5 papers
Data-driven identification of latent port-Hamiltonian systems
Johannes Rettberg, Jonas Kneifl, Julius Herb +3
Conventional physics-based modeling techniques involve high effort, e.g., time and expert knowledge, while data-driven methods often lack interpretability, structure, and sometimes…
On using Machine Learning Algorithms for Motorcycle Collision Detection
Philipp Rodegast, Steffen Maier, Jonas Kneifl +1
Globally, motorcycles attract vast and varied users. However, since the rate of severe injury and fatality in motorcycle accidents far exceeds passenger car accidents, efforts have…
Multi-Hierarchical Surrogate Learning for Structural Dynamical Crash Simulations Using Graph Convolutional Neural Networks
Jonas Kneifl, Jörg Fehr, Steven L. Brunton +1
Crash simulations play an essential role in improving vehicle safety, design optimization, and injury risk estimation. Unfortunately, numerical solutions of such problems using sta…
Improved a posteriori Error Bounds for Reduced port-Hamiltonian Systems
Johannes Rettberg, Dominik Wittwar, Patrick Buchfink +3
Projection-based model order reduction of dynamical systems usually introduces an error between the high-fidelity model and its counterpart of lower dimension. This unknown error c…
Randomized Symplectic Model Order Reduction for Hamiltonian Systems
Robin Herkert, Patrick Buchfink, Bernard Haasdonk +2
Simulations of large scale dynamical systems in multi-query or real-time contexts require efficient surrogate modelling techniques, as e.g. achieved via Model Order Reduction (MOR)…