Master's Thesis Machine Learning Models for Data Preparation

Location: Graz / asap / duration 6 months

Are you currently pursuing a master's degree with a technical focus and looking for a partner company to write your thesis?

Perfect! Magna Steyr is currently seeking a master's student to join us in the area of Computational Fluid Dynamics (CFD) and machine learning (ML).

The aim of this master's thesis is to accelerate the data preparation process for comprehensive vehicle CFD simulation.

Data preparation is the bottleneck in current industrial CFD processes.

Preparing a complete vehicle geometry for external or internal flow investigation keeps an engineer busy for several days.

To speed up data preparation, a machine learning model should be developed to automate some portions of this process (e.g., mesh cleaning, part classification).

You will work together with CFD engineers as well as our machine learning experts and project engineers.

The following scopes should be included in your master's thesis:

• Conduct a literature review of previous works and define a schematic procedure.
• Prepare a training database in ANSA. Either from historical or public data.
• Research of various neural network architectures which can be considered for this application (e.g., 3D point- and mesh-based models).
• Create a first model and train it with the previously created dataset. Optimize the model setup if necessary.
• Create documentation and propose additional work to speed-up data preparation.