Gongora Aldair E, Xu Bowen, Perry Wyatt, Okoye Chika, Riley Patrick, Reyes Kristofer G, Morgan Elise F, Brown Keith A
Department of Mechanical Engineering, Boston University, Boston, MA 02215, USA.
Google Research, Mountain View, CA 94043, USA.
Sci Adv. 2020 Apr 10;6(15):eaaz1708. doi: 10.1126/sciadv.aaz1708. eCollection 2020 Apr.
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.
虽然增材制造（AM）促进了复杂结构的生产，但它也凸显了为特定应用确定最佳增材制造结构所固有的巨大挑战。数值方法是优化的重要工具，但实验仍然是研究诸如韧性等非线性但关键的力学性能的黄金标准。为了解决增材制造设计空间的广阔性以及实验需求，我们开发了一种贝叶斯实验自主研究器（BEAR），它将贝叶斯优化与高通量自动化实验相结合。除了快速进行实验外，BEAR还通过根据所有可用结果选择实验来利用迭代实验。使用BEAR，我们探索了一个参数化结构族的韧性，并观察到相对于基于网格的搜索，识别高性能结构所需的实验数量减少了近60倍。这些结果显示了机器学习在数据稀疏的实验领域中的价值。
