Student Machine learning based methodology for spatial distribution of brake wear emissions (Stuttgart)

The Institute of Vehicle Concepts (FK) of the German Aerospace Centre (DLR) is internationally recognized for the design of future road and rail vehicles that enable climate and environmentally friendly mobility while being affordable and user-friendly at the same time.

We research and demonstrate the required key technologies and maintain close cooperation with other scientific institutions as well as industrial and political bodies.

What to expect

The research field "Vehicle Systems and Technology Assessment" offers a master thesis within the DLR project 3LK, focusing on the characterization and spatial distribution of brake wear emissions from passenger cars.

Brake wear is an important source of non-exhaust particulate matter from road transport. The amount of brake wear generated depends on several factors, including vehicle characteristics, driving behavior, traffic conditions, and braking energy.

The aim of this thesis is to develop a scenario-capable, machine learning based methodology to estimate and spatially distribute passenger car brake wear emissions within urban road networks. The work will combine models describing the relationship between braking energy and brake wear with machine learning approaches for predicting the spatial distribution of braking energy within cities.

Your tasks

• Literature research on passenger car brake wear, braking energy, brake wear emission models, and the influence of vehicle and braking system technologies
• Development of scenarios describing current and potential future passenger car braking systems, including the influence of regenerative braking and vehicle electrification
• Review and aggregation of existing models relating braking energy to brake wear emissions and identification of suitable model formulations for different vehicle and braking system scenarios
• Collection, processing, and aggregation of input data relevant for estimating braking energy, such as road network characteristics, traffic information, vehicle characteristics, and other spatially resolved data
• Development and testing of machine learning models to predict the spatial distribution of braking energy within an urban road network
• Integration of braking energy and brake wear models to estimate spatially resolved passenger car brake wear emissions
• Development of a scenario-capable methodology for estimating future brake wear emissions under different vehicle fleet and braking system assumptions. Evaluation and validation of the developed methodology using suitable urban case studies and available data

Your profile

• Studies in the field of mechanical engineering, automotive engineering, environmental engineering, informatics, data science, or related courses
• Experience or strong interest in machine learning, data analysis, and modeling
• Interest in vehicle technology, brake wear, transport emissions, and data science applications in transport research
• Programming knowledge in Python, including machine learning and data analysis libraries
• Basic knowledge of statistics, numerical modeling, or machine learning
• Fluent expression in English and basic knowledge of German

We look forward to getting to know you!

If you have any questions about this position (Vacancy-ID 6474) please contact:

Ms. Isheeka Dasgupta

Tel.: +49 176 / 878 364 54