skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Materials Design using an Active Subspace-based Batch Bayesian Optimization Approach

Conference · · AIAA SCITECH 2022 Forum
DOI:https://doi.org/10.2514/6.2022-0075· OSTI ID:1894254

Integrated computational materials engineering (ICME) calls for integrating simulation tools and/or experiments to develop new materials and materials systems. However, implementation of ICME approaches is challenging mainly due to the considerable computational expense of such frameworks and large dimensionality of the design space. Addressing these challenges is thus critical to the success of ICME initiatives. We present here a specific Bayesian optimization framework designed to address these two challenges. In particular, we propose an active subspace batch Bayesian optimization framework. The framework makes use of dimension reduction via the active subspace method and makes use of the ability to query in parallel via the batch Bayesian optimization approach. Here, the integration of these techniques leads to significant efficiency improvements while maintaining accuracy.

Research Organization:
Texas A & M Univ., College Station, TX (United States)
Sponsoring Organization:
USDOE Advanced Research Projects Agency - Energy (ARPA-E)
DOE Contract Number:
AR0001427
OSTI ID:
1894254
Journal Information:
AIAA SCITECH 2022 Forum, Conference: AIAA SCITECH 2022 Forum, Held Virtually, San Diego, CA (United States), 3-7 Jan 2022
Country of Publication:
United States
Language:
English

References (25)

The Knowledge-Gradient Policy for Correlated Normal Beliefs journal November 2009
Multi-Information Source Fusion and Optimization to Realize ICME: Application to Dual-Phase Materials journal September 2018
Active Subspaces book January 2015
Batch Bayesian optimization using multi-scale search journal January 2020
Active Subspaces for Shape Optimization conference January 2014
Materials Design Through Batch Bayesian Optimization with Multisource Information Fusion journal October 2020
A Knowledge-Gradient Policy for Sequential Information Collection journal January 2008
Kriging Is Well-Suited to Parallelize Optimization book January 2010
Active Subspace Methods in Theory and Practice: Applications to Kriging Surfaces journal January 2014
Efficiently exploiting process-structure-property relationships in material design by multi-information source fusion journal March 2021
Efficient Global Optimization of Expensive Black-Box Functions journal January 1998
Efficient use of multiple information sources in material design journal November 2019
On Bayesian Methods for Seeking the Extremum book January 1975
Adaptive Dimensionality Reduction for Fast Sequential Optimization With Gaussian Processes journal March 2019
Adaptive active subspace-based efficient multifidelity materials design journal November 2021
A Fusion-Based Multi-Information Source Optimization Approach using Knowledge Gradient Policies conference January 2018
Gaussian Processes for Machine Learning book January 2005
Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Exploration book January 2013
Exploiting active subspaces to quantify uncertainty in the numerical simulation of the HyShot II scramjet journal December 2015
Surrogate-based aerodynamic shape optimization with the active subspace method journal August 2018
Metallurgical Perspectives on Advanced Sheet Steels for Automotive Applications book January 2011
A Survey of Projection-Based Model Reduction Methods for Parametric Dynamical Systems journal January 2015
Conditional sampling and experiment design for quantifying manufacturing error of transonic airfoil conference January 2011
Output Based Dimensionality Reduction of Geometric Variability in Compressor Blades conference January 2013
Discovering a one-dimensional active subspace to quantify multidisciplinary uncertainty in satellite system design journal March 2016