Materials Design Through Batch Bayesian Optimization with Multisource Information Fusion

Integrated computational materials engineering (ICME) calls for the integration of simulation tools and experiments to accelerate the development of materials. ICME approaches tend to be computationally costly, and recently, Bayesian optimization (BO) has been proposed as a way to make ICME more res...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:JOM (1989) Ročník 72; číslo 12; s. 4431 - 4443
Hlavní autoři: Couperthwaite, Richard, Molkeri, Abhilash, Khatamsaz, Danial, Srivastava, Ankit, Allaire, Douglas, Arròyave, Raymundo
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.12.2020
Springer Nature B.V
Témata:
Alloys
Augmenting Physics-based Models in ICME with Machine Learning and Uncertainty Quantification
Bayesian analysis
Case studies
Chemistry/Food Science
Data integration
Design optimization
Dual phase steels
Ductility
Earth Sciences
Engineering
Environment
Experiments
Fashion models
Information sources
Materials engineering
Materials science
Materials selection
Optimization
Physics
Simulation
Stochastic models
model fusion
Computational materials science and engineering
knowledge gradient
reification
ISSN:1047-4838, 1543-1851
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Integrated computational materials engineering (ICME) calls for the integration of simulation tools and experiments to accelerate the development of materials. ICME approaches tend to be computationally costly, and recently, Bayesian optimization (BO) has been proposed as a way to make ICME more resource efficient. Conventional BO, however, is sequential (i.e., one-at-a-time) in nature, which makes it very time-consuming when the evaluation of a materials design choice is costly. While conventional high-throughput approaches enable the synthesis and characterization (or simulation) of materials in a parallel manner, they tend to be “open loop” and are unable to provide recommendations of what to try next once the parallel experiment/simulation has been carried out and analyzed. Here, we address this problem by introducing a batch BO framework that enables the exploration of the material’s design space in a parallel fashion. We augment this approach by incorporating information fusion frameworks capable of integrating multiple information sources. Demonstrating the proposed approach in the computational design of dual-phase steel, we show that batch BO can result in a significant reduction in the time and resources needed to carry out the design task. The proposed approach has wider applicability, well beyond the ICME example used to demonstrate it.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1047-4838
1543-1851
DOI:10.1007/s11837-020-04396-x