Thesis work Early Detection and Classification of Simulation changes using Image & Numerical Data

About this opportunity - Background

We are looking for driven and motivated students interested in pursuing their master thesis within Vehicle Engineering during the spring term 2026.

At Vehicle Engineering our responsibility spans the entire chassis interior climate body & exterior functions mechanical integration and a range of vehicle attributes with impact on design and customer experience of our complete product. Across these domains and all development cycles we will lead an effective delivery operation on complete level in close sync with other Engineering units functions and stakeholders across the company.

This thesis work is within the area of Vehicle Attributes Insight at Vehicle Attributes.

In simulation-based engineering workflows it is essential to identify the impact on performance originating from a particular geometrical change. This understanding plays a crucial role in aerodynamic design optimization in the automotive sector. This is especially important early in the development cycle when the design freedom is relatively high. Simulations provide both quantitative and qualitative information and the performance is typically evaluated based on both visual and numerical outputs such as contour plots isosurfaces section planes and scalar values including the aerodynamic drag coefficient (Cd). Cd values serve as indicators of aerodynamic performance. The difference between a baseline and a new simulation (delta Cd) can be used to evaluate the influence of particular geometrical changes on aerodynamics. Consequently it is beneficial to understand the possible significance of any geometric modification prior to performing simulations. Early classification of such changes e.g. via labeling their impact on aerodynamic performance can accelerate design iterations reduce computational costs and improve decision-making.

Objective:
1. Create a training dataset from historical simulation images and numerical values.
2. Develop a methodology to classify geometric changes based on their impact on aerodynamics using simulation outputs or similarity score values.
3. Implement methodology to automate the classification of new simulations at an early stage.
4. Evaluate the methodology.

Scope of the thesis work

Data collection and pre-processing: gather historical data and label it based on Cd values. Also to consider the image processing generated numerical values with simulation outputs.

Classification: Classify the data at the early stage to detect the magnitude of change.

What youll bring

We see that you have a background in Engineering Mathematics Engineering Physics Statistics Computer Science Data Science or other relevant areas and are at the end of finalizing your masters degree.

You have a strong passion for data science image processing and statistical analysis. Fluency in English is required.

Duration

• Tentative proposed thesis work period: 19th January 2026 to 26th of June 2026 (dates can be flexible with /- 7 days)
• Academic credits: equivalent to 30 ECTS
• This thesis is suitable for 1 Students.