A Bayesian experimental autonomous researcher for mechanical design
Files
Published version
Date
2020-04-10
Authors
Gongora, Aldair
Xu, Bowen
Perry, Wyatt
Okoye, Chika
Riley, Patrick
Reyes, Kristofer
Morgan, Elise
Brown, Keith A.
Version
Published version
OA Version
Citation
Aldair Gongora, Bowen Xu, Wyatt Perry, Chika Okoye, Patrick Riley, Kristofer Reyes, Elise Morgan, Keith Brown. 2020. "A Bayesian experimental autonomous researcher for mechanical design." Science Advances, Volume 6, Issue 15, https://doi.org/10.1126/sciadv.aaz1708
Abstract
While additive manufacturing (AM) has facilitated the production of complex structures, it has also highlighted the immense challenge inherent in identifying the optimum AM structure for a given application. Numerical methods are important tools for optimization, but experiment remains the gold standard for studying nonlinear, but critical, mechanical properties such as toughness. To address the vastness of AM design space and the need for experiment, we develop a Bayesian experimental autonomous researcher (BEAR) that combines Bayesian optimization and high-throughput automated experimentation. In addition to rapidly performing experiments, the BEAR leverages iterative experimentation by selecting experiments based on all available results. Using the BEAR, we explore the toughness of a parametric family of structures and observe an almost 60-fold reduction in the number of experiments needed to identify high-performing structures relative to a grid-based search. These results show the value of machine learning in experimental fields where data are sparse.
Description
License
Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY).