Breaking data barriers: advancing phase prediction in high entropy alloys through a new machine learning framework

被引:1
|
作者
Choudhury, Amitava [1 ]
Kumar, Sandeep [2 ]
机构
[1] Pandit Deendayal Energy Univ, Dept Comp Sci & Engn, Gandhinagar, India
[2] Indian Inst Technol Roorkee, Dept Comp Sci & Engn, Roorkee, India
关键词
High entropy alloy; machine learning; phase prediction; thermodynamics properties; low dataset; SELECTION; STABILITY;
D O I
10.1080/00084433.2024.2395674
中图分类号
TF [冶金工业];
学科分类号
0806 ;
摘要
High entropy alloys (HEAs) represent a promising ADVANCEMENT in the context of Industry 4.0, embodying the principles of interconnectedness, automation and real-time data. The formation of phases in HEAs is predominantly influenced by the composition of the alloy and its corresponding thermodynamic properties. With an expansive composition space, HEAs exhibit diverse phase formations. While previous research has primarily focused on solid solution features, establishing a direct link between compositions and phase formations is crucial for accelerating the development of novel HEAs. Machine learning algorithms have been extensively employed to predict phases in HEAs; however, their effectiveness relies heavily on the availability of large datasets. Unfortunately, acquiring precise data remains challenging due to the nascent nature of HEA research. In this research article, we propose a novel machine learning algorithm to predict alloy phases, even in scenarios with limited data. The primary objective is establishing a robust relationship between elemental properties and phases, enabling phase predictions based on alloy compositions. Our study achieves an accuracy of 92% using a dataset comprising only 118 samples. The proposed work is compared with state-of-the-art approaches, addressing data scarcity challenges in HEAs and advancing predictive modeling for phase predictions in these alloys. Les alliages & agrave; haute entropie (HEA) repr & eacute;sentent un avancement qui promet dans le contexte de Industry 4.0, incorporant les principes d'interconnectivit & eacute;, d'automatisation et de donn & eacute;es en temps r & eacute;el. La formation de phases dans les HEA est influenc & eacute;e de mani & egrave;re pr & eacute;dominante par la composition de l'alliage et de ses propri & eacute;t & eacute;s thermodynamiques correspondantes. Avec un espace de composition en expansion, les HEA d & eacute;montrent diverses formations de phase. Alors que les recherches ant & eacute;c & eacute;dentes & eacute;taient concentr & eacute;es principalement sur les caract & eacute;ristiques des solutions solides, & eacute;tablir un lien direct entre les compositions et les formations de phases est critique pour acc & eacute;l & eacute;rer le d & eacute;veloppement de nouveaux HEA. On a largement utilis & eacute; les algorithmes d'apprentissage informatique pour pr & eacute;dire les phases dans les HEA; cependant, leur efficacit & eacute; repose fortement sur la disponibilit & eacute; de grands ensembles de donn & eacute;es. Malheureusement, l'acquisition de donn & eacute;es pr & eacute;cises reste un d & eacute;fi en raison de la nature naissante de la recherche des HEA. Dans cet article de recherche, nous proposons un nouvel algorithme d'apprentissage informatique pour pr & eacute;dire les phases de l'alliage, m & ecirc;me dans des sc & eacute;narios avec donn & eacute;es limit & eacute;es. Le premier objectif consiste & agrave; & eacute;tablir une relation robuste entre les propri & eacute;t & eacute;s & eacute;l & eacute;mentaires et les phases, permettant des pr & eacute;dictions de phases bas & eacute;es sur les compositions de l'alliage. Notre & eacute;tude atteint une pr & eacute;cision de 92% en utilisant un ensemble de donn & eacute;es comprenant seulement 118 & eacute;chantillons. En outre, nous comparons la performance de notre algorithme propos & eacute; aux approches de pointe couramment disponibles dans le domaine. En relevant les d & eacute;fis pos & eacute;s par la raret & eacute; des donn & eacute;es dans le domaine des HES, notre recherche contribue & agrave; l'avancement de la mod & eacute;lisation pr & eacute;dictive pour les pr & eacute;dictions de phase dans ces alliages. Ces r & eacute;sultats tracent le chemin & agrave; d'autres explorations et d & eacute;veloppements des HEA, facilitant leur int & eacute;gration dans diverses applications industrielles.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] Enhanced phase prediction of high-entropy alloys through machine learning and data augmentation
    Wu, Song
    Song, Zihao
    Wang, Jianwei
    Niu, Xiaobin
    Chen, Haiyuan
    PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2025, 27 (02) : 717 - 729
  • [2] Machine learning-enabled framework for the prediction of mechanical properties in new high entropy alloys
    Bundela, Amit Singh
    Rahul, M. R.
    JOURNAL OF ALLOYS AND COMPOUNDS, 2022, 908
  • [3] Machine learning-enabled framework for the prediction of mechanical properties in new high entropy alloys
    Bundela, Amit Singh
    Rahul, M.R.
    Journal of Alloys and Compounds, 2022, 908
  • [4] Machine learning guided phase formation prediction of high entropy alloys
    Qu N.
    Liu Y.
    Zhang Y.
    Yang D.
    Han T.
    Liao M.
    Lai Z.
    Zhu J.
    Zhang L.
    Materials Today Communications, 2022, 32
  • [5] Machine learning guided phase formation prediction of high entropy alloys
    Qu, Nan
    Liu, Yong
    Zhang, Yan
    Yang, Danni
    Han, Tianyi
    Liao, Mingqing
    Lai, Zhonghong
    Zhu, Jingchuan
    Zhang, Lin
    MATERIALS TODAY COMMUNICATIONS, 2022, 32
  • [6] Machine-learning phase prediction of high-entropy alloys
    Huang, Wenjiang
    Martin, Pedro
    Zhuang, Houlong L.
    ACTA MATERIALIA, 2019, 169 : 225 - 236
  • [7] Improving phase prediction accuracy for high entropy alloys with Machine learning
    Risal, Sandesh
    Zhu, Weihang
    Guillen, Pablo
    Sun, Li
    COMPUTATIONAL MATERIALS SCIENCE, 2021, 192
  • [8] Machine learning guided phase formation prediction of high entropy alloys
    Qu, Nan
    Liu, Yong
    Zhang, Yan
    Yang, Danni
    Han, Tianyi
    Liao, Mingqing
    Lai, Zhonghong
    Zhu, Jingchuan
    Zhang, Lin
    MATERIALS TODAY COMMUNICATIONS, 2022, 32
  • [9] A machine learning framework for discovering high entropy alloys phase formation drivers
    Syarif, Junaidi
    Elbeltagy, Mahmoud B.
    Nassif, Ali Bou
    HELIYON, 2023, 9 (01)
  • [10] Overview: recent studies of machine learning in phase prediction of high entropy alloys
    Yan, Yong-Gang
    Lu, Dan
    Wang, Kun
    TUNGSTEN, 2023, 5 (01) : 32 - 49