Master Thesis Application of Physics-Informed Machine Learning for Grid-Tied Inverter Control

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

Responsibilities

As a part of your Master thesis, you will develop a physics-informed current controller for grid-tied inverter control.; You will evaluate the linear regulator and the predictive controller as reference points, as well as establish their boundaries.; In addition, you will research current AI-based implementations in the literature.; Furthermore, you will be responsible for developing a concept to improve the implementation of AI-based black boxes and mitigate their drawbacks in grid-tied inverter applications.; Last but not least, you will select an AI-based concept, which may include machine learning, recurrent neural networks or reinforcement learning. If necessary, you will model the system alongside the implemented controller.

Requirements

Education: Master studies in the field of Engineering, Mathematics, Information Technology or comparable; Experience and Knowledge: in the application of AI methods, system modelling and control engineering, in power electronics advantageous; Personality and Working Practice: you are a team player with good communication skills who is able to work independently, proactively and meticulously; Work Routine: office and laboratory work required, partially mobile working possible; Languages: good in English