Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules

Pei, Zongrui; Yin, Junqi; Hawk, Jeffrey A.; Alman, David E.; Gao, Michael C.

doi:10.1038/s41524-020-0308-7

Cited by 145 publications

(104 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There is a fundamental interconnection between the mixing entropy of multicomponent single-phase alloys and their mechanical hardness and melting temperature 61 . This interconnection has been used to predict the formation of high-entropy alloys 62 . According to the Boltzmann hypothesis regarding the relationship between the entropy of a system and the system complexity for a random solid solution, the configurational entropy of mixing ΔS is represented by Eq.…”

Section: Discussionmentioning

confidence: 99%

Corrosion and transformation of solution combustion synthesized Co, Ni and CoNi nanoparticles in synthetic freshwater with and without natural organic matter

Khort

Hedberg

Mei

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Pure metallic Co, Ni, and their bimetallic compositions of Co3Ni, CoNi, and CoNi3 nanomaterials were prepared by solution combustion synthesis. Microstructure, phase composition, and crystalline structure of these nanoparticles (NPs) were characterized along with studies of their corrosion and dissolution properties in synthetic freshwater with and without natural organic matter (NOM). The nanomaterials consisted of aggregates of fine NPs (3–30 nm) of almost pure metallic and bimetallic crystal phases with a thin surface oxide covered by a thin carbon shell. The nanomaterials were characterized by BET surface areas ranging from ~ 1 to 8 m2/g for the Ni and Co NPs, to 22.93 m2/g, 14.86 m2/g, and 10.53 m2/g for the Co3Ni, CoNi, CoNi3 NPs, respectively. More Co and Ni were released from the bimetallic NPs compared with the pure metals although their corrosion current densities were lower. In contrast to findings for the pure metal NPs, the presence of NOM increased the release of Co and Ni from the bimetallic NPs in freshwater compared to freshwater only even though its presence reduced the corrosion rate (current density). It was shown that the properties of the bimetallic nanomaterials were influenced by multiple factors such as their composition, including carbon shell, type of surface oxides, and the entropy of mixing.

show abstract

Section: Discussionmentioning

confidence: 99%

Corrosion and transformation of solution combustion synthesized Co, Ni and CoNi nanoparticles in synthetic freshwater with and without natural organic matter

Khort

Hedberg

Mei

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…However, new strategies/approaches are needed to quickly navigate the path between properties that sensitively depend on composition and exquisitely designed microstructures [7,23,24] . For example, applying machine learning algorithms to identify trends in large datasets (from both theoretical simulations [25] and experimental work [26] ) and also to make predictions on HEAs has not yet been fully studied [24,27] .…”

Section: Understanding New Mechanisms By Modern Techniquesmentioning

confidence: 99%

Nonstoichiometric Multicomponent Nitride Thin Films

Shu

2020

Linköping Studies in Science and Technology. Licentiate Thesis

View full text Add to dashboard Cite

High entropy ceramics have rapidly developed as a class of materials based on high entropy alloys; the latter being materials that contain five or more elements in near-equal proportions. Their unconventional compositions and chemical structures hold promise for achieving unprecedented combinations of mechanical, electrical and chemical properties. In this thesis, high entropy ceramic films, (TiNbZrTa)Nx were deposited using reactive magnetron sputtering with segmented targets. The stoichiometry x was tuned with two deposition parameters, i.e., substrate temperature and nitrogen flow ratio fN, their effect on microstructure and mechanical, electric, and electrochemical properties were investigated.

show abstract

“…This work has an advantage of saving costs for generating training set data. The existing work based on raw features and neural networks used at least 80% data of HEA in the training process to classify the phases of HEA 23 , 55 , 56 . The HEA data for training is limited because it is based on the experimental results, and it is hard to get calculation data for its substantial computational cost.…”

Section: Resultsmentioning

confidence: 99%

Accelerated crystal structure prediction of multi-elements random alloy using expandable features

Jin

Park

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Properties of solid-state materials depend on their crystal structures. In solid solution high entropy alloy (HEA), its mechanical properties such as strength and ductility depend on its phase. Therefore, the crystal structure prediction should be preceded to find new functional materials. Recently, the machine learning-based approach has been successfully applied to the prediction of structural phases. However, since about 80% of the data set is used as a training set in machine learning, it is well known that it requires vast cost for preparing a dataset of multi-element alloy as training. In this work, we develop an efficient approach to predicting the multi-element alloys' structural phases without preparing a large scale of the training dataset. We demonstrate that our method trained from binary alloy dataset can be applied to the multi-element alloys' crystal structure prediction by designing a transformation module from raw features to expandable form. Surprisingly, without involving the multi-element alloys in the training process, we obtain an accuracy, 80.56% for the phase of the multi-element alloy and 84.20% accuracy for the phase of HEA. It is comparable with the previous machine learning results. Besides, our approach saves at least three orders of magnitude computational cost for HEA by employing expandable features. We suggest that this accelerated approach can be applied to predicting various structural properties of multi-elements alloys that do not exist in the current structural database.

show abstract

Machine-learning informed prediction of high-entropy solid solution formation: Beyond the Hume-Rothery rules

Cited by 145 publications

References 46 publications

Corrosion and transformation of solution combustion synthesized Co, Ni and CoNi nanoparticles in synthetic freshwater with and without natural organic matter

Corrosion and transformation of solution combustion synthesized Co, Ni and CoNi nanoparticles in synthetic freshwater with and without natural organic matter

Nonstoichiometric Multicomponent Nitride Thin Films

Accelerated crystal structure prediction of multi-elements random alloy using expandable features

Contact Info

Product

Resources

About