyze and design the functional, loss, and noise behavior of complete technical systems, with a focus on drive technology. Additionally, the developed models support the research and development of methods in Model-Based Systems Engineering (MBSE) as a key element in future industrial product development processes.
The flow processes in rolling bearings significantly influence friction behavior, lubricant distribution, and ultimately the service life of the components. While CFD simulations can be used for precise analysis, their application in a system context is limited due to high computational costs. The aim of this work is to develop efficient CFD surrogate models that can describe the relevant flow behavior at various levels of abstraction.
To achieve this, systematically simplified models will be developed based on existing numerical and experimental data, which efficiently reproduce the effects of bearing flow on the surrounding system. In addition, methods such as dimensional analysis, reduced-order models (e.g., POD), and AI-based approaches (e.g., regression models or neural networks) will be applied to reliably approximate the input-output behavior of bearing flows.
Tasks:
- Research on surrogate modeling approaches in fluid mechanics
- Systematic reduction of geometry and model complexity (hierarchical surrogate models)
- Application and comparison of methods such as POD, dimensional analysis, or machine learning
- Development and implementation of flow-based surrogate models
- Validation using CFD and experimental data
Requirement:
- Interest in fluid mechanics, modeling, and data-driven methods
- Experience with CFD can be helpful (not required)
- Basic knowledge of Python and machine learning is an advantage
- Independent and structured working style
We offer:
- Flexible design of work focus
- Quick processing possibilities
- Intensive support
- Immediate start or by arrangement
- Very good working atmosphere
We look forward to your application by email:
Amirreza Niazmehr, M. Sc. RWTH
Institute of Machine Elements and System Engineering
Schinkelstraße 10, 52062 Aachen
amirreza.niazmehr@imse.rwth-aachen.de
Um sich für diesen Job zu bewerben, sende deine Unterlagen per E-Mail an amirreza.niazmehr@imse.rwth-aachen.de