Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling
In this study, a framework for the multi-objective materials discovery based on Bayesian approaches is developed and demonstrated on the efficient discovery of precipitation-strengthened NiTi shape memory alloys with up to three desired properties. The framework is used to minimize the required comp...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2018-12-01
|
Series: | Materials & Design |
Online Access: | http://www.sciencedirect.com/science/article/pii/S026412751830769X |
id |
doaj-b712319db3b34c2a91565accb51986aa |
---|---|
record_format |
Article |
spelling |
doaj-b712319db3b34c2a91565accb51986aa2020-11-25T01:02:31ZengElsevierMaterials & Design0264-12752018-12-01160810827Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modelingAlexandros Solomou0Guang Zhao1Shahin Boluki2Jobin K. Joy3Xiaoning Qian4Ibrahim Karaman5Raymundo Arróyave6Dimitris C. Lagoudas7Department of Aerospace Engineering, Texas A&M University, College Station, TX 77843, United States; Corresponding author.Department of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, United StatesDepartment of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, United StatesDepartment of Aerospace Engineering, Texas A&M University, College Station, TX 77843, United StatesDepartment of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, United StatesDepartment of Materials Science and Engineering, Texas A&M University, College Station, TX 77843, United StatesDepartment of Materials Science and Engineering, Texas A&M University, College Station, TX 77843, United StatesDepartment of Aerospace Engineering, Texas A&M University, College Station, TX 77843, United States; Department of Materials Science and Engineering, Texas A&M University, College Station, TX 77843, United StatesIn this study, a framework for the multi-objective materials discovery based on Bayesian approaches is developed and demonstrated on the efficient discovery of precipitation-strengthened NiTi shape memory alloys with up to three desired properties. The framework is used to minimize the required computational experiments for the discovery of the targeted materials, performed by a thermodynamically-consistent micromechanical model that predicts the materials response based on its composition and microstructure. The developed scheme features a Bayesian optimal experimental design process that operates in a closed loop. During each iteration of the process, a Gaussian process regression model is constructed based on the available computational data and used to emulate the response of the material in the unexplored regions of the materials design space. The sequential exploration of the materials design space is carried out by using an optimal experiment selection policy based on the expected hyper-volume improvement acquisition function that accounts for the uncertainty on the predictions of the regression model. The results indicate the considerable efficiency of the proposed framework, in discovering the targeted materials, compared with the exhaustive model-driven exploration of the materials design space. Keywords: Bayesian optimization, Bayesian optimal experimental design, Shape memory alloys, Micromechanical modelinghttp://www.sciencedirect.com/science/article/pii/S026412751830769X |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Alexandros Solomou Guang Zhao Shahin Boluki Jobin K. Joy Xiaoning Qian Ibrahim Karaman Raymundo Arróyave Dimitris C. Lagoudas |
spellingShingle |
Alexandros Solomou Guang Zhao Shahin Boluki Jobin K. Joy Xiaoning Qian Ibrahim Karaman Raymundo Arróyave Dimitris C. Lagoudas Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling Materials & Design |
author_facet |
Alexandros Solomou Guang Zhao Shahin Boluki Jobin K. Joy Xiaoning Qian Ibrahim Karaman Raymundo Arróyave Dimitris C. Lagoudas |
author_sort |
Alexandros Solomou |
title |
Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling |
title_short |
Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling |
title_full |
Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling |
title_fullStr |
Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling |
title_full_unstemmed |
Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling |
title_sort |
multi-objective bayesian materials discovery: application on the discovery of precipitation strengthened niti shape memory alloys through micromechanical modeling |
publisher |
Elsevier |
series |
Materials & Design |
issn |
0264-1275 |
publishDate |
2018-12-01 |
description |
In this study, a framework for the multi-objective materials discovery based on Bayesian approaches is developed and demonstrated on the efficient discovery of precipitation-strengthened NiTi shape memory alloys with up to three desired properties. The framework is used to minimize the required computational experiments for the discovery of the targeted materials, performed by a thermodynamically-consistent micromechanical model that predicts the materials response based on its composition and microstructure. The developed scheme features a Bayesian optimal experimental design process that operates in a closed loop. During each iteration of the process, a Gaussian process regression model is constructed based on the available computational data and used to emulate the response of the material in the unexplored regions of the materials design space. The sequential exploration of the materials design space is carried out by using an optimal experiment selection policy based on the expected hyper-volume improvement acquisition function that accounts for the uncertainty on the predictions of the regression model. The results indicate the considerable efficiency of the proposed framework, in discovering the targeted materials, compared with the exhaustive model-driven exploration of the materials design space. Keywords: Bayesian optimization, Bayesian optimal experimental design, Shape memory alloys, Micromechanical modeling |
url |
http://www.sciencedirect.com/science/article/pii/S026412751830769X |
work_keys_str_mv |
AT alexandrossolomou multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling AT guangzhao multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling AT shahinboluki multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling AT jobinkjoy multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling AT xiaoningqian multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling AT ibrahimkaraman multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling AT raymundoarroyave multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling AT dimitrisclagoudas multiobjectivebayesianmaterialsdiscoveryapplicationonthediscoveryofprecipitationstrengthenednitishapememoryalloysthroughmicromechanicalmodeling |
_version_ |
1725204486191841280 |