We are the Chair of Vehicle Mechatronics at Technische Universität Dresden, specializing in battery research. Our work addresses key challenges in battery engineering, such as modelling the electrical, thermal, and ageing behaviour based on laboratory and fleet data, using various modelling approaches (empirical, data-driven, and physical).

We offer topics in this field across multiple disciplines, including electrical, mechanical, and software engineering.

The aging of lithium-ion batteries is a complex process influenced by numerous physical, chemical, and mechanical effects. The scientific literature contains a wealth of expertise on these aging mechanisms—spread across countless papers, often documented in varying levels of detail and
under different experimental conditions.

At the same time, physical battery models enable numerical approximation of the electrochemical processes inside the cell. These models simulate processes such as ion transport, reaction kinetics, or heat generation.

The planned AI Battery Expert aims to connect these two worlds:

• From the literature: capture a broad range of aging-relevant effects and their associated physical parameters (e.g., particle size, electrode thickness).
• From simulation: use effects simulated with PyBaMM (Python Battery Mathematical Modelling) for validation and cross-comparison.

This will create a system that both deepens understanding of the relationships between model parameters and aging behavior, and highlights where models deviate from or need to be complemented by the reality documented in the literature.

The goal of this thesis is to design and implement a modular Retrieval-Augmented Generation (RAG) system for an AI Battery Expert that combines literature knowledge with simulation data.

More Informations:

especially for degree programs in Computer Science, Computational Modelling and Simulation,
Electrical Engineering, Mechatronics, and Mechanical Engineering with prior knowledge of Machine
Learning

• Interest in scientific research
• Interest in modelling across various domains
• Willingness to learn new topics (e.g., battery technology)

Please send your application, including a CV and your transcript of records, to the mentioned contact. We’ll be in touch.