A promising technology investigated at the Institute of Energy Technologies - Fundamental Electrochemistry (IET-1) is the reversible Solid Oxide Cell (rSOC), which enables the efficient conversion of electrical energy into hydrogen and vice versa. Coupled with renewable energy sources such as solar and wind power, rSOC systems play an important role in future sustainable energy infrastructures. However, the fluctuating nature of renewable generation subjects these systems to dynamic operating conditions, creating significant challenges for control, efficiency, and long-term durability.

Join our team Master Thesis – Data-Driven System Identification for Dynamic Modeling of rSOC-Systems

In previous projects, a detailed dynamic model of the system was developed based on first-principle (white-box) approaches. While such models provide valuable insight, advanced model-based control methods such as Model Predictive Control (MPC) are often limited by discrepancies between the nominal model and the actual system behavior. The objective of this thesis is to improve model accuracy through data-driven modeling and parameter estimation techniques. A comprehensive experimental dataset is already available, with the possibility of conducting additional experiments if required. Potential approaches include data-driven parameter estimation for white-box models, the development of black-box models using machine learning methods (e. g., neural networks) and their combination (grey-box). The thesis offers the opportunity to work on state-of-the-art research at the interface of control engineering, system identification, machine learning, and sustainable energy systems while contributing to the advancement of hydrogen technologies for the energy transition.

Your responsibilities within the team:

• Literature review and familiarization with rSOC, with focus on operation and degradation as well as existing data and experimental setup
• Literature review on dynamic modeling (system identification), especially data-driven approaches and comparison of past system identification for rSOC
• Development of the digital twin of the rSOC system. Validation on experimental and simulation data.
• Analysis of results: Potential comparison of different system models regarding performance, adaptability and real-time applicability. The comparison can include the integration of the model in the current model-based control approach. Opportunity to contribute to a scientific publication

• Currently pursuing a master’s degree in automation engineering, process engineering, mechanical engineering or a comparable field of study
• Strong interest in control engineering, system dynamics and mathematical modeling
• Knowledge in advanced control methods such as nonlinear control preferred
• Experience in programming (especially Matlab/Simulink) is preferred
• Ability to take initiative and work independently
• Excellent collaboration and communication skills, as well as the ability to work as part of a team
• Very good command of written and spoken English with extensive vocabulary is required (at least B2 level according to the CEFR), ideally supported by a certificate confirming the language level. Knowledge of the German language is not mandatory but certainly appreciated