A focused review on machine learning aided high-throughput methods in high entropy alloy

Qiao, Lei; Liu, Yong; Zhu, Jingchuan

doi:10.1016/j.jallcom.2021.160295

Cited by 96 publications

(23 citation statements)

References 237 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, ML could help CALPHAD extend its application and establish the structure-property connection quantitatively. A recent review of the HT-CALPHAD method could be found in [31].…”

Section: High-throughput Calphad (Ht-calphad) Calculations For the He...mentioning

confidence: 99%

CALPHAD as a Toolbox to Facilitate the Development of HEAs

Wang¹,

Li²

2023

High Entropy Materials - Microstructures and Properties

View full text Add to dashboard Cite

This chapter would be a comprehensive review of the successful application of the CALPHAD method in the research and development of high-entropy alloys (HEAs) in recent years. The structure of this chapter is obedient to the conventional framework in materials science, and several topics would be covered, including composition and structure design, heat treatment and solidification processing, and some properties and performances, such as mechanical and electrochemical corrosion behaviors and high-temperature oxidation characteristics. A conclusion and outlook of the CALPHAD method are also provided at the end of this chapter. Hope this chapter could offer a thermodynamic and kinetic perspective for facilitating the field of HEA research and inspire other researchers to contribute more valuable ideas and works.

show abstract

Section: High-throughput Calphad (Ht-calphad) Calculations For the He...mentioning

confidence: 99%

CALPHAD as a Toolbox to Facilitate the Development of HEAs

Wang¹,

Li²

2023

High Entropy Materials - Microstructures and Properties

View full text Add to dashboard Cite

show abstract

“…ML methods have been gaining interest due to their intrinsic ability to construct complex non-linear relationships between input and output data. Recent developments in ML for alloy design have been appealing with the promise of exploring the phase formation, phase stability and properties of metallic materials (Abu-Odeh et al, 2018;Qu et al, 2019;Qiao et al, 2021a;Choi et al, 2021;Li et al, 2021;Nassar and Mullis, 2021;Xiong et al, 2021;Zhao et al, 2021;Yang et al, 2022), as well as processability of the alloys such as castability and 3D printability (Seede et al, 2021). These methods usually provide a reasonable calculation accuracy of typically >85%.…”

Section: Machine Learning For Alloy Developmentmentioning

confidence: 99%

“…Besides ANNs, other machine learning models such as support vector machines (SVMs) and decision trees (DTs) have been widely used in literature (Frydrych et al, 2021). New methods such as deep learning (DL) has also been gaining attention, eventually making machine learning a promising tool for material discovery, as well as material property prediction (Qiao et al, 2021a). Generally, unsupervised ML aims at finding the internal structure and the relationship among data, and supervised ML is used to compare the prediction results with the actual training data.…”

Section: Machine Learning For Alloy Developmentmentioning

confidence: 99%

“…While there has been some progress in computational HT screening, the experimental HT (HT alloy production and testing) requires much more development to reach the same level of maturity. For computational HT, ongoing efforts try to integrate novel machine learning and artificial intelligence with alloy design models; calculations can be conducted in various scales from atomic (first principle, such as density functional theory; DFT) to nano/micro (Molecular Dynamics; MD), micro/ macro (CALPHAD), and macro (Finite Element Modelling; FEM) (Lederer et al, 2018;Li et al, 2020;Qiao et al, 2021a;Sorkin et al, 2021b;Yaqi, 2021). Table 1 summarises the capabilities and limitations of each method and the typical scale each method is applicable in.…”

Section: High-throughput Screeningmentioning

confidence: 99%

See 1 more Smart Citation

High-Throughput CALPHAD: A Powerful Tool Towards Accelerated Metallurgy

Ghassemali

Conway

2022

Front. Mater.

View full text Add to dashboard Cite

Introduction of high entropy alloys or multi-principal element alloys around 15 years ago motivated revising conventional alloy design strategies and proposed new ways for alloy development. Despite significant research since then, the potential for new material discoveries using the MPEA concept has hardly been scratched. Given the number of available elements and the vastness of possible composition combinations, an unlimited number of alloys are waiting to be investigated! Discovering novel high-performance materials can be like finding a needle in a haystack, which demands an enormous amount of time and computational capacity. To overcome the challenge, a systematic approach is essential to meet the growing demand for developing novel high-performance or multifunctional materials. This article aims to briefly review the challenges, recent progress and gaps, and future outlook in accelerated alloy development, with a specific focus on computational high-throughput (HT) screening methods integrated with the Calculation of Phase Diagrams (CALPHAD) technique.

show abstract

“…[2,3] Owing to the high configurational entropy of mixing, HEAs often form simple solid solutions, e.g., face-centered cubic (FCC) or body-centered cubic (BCC) and hexagonal closed-packed (HCP) structure during solidification rather than complex phases and intermetallic compounds. [4][5][6] This may result in attractive performance characteristics relevant to structural applications, such as superior strength and ductility, [7][8][9][10] high strength at elevated temperatures, [11][12][13] and excellent wear resistance. [14][15][16][17][18] Several types of microstructures have been produced in HEAs, including single-phase, multiphase, and even amorphous alloys.…”

Section: Introductionmentioning

confidence: 99%

Effect of Aluminum on the Friction and Wear Behavior of AlxCrFeNi Medium‐Entropy Alloys

2022

Self Cite

View full text Add to dashboard Cite

Several high‐entropy alloys (HEAs) and medium‐entropy alloys (MEAs) are promising for wear applications due to their excellent strength and fracture toughness. Herein, a series of MEAs (x = 0.3, 0.5, 0.8, 1.0, 1.2) are prepared by a vacuum arc‐melting techniques. The effects of Al content on the crystal structures and mechanical properties are evaluated in terms of hardness and wear resistance. With an increase in Al content, the microstructure changes from face‐centered cubic (FCC) + body‐centered cubic (BCC)/B2 phases to B2/BCC phases. A higher volume fraction of the BCC phase with increasing Al content favors spinodal decomposition. The Vickers microhardness increases from 345HV (x = 0.3) to 486HV (x = 1.2) with increasing Al content; a nanohardness size effect is revealed by nanoindentation tests. For high Al contents (x = 1.2), the coefficient of friction and wear rate reach the lowest value when the worn surface is smooth with smaller debris, indicating improved wear resistance. Furthermore, this series of MEAs exhibits wear related to abrasion, adhesion, and oxidation; the dominant wear mechanism is influenced by the Al content.

show abstract

A focused review on machine learning aided high-throughput methods in high entropy alloy

Cited by 96 publications

References 237 publications

CALPHAD as a Toolbox to Facilitate the Development of HEAs

CALPHAD as a Toolbox to Facilitate the Development of HEAs

High-Throughput CALPHAD: A Powerful Tool Towards Accelerated Metallurgy

Effect of Aluminum on the Friction and Wear Behavior of AlxCrFeNi Medium‐Entropy Alloys

Contact Info

Product

Resources

About