Mesoscale informed parameter estimation through machine learning: A case-study in fracture modeling

JOURNAL OF COMPUTATIONAL PHYSICS

卷:420

Article

Panda, Nishant¹  Osthus, Dave²  Srinivasan, Gowri³  O'Malley, Daniel⁴  Chau, Viet⁵  Oyen, Diane⁶  Godinez, Humberto¹ 

[1] Los Alamos Natl Lab, Appl Math & Plasma Phys, T-5, Los Alamos, NM 87545 USA

[2] Los Alamos Natl Lab, Stat Sci, CCS-6, Los Alamos, NM 87545 USA

[3] Los Alamos Natl Lab, Computat Phys, XCP-8, Los Alamos, NM 87545 USA

[4] Los Alamos Natl Lab, Computat Earth Sci, EES-16, Los Alamos, NM 87545 USA

[5] Los Alamos Natl Lab, Earth & Environm Sci Div, EES-17, Los Alamos, NM 87545 USA

[6] Los Alamos Natl Lab, Informat Sci, CCS-3, Los Alamos, NM 87545 USA

关键词: Uncertainty quantification;    Reduced order model;    Machine learning;    Data driven upscaling;    Probabilistic emulator;    Fracture propagation;   

DOI  :  10.1016/j.jcp.2020.109719

来源: Elsevier

【 摘 要 】

Scale bridging is a critical need in computational sciences, where the modeling community has developed accurate physics models from first principles, of processes at lower length and time scales that influence the behavior at the higher scales of interest. However, it is not computationally feasible to incorporate all of the lower length scale physics directly into upscaled models. This is an area where machine learning has shown promise in building emulators of the lower length scale models, which incur a mere fraction of the computational cost of the original higher fidelity models. We demonstrate the use of machine learning using an example in materials science estimating continuum scale parameters by emulating, with uncertainties, complicated mesoscale physics. We describe a new framework to emulate the fine scale physics, especially in the presence of microstructures, using machine learning, and showcase its usefulness by providing an example from modeling fracture propagation. Our approach can be thought of as a data-driven dimension reduction technique that yields probabilistic emulators. Our results show well-calibrated predictions for the quantities of interests in a low-strain simulation of fracture propagation at the mesoscale level. On average, we achieve similar to 10% relative errors on time-varying quantities like total damage and maximum stresses. Successfully replicating mesoscale scale physics within the continuum models is a crucial step towards predictive capability in multi-scale problems. Published by Elsevier Inc.

【 授权许可】

Free