Kategorien
Seiten
-

IRTG Modern Inverse Problems (MIP)
Lade Veranstaltungen

« Alle Veranstaltungen

SSD Seminar Series with Prof. Surya R. Kalidindi

Juli 11 @ 16:00 - 17:00

Prof. Surya R. Kalidindi – A new AI/ML framework for materials innovation

Woodruff School of Mechanical Engineering at Georgia Institute of Technology, Atlanta, USA

Abstract

A novel information gain-driven Bayesian AI/ML (artificial intelligence/machine learning) framework is presented with the following main features: (i) explicit consideration of the physics parameters as inputs (i.e., regressors) in the formulation of process-structure-property (PSP) surrogate models needed to drive materials improvement workflows; (ii) information gain-driven autonomous workflows for training efficient AI/ML surrogates to otherwise computationally expensive physics-based simulations; (iii) versatile feature engineering for multiscale material internal structure using the formalism of n-point spatial correlations; (iv) amenable to a broad suite of surrogate model building approaches (including Gaussian Process regression (GPR), convolutional neural networks (CNN)); and (v) Markov chain Monte Carlo (MCMC)-based  computation of posteriors for physics parameters using all available experimental observations (usually disparate and sparse). The benefits of this framework in supporting accelerated design and development of heterogeneous materials will be demonstrated using multiple case studies.

Details

Datum:
Juli 11
Zeit:
16:00 - 17:00

Veranstalter

IRTG-2379 MIP

Veranstaltungsort

Rogowski Building, Room 115
Schinkelstraße 2
Aachen, 52062 Deutschland
Google Karte anzeigen