7 papers
Machine Learning Inference Limits of Routine Cement Characterization for CEM I Performance: Evidence From a Multi-Producer Dataset
Marchellino Ghorayeb, Christiane RöÃler, Horst-Michael Ludwig +2
Routine cement performance characterization provides continuous quality control data, but its information content for performance inference and transferability across independent p…
Lightweight return-mapping surrogates for multiscale plasticity: a practical guide
Alireza Daneshyar, Leon Herrmann, Stefan Kollmannsberger
This paper presents a practical guide to building lightweight neural-network surrogates for the plastic return-mapping process in concurrent multiscale (FE2) simulations. Rather th…
A Memory Efficient Adjoint Method to Enable Billion Parameter Optimization on a Single GPU in Dynamic Problems
Leon Herrmann, Tim Bürchner, László Kudela +1
Dynamic optimization is currently limited by sensitivity computations that require information from full forward and adjoint wave fields. Since the forward and adjoint solutions ar…
Full-waveform inversion via the scaled boundary finite element method
Alireza Daneshyar, Stefan Kollmannsberger
We begin by addressing the time-domain full-waveform inversion using the adjoint method. Next, we derive the scaled boundary semi-weak form of the scalar wave equation in heterogen…
A plastic damage model with mixed isotropic-kinematic hardening for low-cycle fatigue in 7020 aluminum
Alireza Daneshyar, Dorina Siebert, Christina Radlbeck +1
The paper at hand presents an in-depth investigation into the fatigue behavior of the high-strength aluminum alloy EN AW-7020 T6 using both experimental and numerical approaches. T…
Accelerating Full Waveform Inversion By Transfer Learning
Divya Shyam Singh, Leon Herrmann, Qing Sun +3
Full waveform inversion (FWI) is a powerful tool for reconstructing material fields based on sparsely measured data obtained by wave propagation. For specific problems, discretizin…