Henning Schwarz

Associated PhD Student
Address
Office
Contact
Project
Development of decision support systems for predicting dynamic aircraft ditching
The PhD is concerned with predicting the loading and deformation of aircraft fuselages during ditching. Emphasis is given to the structural response part and the two-way fluid structure interaction, which involves learning (approximated) physical laws. To this end, combinations of advanced engineering tools with machine learning methods, i.e. convolutional autoencoder and long-term short-term memory approaches, and classical order-reduction approaches, e.g. singular value decomposition and approximations to the Koopman operator, will be used. The central aim is to learn the deformation behaviour during this crash-similar scenario and provide a reliable, interpretable model to be used in near-to real time, two-way coupled fluid structure simulations of aircraft ditching. The research is of relevance for investigating the design of future hydrogen powered aircrafts and supports the aircraft certification under chapter CS 25.801, cf. LINK: https://www.easa.europa.eu/en/document-library/easy-access-rules/online-publications/easy-access-rules-large-aeroplanes-cs-25?page=27.
Advisor: Prof. Dr. Thomas Rung
Co-Advisor: Dr. Jens-Peter M. Zemke
Publications
Information are coming soon!
Talks/Poster
22.-24.11.2023
6th Int. Workshop on Model Reduction Techniques (MORTech): "Comparison of LSTM and Koopman-operator approaches for predicting transient ditching loads", Paris, France