Formation ability descriptors for high-entropy carbides established through high-throughput methods and machine learning

Meng, Hong; Yu, Renwang; Tang, Zhongyu; Wen, Zihao; Chu, Yanhui

doi:10.1016/j.xcrp.2023.101512

Cited by 9 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, the microstructure evolution of phase decomposition is first observed in the V15 sample with a V content of 0.15, which is in agreement with the calculated phase diagram. In addition, the lattice distortion (δ) and mixed enthalpy ( ) are widely recognized as important parameters for the criterion of single-phase formation for high-entropy alloys and ceramics [18,37,38]. The variation tendencies of the lattice distortion and mixed enthalpy with increasing V content are calculated and depicted in Fig.…”

Section: Effect Of V Addition On Phase Compositionmentioning

confidence: 99%

“…For a variety of multi-component carbide ceramics with nearly infinite combinations of metal elements, many systems can hardly form single-phase multi-component carbide ceramics. In fact, the single-phase formation ability of multi-component carbide ceramics has been predicted via first-principle density functional theory (DFT) and machine learning [17,18]. Meng et al [19] selected 8 parameters with the best prediction of single-phase formation ability out of 22 parameters of formation ability and successfully predicted the single-phase formation ability of equimolar multi-component ceramics through machine learning and genetic algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Phase transition of multi-component (TiZrVNb)C ceramics—Part II: From single phase to multiple phases via adjusting V content

Kong,

Chen,

Huo

et al. 2024

Journal of Advanced Ceramics

View full text Add to dashboard Cite

To address the relatively mediocre mechanical properties of single-phase multi-component carbide ceramics, a phase transition from a single phase to multiple phases was proposed to achieve superior mechanical properties. A series of (TiZrV x Nb)C 0.8 ceramics with different V contents were fabricated by spark plasma sintering (SPS). The influence of the V content on the phase composition, microstructural evolution, and mechanical properties was investigated in detail. The transition behavior from a single phase to multiple phases is discovered and discussed. The formation of the Zr-rich phase and Zr-poor phase can be attributed to the increase in lattice distortion and mixed enthalpy caused by the addition of V. A nanometer lamellar structure with a semi-coherent interface obtained via in situ decomposition is reported for the first time in multi-component carbide ceramics. The semi-coherent interfaces with high dislocation density and strain concentration effectively improve the mechanical properties, grain refinement, and multi-phase formation. The optimal comprehensive mechanical properties of the Vickers hardness (26.3 GPa), flexural strength (369 MPa), and fracture toughness (3.1 MPa•m 1/2 ) were achieved for the sample with 20 mol% V.

show abstract

Section: Effect Of V Addition On Phase Compositionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Phase transition of multi-component (TiZrVNb)C ceramics—Part II: From single phase to multiple phases via adjusting V content

Kong,

Chen,

Huo

et al. 2024

Journal of Advanced Ceramics

View full text Add to dashboard Cite

show abstract

“…It is also worth noting that the experimentally studied compositional libraries are often narrowed by preliminary theoretical calculations using DFT, MD, ML, or CALPHAD methods. [16][17][18][19][20][21][66][67][68][69] However, this study focuses on the experimental part of the combinatorial design of MPEAs; therefore, only a brief overview of this theoretical field is given here. The high-throughput computational techniques can help to identify the compositions promising from the point of view of application demands, thereby reducing the time and effort invested in the experimental investigations.…”

Section: Complementary Theoretical Approaches Of Combinatorial Design...mentioning

confidence: 99%

Combinatorial Design of Novel Multiprincipal Element Alloys Using Experimental Techniques

Gubicza

2023

Adv Eng Mater

View full text Add to dashboard Cite

Multiprincipal element alloys (MPEAs) including high‐entropy alloys are in the focus of materials science since many MPEA compositions exhibit outstanding mechanical and physical properties. These alloys contain 3–6 constituents with similar fractions; therefore, MPEAs correspond to the unexplored middle part of the phase diagrams. The phase composition and the performance of MPEAs are strongly influenced by their chemistry. Thus, it is very important to reveal the correlation between the composition, the structure, and the properties of MPEAs. On the other hand, this task is challenging due to the vast composition space of these alloys. The processing and characterization of combinatorial specimens can yield a fast mapping of compositional libraries of MPEAs. Herein, the experimental techniques developed for manufacturing and investigation of these alloys are overviewed and the results are critically discussed. Finally, further development directions in the field of combinatorial MPEAs are recommended in order to improve the study of the different alloy compositions.

show abstract

“…Zhang et al 12 used artificial neural network(ANN) and support vector machine (SVM) model to identify single-phase HECs and evaluated the single-phase probabilities of 90 HECs that have not yet been experimentally 4 reported, with a prediction accuracy as high as 98.2%. Meng et al 16 used high-throughput synthesis and calculation combined with ML methods to identify 22 phase-forming ability descriptors for novel HECs, achieving a verification accuracy at least 25.3% higher than previously reported, which provide theoretical guidance for discovering HECs. Tang et al 17 proposed a ML strategy based on bond parameters (bond order, bond ionicity, and bond length) to explore new HECs with excellent mechanical properties, the mean absolute error (MAE) and R 2 of their model were 32.2 GPa and 0.84.…”

Section: Introductionmentioning

confidence: 99%

Predicting Mechanical Properties of Non-Equimolar High-Entropy Carbides using Machine Learning

Zhao,

Cheng

et al. 2024

Preprint

View full text Add to dashboard Cite

High-entropy carbides (HECs) have garnered significant attention due to their unique mechanic properties. However, the design of novel HECs has been limited by extensive trial-and-error strategies, along with insufficient knowledge and computational capabilities. In this work, the intrinsic correlations between elements in the high-dimensional compositional space of HECs are investigated using high-throughput density functional theory calculations and two machine learning models, which enable us to predict the Young's modulus, hardness and wear resistance only using a chemical formula. Our models demonstrate low root mean square error (11.5GPa) and mean absolute errors (9.0GPa) in predicting the mechanic properties of HECs with arbitrary non-equimolar compositions. We further establish a database of 566,370 HECs and identified 15 novel HECs with best mechanical properties. Our models can rapidly explore the mechanical properties of HECs with descriptor-property correlation analysis, and hence provide an efficient method for accelerating the design of non-equimolar high-entropy materials with desired performance.

show abstract

Formation ability descriptors for high-entropy carbides established through high-throughput methods and machine learning

Cited by 9 publications

References 43 publications

Phase transition of multi-component (TiZrVNb)C ceramics—Part II: From single phase to multiple phases via adjusting V content

Phase transition of multi-component (TiZrVNb)C ceramics—Part II: From single phase to multiple phases via adjusting V content

Combinatorial Design of Novel Multiprincipal Element Alloys Using Experimental Techniques

Predicting Mechanical Properties of Non-Equimolar High-Entropy Carbides using Machine Learning

Contact Info

Product

Resources

About