Pedro John
DC14: Development of an NH3-H2 engine digital twin based on heterogeneous multi-fidelity and system level simulation data
The transition to low-carbon propulsion requires new engine concepts capable of operating with alternative fuels such as hydrogen and ammonia. My research focuses on developing a digital twin for NH₃–H₂ combustion systems to support the design and optimization of next-generation engines.
To achieve this, I will combine high-fidelity CFD simulations (RANS and LES) with machine-learning techniques to create a data-driven reduced-order model that reproduces complex combustion dynamics with significantly lower computational cost. This includes generating and managing simulation datasets, applying dimensionality-reduction methods, and training models using approaches such as Gaussian Process Regression and neural networks.
Supervisor Dr Filippo Aglietti hosted by
1st secondment: academia hosted by
About me
After completing my Bachelor’s degree at the University of Stuttgart, I developed a strong interest in the field of fluid mechanics. To deepen my knowledge in this area, I decided to pursue a double Master’s degree (DMD) in 2023 at the University of Stuttgart in collaboration with Chalmers University of Technology in Gothenburg. During the first year of my Master’s program in Stuttgart, I focused on vehicle propulsion systems and their various configurations. During my second yearin Gothenburg, I had the worked on a six-month engineering project focused on machine learning-based optimisation for battery pack cooling, where I automated simulations and prepared data for further use.
Through the MSCA Doctoral Network, I aim to deepen my knowledge in the field of machine learning, expand my network of people working on similar topics, and, in the long term, contribute to reducing CO2 emissions.
I am excited to contribute to the development of cleaner propulsion technologies while collaborating with researchers across Europe as part of the MSCA network.