期刊
GRANULAR MATTER
卷 24, 期 1, 页码 -出版社
SPRINGER
DOI: 10.1007/s10035-021-01137-y
关键词
Causal discovery; Granular materials; Knowledge graph; Path-dependent responses; Soil mechanics
资金
- National Science Foundation [CMMI-1846875, OAC-1940203, 1940107]
- Earth Materials and Processes program from the US Army Research Office [W911NF-18-2-0306]
- Dynamic Materials and Interactions Program from the Air Force Office of Scientific Research [FA9550-17-1-0169]
- Office of Advanced Cyberinfrastructure (OAC)
- Direct For Computer & Info Scie & Enginr [1940107] Funding Source: National Science Foundation
This paper presents a computational framework for generating ensemble predictive mechanics models with uncertainty quantification, and introduces a causal discovery algorithm for inferring causal relationships among time-history data.
This paper presents a computational framework that generates ensemble predictive mechanics models with uncertainty quantification (UQ). We first develop a causal discovery algorithm to infer causal relations among time-history data measured during each representative volume element (RVE) simulation through a directed acyclic graph. With multiple plausible sets of causal relationships estimated from multiple RVE simulations, the predictions are propagated in the derived causal graph while using a deep neural network equipped with dropout layers as a Bayesian approximation for UQ. We select two representative numerical examples (traction-separation laws for frictional interfaces, elastoplasticity models for granular assembles) to examine the accuracy and robustness of the proposed causal discovery method for the common material law predictions in civil engineering applications.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据