Data-augmented modeling for yield strength of refractory high entropy alloys: A Bayesian approach
Data-augmented modeling for yield strength of refractory high entropy alloys: A Bayesian approach
复制标题
难熔高熵合金屈服强度的数据增强建模：贝叶斯方法
DOI：
10.1016/j.actamat.2023.119351
复制
发表时间：
2023
期刊：
影响因子：
9.4
通讯作者：
Arróyave, Raymundo
中科院分区：
文献类型：
--
作者：
Vela, Brent;Khatamsaz, Danial;Acemi, Cafer;Karaman, Ibrahim;Arróyave, Raymundo
难熔高熵合金作为镍基高温合金在燃气涡轮机应用中的潜在替代品，近年来受到了广泛关注。改善其性能，如高温屈服强度，是其成功的关键。不幸的是，探索这一巨大的化学空间，使用专门的实验方法是不切实际的，由于相当大的成本的合成，加工和测试的候选合金，特别是在操作相关的温度。另一方面，缺乏合理准确的预测性能模型，特别是对于高温性能，使得传统的集成计算材料工程（ICME）方法不足。在本文中，我们通过结合机器学习模型、易于实现的基于物理的模型和廉价的代理实验数据来解决这一挑战，以使用贝叶斯更新的概念开发鲁棒且快速的模型。该框架结合了来自RHEA最全面的数据库之一的数据（博格等人，2020）与BCC RHEA（Maresca和科廷，2020）中最广泛使用的基于物理的强度模型之一相结合，形成一个紧凑的预测模型，该模型比最先进的预测模型准确得多。该模型经过交叉验证，测试了基于物理的外推，并在玩具贝叶斯优化问题中对标准高斯过程回归（GPR）进行了严格的基准测试。这样的模型可以用作ICME框架内的工具，以筛选具有上级高温性能的RHEAs。与本工作相关的代码可在https://codeocean.com/capsule/7849853/tree/v2上获得。
Refractory high entropy alloys (RHEAs) have gained significant attention in recent years as potential replacements for Ni-based superalloys in gas turbine applications. Improving their properties, such as their high-temperature yield strength, is crucial to their success. Unfortunately, exploring this vast chemical space using exclusively experimental approaches is impractical due to the considerable cost of the synthesis, processing, and testing of candidate alloys, particularly at operation-relevant temperatures. On the other hand, the lack of reasonably accurate predictive property models, especially for high-temperature properties, makes traditional Integrated Computational Materials Engineering (ICME) methods inadequate. In this paper, we address this challenge by combining machine-learning models, easy-to-implement physics-based models, and inexpensive proxy experimental data to develop robust and fast-acting models using the concept of Bayesian updating. The framework combines data from one of the most comprehensive databases on RHEAs (Borg et al., 2020) with one of the most widely used physics-based strength models for BCC-based RHEAs (Maresca and Curtin, 2020) into a compact predictive model that is significantly more accurate than the state-of-the-art. This model is cross-validated, tested for physics-informed extrapolation, and rigorously benchmarked against standard Gaussian process regressors (GPRs) in a toy Bayesian optimization problem. Such a model can be used as a tool within ICME frameworks to screen for RHEAs with superior high-temperature properties. The code associated with this work is available at: https://codeocean.com/capsule/7849853/tree/v2.
登录
查看更多内容
影响因子：
9.8
作者：
Borg CKH;Frey C;Moh J;Pollock TM;Gorsse S;Miracle DB;Senkov ON;Meredig B;Saal JE
通讯作者：
Saal JE
影响因子：
9.1
作者：
Sun, Qingping;Zhou, Guowei;Su, Xuming
通讯作者：
Su, Xuming
影响因子：
8.6
作者：
A. Wang;Ryan Murdock;Steven K. Kauwe;A. Oliynyk;A. Gurlo;Jakoah Brgoch;K. Persson;Taylor D. Sparks
通讯作者：
A. Wang;Ryan Murdock;Steven K. Kauwe;A. Oliynyk;A. Gurlo;Jakoah Brgoch;K. Persson;Taylor D. Sparks
影响因子：
29.4
作者：
Feng, Rui;Feng, Bojun;Liaw, Peter K.
通讯作者：
Liaw, Peter K.
实验数据融合的分层贝叶斯方法：根据硬度测量预测高熵合金的强度的应用
影响因子：
3.3
作者：
Karumuri, Sharmila;McClure, Zachary D.;Strachan, Alejandro;Titus, Michael;Bilionis, Ilias
通讯作者：
Bilionis, Ilias