Non-intrusive surrogate modelling using sparse random features with applications in crashworthiness analysis
Machine Learning
2023-01-02 v1 Computational Engineering, Finance, and Science
Numerical Analysis
Numerical Analysis
Optimization and Control
Machine Learning
Abstract
Efficient surrogate modelling is a key requirement for uncertainty quantification in data-driven scenarios. In this work, a novel approach of using Sparse Random Features for surrogate modelling in combination with self-supervised dimensionality reduction is described. The method is compared to other methods on synthetic and real data obtained from crashworthiness analyses. The results show a superiority of the here described approach over state of the art surrogate modelling techniques, Polynomial Chaos Expansions and Neural Networks.
Cite
@article{arxiv.2212.14507,
title = {Non-intrusive surrogate modelling using sparse random features with applications in crashworthiness analysis},
author = {Maternus Herold and Anna Veselovska and Jonas Jehle and Felix Krahmer},
journal= {arXiv preprint arXiv:2212.14507},
year = {2023}
}
Comments
19 pages, 7 figures