当前位置: X-MOL 学术Small › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine Learning Accelerated, High Throughput, Multi-Objective Optimization of Multiprincipal Element Alloys
Small ( IF 13.0 ) Pub Date : 2021-09-15 , DOI: 10.1002/smll.202102972
Tian Guo 1 , Lianping Wu 1 , Teng Li 1
Affiliation  

Multiprincipal element alloys (MPEAs) have gained surging interest due to their exceptional properties unprecedented in traditional alloys. However, identifying an MPEA with desired properties from a huge compositional space via a cost-effective design remains a grand challenge. To address this challenge, the authors present a highly efficient design strategy of MPEAs through a coherent integration of molecular dynamics (MD) simulation, machine learning (ML) algorithms, and genetic algorithm (GA). The ML model can be effectively trained from 54 MD simulations to predict the stiffness and critical resolved shear stress (CRSS) of CoNiCrFeMn alloys with a relative error of 2.77% and 2.17%, respectively, with a 12 600-fold reduction of computation time. Furthermore, by combining the highly efficient ML model and a multi-objective GA, one can predict 100 optimal compositions of CoNiCrFeMn alloys with simultaneous high stiffness and CRSS, as verified by 100 000 ML-accelerated predictions. The highly efficient and precise design strategy can be readily adapted to identify MPEAs of other principal elements and thus substantially accelerate the discovery of other high-performance MPEA materials.

中文翻译:

多主元素合金的机器学习加速、高吞吐量、多目标优化

多基元合金 (MPEA) 因其在传统合金中前所未有的卓越性能而引起了广泛关注。然而,通过具有成本效益的设计从巨大的组成空间中识别具有所需特性的 MPEA 仍然是一个巨大的挑战。为了应对这一挑战,作者通过分子动力学 (MD) 模拟、机器学习 (ML) 算法和遗传算法 (GA) 的相干集成,提出了一种高效的 MPEA 设计策略。ML 模型可以通过 54 次 MD 模拟进行有效训练,以预测 CoNiCrFeMn 合金的刚度和临界分辨剪应力 (CRSS),相对误差分别为 2.77% 和 2.17%,计算时间减少了 12 600 倍。此外,通过结合高效的 ML 模型和多目标 GA,可以预测 100 种同时具有高刚度和 CRSS 的 CoNiCrFeMn 合金的最佳成分,如 100 000 ML 加速预测所证实的那样。高效和精确的设计策略可以很容易地用于识别其他主要元素的 MPEA,从而大大加速其他高性能 MPEA 材料的发现。
更新日期:2021-10-21
down
wechat
bug