Probabilistic learning and updating of a digital twin for composite material systems

Abstract

This article presents an approach for characterizing and estimating statistical dependence between a large number of observables in a composite material system. Conditional regression is carried out using the estimated joint density function, permitting a systematic exploration of interdependence between fine scale and coarse observables that can be used for both prognosis and design of complex material systems. An example demonstrates the integration of experimental data with a computational database. The statistical approach is based on the probabilistic learning on manifolds recently developed by the authors. This approach leverages intrinsic structure detected through diffusion on graphs with projected stochastic differential equations to generate samples constrained to that structure.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jun 29, 2020
Source ID
10.1002/nme.6430

Entities

People

  • Christian Soize
  • Loujaine Mehrez
  • Roger Ghanem
  • Venkat Aitharaju

Organizations

  • General Motors
  • United States Department of Energy
  • University of Southern California

Tags

Readers

  • Neural Network Machine Learning.
  • Statistical inference.
  • Structural Health Monitoring of Composite Structures.