English

Machine Learning-Accelerated Computational Solid Mechanics: Application to Linear Elasticity

Machine Learning 2022-11-24 v2 Materials Science

Abstract

This work presents a novel physics-informed deep learning based super-resolution framework to reconstruct high-resolution deformation fields from low-resolution counterparts, obtained from coarse mesh simulations or experiments. We leverage the governing equations and boundary conditions of the physical system to train the model without using any high-resolution labeled data. The proposed approach is applied to obtain the super-resolved deformation fields from the low-resolution stress and displacement fields obtained by running simulations on a coarse mesh for a body undergoing linear elastic deformation. We demonstrate that the super-resolved fields match the accuracy of an advanced numerical solver running at 400 times the coarse mesh resolution, while simultaneously satisfying the governing laws. A brief evaluation study comparing the performance of two deep learning based super-resolution architectures is also presented.

Keywords

Cite

@article{arxiv.2112.08676,
  title  = {Machine Learning-Accelerated Computational Solid Mechanics: Application to Linear Elasticity},
  author = {Rajat Arora},
  journal= {arXiv preprint arXiv:2112.08676},
  year   = {2022}
}

Comments

3 figures, 9 pages, Accepted in AAAI 2022: Workshop on AI to Accelerate Science and Engineering (AI2ASE)

R2 v1 2026-06-24T08:19:51.862Z