Saurabh Deshpande: Surrogate Deep Learning Framework for Real-Time Hyper-Elastic Simulations with Uncertainties

Machine Learning Seminar presentation

Topic: Surrogate Deep Learning Framework for Real-Time Hyper-Elastic Simulations with Uncertainties

Speaker: Saurabh Deshpande, Faculty of Science, Technology and Medicine; University of Luxembourg

Time: Wednesday, 2021.09.29, 10:00 CET

How to join: Please contact Jakub Lengiewicz

Abstract:

Conventional finite element solvers are computationally expensive to solve non-linear partial differential equations, particularly they perform poorly in real time scale applications. In this work we propose a deep learning surrogate model which predicts nonlinear displacement solutions for hyper-elastic constitutive models in real time. We implement the Bayesian inference approach, thereby giving probabilistic predictions of displacement fields, capable of giving uncertainty of predictions. We implement our framework to benchmark hyper-elastic simulations to prove that it is extremely fast yet accurate.

Additional material: