Master Thesis Machine Learning for retired Lithium-Ion Cell Sorting (all genders)

Our team at Fraunhofer LBF conducts research into solutions for the design of sustainable materials, structures, and systems, as well as circular economy strategies that meet the highest standards of reliability, efficiency, and resilience. Would you like to be part of this inspiring team? We look forward to receiving your application!

Master Thesis Machine Learning for retired Lithium-Ion Cell Sorting (all genders)
Darmstadt

As electric mobility continues to expand globally, sustainable recycling and second-life utilization of traction batteries are becoming increasingly critical. At Fraunhofer LBF, we are developing an automated disassembly system for electric vehicle batteries. A key component of this process is the rapid and reliable evaluation of individual cell health.

The master thesis focuses on the development of a machine learning model for the automatic sorting of used lithium-ion cells based on custom electrochemical impedance spectroscopy (EIS) data. The objective is to build a model that processes EIS measurements and assigns cells to the appropriate sorting category. The sorted cells are subsequently grouped according to their intended secondary use.

A dataset for training and testing the model will be provided. In addition, the thesis should investigate how different types of EIS data influence sorting accuracy and model performance.