期刊
MATERIALS & DESIGN
卷 197, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.matdes.2020.109260
关键词
High-entropy alloys; Phase prediction; Deep learning; Deep neural networks; Bayesian optimization; Conditional generative adversarial networks
资金
- National Research Foundation of Korea (NRF) - Korea Government Ministry of Science and ICT (MSIT) [2020R1A2C1009744]
- High-Potential Individuals Global Training Program of Institute for Information and Communications Technology Promotion (IITP) [2019-0-01589]
- Korea Institute of Energy Technology Evaluation and Planning (KETEP) - Korean Government (MOTIE) [20188550000290]
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [NRF-2020R1C1C1004291]
- Korea Evaluation Institute of Industrial Technology (KEIT) [20188550000290, 20206610100290] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
- National Research Foundation of Korea [2020R1A2C1009744, 4199990514509] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Researchers utilize deep learning methods to predict phases of high-entropy alloys, achieving significant improvement in prediction accuracy and guidance for design through optimization, generation, and explanation of phase information.
Identifying phase information of high-entropy alloys (HEAs) can be helpful as it provides useful information such as anticipated mechanical properties. Recently, machine learning methods are attracting interest to predict phases of HEAs, which could reduce the effort for designing new HEAs. As research direction is in its infancy, there is still plenty of room to develop machine learning models to improve the prediction accuracy and further guide the design of HEAs. In this work, we employ deep learning-based methods regarding optimization, generation, and explanation, for enhancing the performance and identifying key design parameters for phase prediction of HEAs. We first establish regularized deep neural networks for predicting HEA phases and optimize hyper parameters concerning model architecture, training, and regularization. To overcome data shortage of HEAs, we then focus on developing conditional generative adversarial network for generating additional HEA samples. We observe the augmentation from our generative model significantly improves model performance, achieving prediction accuracy of 93.17%. Lastly, we concentrate on understanding contributions of design parameters to identifying solid solution (SS) phase as an example. Our work delivers guidance not only for developing a reliable deep learning-based phase prediction model, but for explaining significant design parameters to assist design of novel HEAs. (C) 2020 The Author(s). Published by Elsevier Ltd.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据