Machine learning guided discovery of super-hard high entropy ceramics

Russlan Jaafreh; Yoo Seong Kang; Jung Gu Kim; Kotiba Hamad

doi:10.1016/j.matlet.2021.130899

Machine learning guided discovery of super-hard high entropy ceramics

Russlan Jaafreh
, Yoo Seong Kang
, Jung Gu Kim
, Kotiba Hamad

Department of Advanced Materials Science and Engineering

Sungkyunkwan University

Research output: Contribution to journal › Article › peer-review

32 Scopus citations

Abstract

In the present work, we used machine learning (ML) to explore new compositions of high entropy ceramic (HEC) materials that show improved hardness. Starting from a dataset containing hardness, loads and compositions of 557 ceramic materials including HECs, a ML model was built using random forest (RF) algorithm. The RF-based model successfully reproduced experimental load-hardness behavior of Al₂O₃, (Hf_0.2Zr_0.2Ti_0.2Ta_0.2Nb_0.2)B₂ and (Hf_0.2Zr_0.2Ti_0.2Ta_0.2Mo_0.2)B₂. Accordingly, the built model was employed to find super-hard HECs.

Original language	English
Article number	130899
Journal	Materials Letters
Volume	306
DOIs	https://doi.org/10.1016/j.matlet.2021.130899
State	Published - 1 Jan 2022

Keywords

Composition features
Hardness
High entropy ceramics
Machine learning

Access to Document

10.1016/j.matlet.2021.130899

Cite this

@article{4b7e35d9ad1c429ca277ef98ea3c7e56,

title = "Machine learning guided discovery of super-hard high entropy ceramics",

abstract = "In the present work, we used machine learning (ML) to explore new compositions of high entropy ceramic (HEC) materials that show improved hardness. Starting from a dataset containing hardness, loads and compositions of 557 ceramic materials including HECs, a ML model was built using random forest (RF) algorithm. The RF-based model successfully reproduced experimental load-hardness behavior of Al2O3, (Hf0.2Zr0.2Ti0.2Ta0.2Nb0.2)B2 and (Hf0.2Zr0.2Ti0.2Ta0.2Mo0.2)B2. Accordingly, the built model was employed to find super-hard HECs.",

keywords = "Composition features, Hardness, High entropy ceramics, Machine learning",

author = "Russlan Jaafreh and Kang, \{Yoo Seong\} and Kim, \{Jung Gu\} and Kotiba Hamad",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier B.V.",

year = "2022",

month = jan,

day = "1",

doi = "10.1016/j.matlet.2021.130899",

language = "English",

volume = "306",

journal = "Materials Letters",

issn = "0167-577X",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Machine learning guided discovery of super-hard high entropy ceramics

AU - Jaafreh, Russlan

AU - Kang, Yoo Seong

AU - Kim, Jung Gu

AU - Hamad, Kotiba

PY - 2022/1/1

Y1 - 2022/1/1

N2 - In the present work, we used machine learning (ML) to explore new compositions of high entropy ceramic (HEC) materials that show improved hardness. Starting from a dataset containing hardness, loads and compositions of 557 ceramic materials including HECs, a ML model was built using random forest (RF) algorithm. The RF-based model successfully reproduced experimental load-hardness behavior of Al2O3, (Hf0.2Zr0.2Ti0.2Ta0.2Nb0.2)B2 and (Hf0.2Zr0.2Ti0.2Ta0.2Mo0.2)B2. Accordingly, the built model was employed to find super-hard HECs.

AB - In the present work, we used machine learning (ML) to explore new compositions of high entropy ceramic (HEC) materials that show improved hardness. Starting from a dataset containing hardness, loads and compositions of 557 ceramic materials including HECs, a ML model was built using random forest (RF) algorithm. The RF-based model successfully reproduced experimental load-hardness behavior of Al2O3, (Hf0.2Zr0.2Ti0.2Ta0.2Nb0.2)B2 and (Hf0.2Zr0.2Ti0.2Ta0.2Mo0.2)B2. Accordingly, the built model was employed to find super-hard HECs.

KW - Composition features

KW - Hardness

KW - High entropy ceramics

KW - Machine learning

UR - https://www.scopus.com/pages/publications/85115400950

U2 - 10.1016/j.matlet.2021.130899

DO - 10.1016/j.matlet.2021.130899

M3 - Article

AN - SCOPUS:85115400950

SN - 0167-577X

VL - 306

JO - Materials Letters

JF - Materials Letters

M1 - 130899

ER -

Machine learning guided discovery of super-hard high entropy ceramics

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this