Thesis in the field of development of an AI-based component protection function in the electric drive train from September 2024

To further optimize the range of electrically powered vehicles, the permanently excited synchronous machine (PSM) on the front axle is equipped with a disconnect unit (DCU). This intelligent disconnection system makes it possible to decouple the front axle fully automatically and depending on the situation. This measure reduces drag losses to a minimum and thus contributes to extending the range by only using the rear axle for the drive (source: Mercedes EQE SUV with disconnect unit - JESMB).

However, certain driving situations can lead to increased mechanical stress, which could potentially affect the DCU. To prevent this, the DCU must be opened proactively. The current approach is based on a logic-based method. However, the implemented algorithm occasionally leads to unnecessary openings (false positives) of the DCU, which can affect the lifetime.

The aim of this work is therefore to investigate when it makes sense to use AI systems instead of conventional approaches in the powertrain. To this end, machine learning is to be used to optimize the opening behavior of the DCU and limit it to driving situations that are actually relevant. This could be achieved, for example, by taking other relevant features into account. Finally, the extent to which the existing analytical approach can be replaced or supplemented by an AI-based model will be evaluated.

The work includes the following tasks:

• Familiarization with the use case and the logic already implemented
• Selection of additional input signals that may be relevant for the DCU opening
• Formulation of requirements for recording measurement data
• Selection and implementation of a suitable machine learning method with a focus on recurrent neural networks
• Validation and documentation of the results

The final topic is determined in consultation with the university, you and us.

Master's degree in engineering, computer science, mathematics, data science or a comparable course of study

Language skills: Very good written and spoken German and English skills

Other knowledge:

• Very good knowledge in the field of machine learning
• Good knowledge of Python and data science libraries

Personal skills: Structured and independent work, communication skills, commitment, creativity and initiative

Additional information:

Of course, we are not completely without formalities. Please apply online only and enclose a CV, current certificate of enrolment stating the semester of study, current transcript of records, relevant certificates (max. total size of attachments 5 MB) and mark your application documents as "relevant for this application" in the online form.

Further information on the recruitment criteria can be found"here".

Nationals from countries outside the European Economic Area should send their residence/work permit with their application.

We particularly welcome online applications from severely disabled persons and persons with equivalent disabilities. If you have any questions, you can also contact the site's representative for severely disabled employees at sbv-sindelfingen@mercedes-benz.com, who will be happy to support you in the further application process after your application.

Please understand that we no longer accept paper applications and that there is no entitlement to return postage.

If you have any questions about the application process, please contact HR Services by e-mail at myhrservice@mercedes-benz.com or by phone: 0711/17-99000 (Monday to Friday between 10 a.m. - 12 p.m. and 1 p.m. - 3 p.m.).