Composition design of high-entropy alloys with deep sets learning
Composition design of high-entropy alloys with deep sets learning
复制标题
DOI：
10.1038/s41524-022-00779-7
复制
发表时间：
2022-04
影响因子：
9.7
通讯作者：
J. Zhang;Chen Cai;George Kim;Yusu Wang;Wei Chen
中科院分区：
文献类型：
--
作者：
J. Zhang;Chen Cai;George Kim;Yusu Wang;Wei Chen
高熵合金（HEA）是下一代结构材料开发中的重要材料类别，但天文数字般巨大的成分空间无法通过实验或第一性原理计算有效探索。机器学习 (ML) 方法可能会解决这一挑战，但 HEA 的 ML 受到 HEA 属性数据稀缺的阻碍。在这项工作中，EMTO-CPA方法用于生成一个大型HEA数据集（跨越14个元素的组成空间），其中包含7086个具有结构特性的立方HEA结构，其中1911个具有计算的完整弹性张量。弹性属性数据集用于训练具有 Deep Sets 架构的 ML 模型。与其他 ML 模型相比，Deep Sets 模型具有更好的预测性能和泛化性。将关联规则挖掘应用于模型预测，以描述 HEA 弹性性能的成分依赖性，并展示数据驱动合金设计的潜力。
High entropy alloys (HEAs) are an important material class in the development of next-generation structural materials, but the astronomically large composition space cannot be efficiently explored by experiments or first-principles calculations. Machine learning (ML) methods might address this challenge, but ML of HEAs has been hindered by the scarcity of HEA property data. In this work, the EMTO-CPA method was used to generate a large HEA dataset (spanning a composition space of 14 elements) containing 7086 cubic HEA structures with structural properties, 1911 of which have the complete elastic tensor calculated. The elastic property dataset was used to train a ML model with the Deep Sets architecture. The Deep Sets model has better predictive performance and generalizability compared to other ML models. Association rule mining was applied to the model predictions to describe the compositional dependence of HEA elastic properties and to demonstrate the potential for data-driven alloy design.