TY - GEN
T1 - Data-centric mixed-variable Bayesian optimization for materials design
AU - Iyer, Akshay
AU - Zhang, Yichi
AU - Prasad, Aditya
AU - Tao, Siyu
AU - Wang, Yixing
AU - Schadler, Linda
AU - Brinson, L Catherine
AU - Chen, Wei
N1 - Funding Information:
Support from NSF grants (ACI 1640840, CMMI 1729452, CMMI 1818574, CMMI 1729743, CMMI 1537641, OAC 1835782) and Center for Hierarchical Materials Design (ChiMaD NIST 70NANB14H012) are greatly appreciated.
PY - 2019
Y1 - 2019
N2 - Materials design can be cast as an optimization problem with the goal of achieving desired properties, by varying material composition, microstructure morphology, and processing conditions. Existence of both qualitative and quantitative material design variables leads to disjointed regions in property space, making the search for optimal design challenging. Limited availability of experimental data and the high cost of simulations magnify the challenge. This situation calls for design methodologies that can extract useful information from existing data and guide the search for optimal designs efficiently. To this end, we present a data-centric, mixed-variable Bayesian Optimization framework that integrates data from literature, experiments, and simulations for knowledge discovery and computational materials design. Our framework pivots around the Latent Variable Gaussian Process (LVGP), a novel Gaussian Process technique which projects qualitative variables on a continuous latent space for covariance formulation, as the surrogate model to quantify “lack of data” uncertainty. Expected improvement, an acquisition criterion that balances exploration and exploitation, helps navigate a complex, nonlinear design space to locate the optimum design. The proposed framework is tested through a case study which seeks to concurrently identify the optimal composition and morphology for insulating polymer nanocomposites. We also present an extension of mixed-variable Bayesian Optimization for multiple objectives to identify the Pareto Frontier within tens of iterations. These findings project Bayesian Optimization as a powerful tool for design of engineered material systems.
AB - Materials design can be cast as an optimization problem with the goal of achieving desired properties, by varying material composition, microstructure morphology, and processing conditions. Existence of both qualitative and quantitative material design variables leads to disjointed regions in property space, making the search for optimal design challenging. Limited availability of experimental data and the high cost of simulations magnify the challenge. This situation calls for design methodologies that can extract useful information from existing data and guide the search for optimal designs efficiently. To this end, we present a data-centric, mixed-variable Bayesian Optimization framework that integrates data from literature, experiments, and simulations for knowledge discovery and computational materials design. Our framework pivots around the Latent Variable Gaussian Process (LVGP), a novel Gaussian Process technique which projects qualitative variables on a continuous latent space for covariance formulation, as the surrogate model to quantify “lack of data” uncertainty. Expected improvement, an acquisition criterion that balances exploration and exploitation, helps navigate a complex, nonlinear design space to locate the optimum design. The proposed framework is tested through a case study which seeks to concurrently identify the optimal composition and morphology for insulating polymer nanocomposites. We also present an extension of mixed-variable Bayesian Optimization for multiple objectives to identify the Pareto Frontier within tens of iterations. These findings project Bayesian Optimization as a powerful tool for design of engineered material systems.
KW - Acquisition Functions
KW - Data-centric Material Design
KW - Latent Variable Gaussian Process
KW - Mixed-variable Bayesian Optimization
KW - Nanocomposites
UR - http://www.scopus.com/inward/record.url?scp=85076463288&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076463288&partnerID=8YFLogxK
U2 - 10.1115/DETC2019-98222
DO - 10.1115/DETC2019-98222
M3 - Conference contribution
AN - SCOPUS:85076463288
T3 - Proceedings of the ASME Design Engineering Technical Conference
BT - 45th Design Automation Conference
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2019
Y2 - 18 August 2019 through 21 August 2019
ER -