Master Thesis AI-based Power Electronics Control

About the role

This master thesis focuses on developing next‑generation closed‑loop control algorithms for highly non‑linear power electronic converters used in e‑mobility, robotics and data‑center applications. You will work with an existing simulation model of Bosch's next‑generation charger/converter topologies.

Key responsibilities

• Select a promising control concept and design a tailor‑made strategy using the provided simulation model.
• Investigate advanced control methodologies such as Model Predictive Control, neural‑network‑based control and reinforcement learning.
• Implement the chosen algorithm in a simulation environment (MATLAB/Simulink, Python or PLECS).
• Validate and benchmark the controller under realistic operating conditions, assessing transient behavior, efficiency and stability.
• Analyse execution effort, dynamic response, robustness to parameter variations and suitability for real‑time implementation.
• Document the research findings and present the results.

Required profile

• Enrolled in a Master program in Electrical Engineering, Control Theory, Mechatronics, Cybernetics, Computer Science or a comparable field.
• Strong background in control systems (state‑space, non‑linear, predictive/modern control methods).
• Proficiency with simulation tools such as MATLAB/Simulink and/or Python, including machine‑learning frameworks like PyTorch.
• Knowledge of power electronics (AC/DC and DC/DC converters) is an advantage.
• Goal‑oriented, motivated and solution‑focused mindset.
• Business‑fluent in English or German.

Required skills

• MATLAB/Simulink
• Python
• PyTorch
• PLECS
• Model Predictive Control (MPC)
• Neural Networks
• Reinforcement Learning (RL)
• Control Systems
• Power Electronics