Abstract
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.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.