Research Seminar on AI: Training Data Selection for Machine Learning-Enhanced Monte Carlo Simulations in Structural Dynamics
- +49 241 80 94601
- E-Mail schreiben
Dienstag, 22.03.2022, 16.00 Uhr
The evaluation of structural response constitutes a fundamental task in the design of ground-excited structures. In this context, the Monte Carlo simulation is a powerful tool to estimate the response statistics of nonlinear systems, which cannot be represented analytically. Unfortunately, the number of samples which is required for estimations with high confidence increases disproportionally to obtain a reliable estimation of low-probability events. As a consequence, the Monte Carlo simulation becomes a non-realizable task from a computational perspective. It has been shown that the application of machine learning algorithms significantly lowers the computational burden of the Monte Carlo method. We use artificial neural networks to predict structural response behavior using supervised learning. However, one shortcoming of supervised learning is the inability of a sufficiently accurate prediction when extrapolating to data the neural network has not seen yet. Denny Thaler will present a selection process for the training data to provide the required samples to reliably predict rare events.
Denny Thaler is a Ph.D. student at the Institute of General Mechanics at RWTH Aachen University, where Prof. Bernd Markert and Franz Bamer supervise him. While working as a cooperative student at Siemens AG in Mülheim an der Ruhr, he obtained his B.Eng. degree and his M.Sc. degree in Mechanical Engineering at WHS Gelsenkirchen and at Ruhr-University Bochum, respectively. He investigates efficient methods to accelerate simulations in structural mechanics.