Design of super-hard high-entropy ceramics coatings via machine learning

Xu, Xiaoqian; Wang, Xiaobo; Wu, Shaoyu; Yan, Luchun; Guo, Tao; Gao, Kewei; Pang, Xiaolu; Volinsky, Alex A.

doi:10.1016/j.ceramint.2022.07.145

Cited by 17 publications

(7 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By combining ML and high‐throughput experimental methods, it is possible to rapidly screen superhard high‐entropy ceramic materials. Xu et al [247] . employed the random forest algorithm to predict the hardness of advanced ceramic coatings based on the coating composition and process parameters.…”

Section: Applications Of Htc In Materials Developmentmentioning

confidence: 99%

Advances in data‐assisted high‐throughput computations for material design

Xu,

Zhang,

Huo

et al. 2023

Materials Genome Engineering Advances

View full text Add to dashboard Cite

Extensive trial and error in the variable space is the main cause of low efficiency and high cost in material development. The experimental tasks can be reduced significantly in the case that the variable space is narrowed down by reliable computer simulations. Because of their numerous variables in material design, however, the variable space is still too large to be accessed thoroughly even with a computational approach. High‐throughput computations (HTC) make it possible to complete a material screening in a large space by replacing the conventionally manual and sequential operations with automatic, robust, and concurrent streamlines. The efficiency of HTC, which is one of the pillars of materials genome engineering, has been verified in many studies, but its applications are still limited by demanding computational costs. Introduction of data mining and artificial intelligence into HTC has become an effective approach to solve the problem. In the past years, many studies have focused on the development and application of HTC and data combined approaches, which is considered as a new paradigm in computational materials science. This review focuses on the main advances in the field of data‐assisted HTC for material research and development and provides our outlook on its future development.

show abstract

Section: Applications Of Htc In Materials Developmentmentioning

confidence: 99%

Advances in data‐assisted high‐throughput computations for material design

Xu,

Zhang,

Huo

et al. 2023

Materials Genome Engineering Advances

View full text Add to dashboard Cite

show abstract

“…73 To gain a deeper understanding of the relationship between the feature variables and the target variables, the SHAP module is used to draw SHAP summary plot, which could identify whether the contribution of input variables to each prediction is positive or negative. 34,74 The color from red to blue in Figure 7B represents the value of feature from high to low. It is clear that the SHAP value increases as the value of 𝑟 𝐴 ∕𝑟 𝐶 increases, which means that a higher 𝑟 𝐴 ∕𝑟 𝐶 could have a positive to the output.…”

Section: Features Analysismentioning

confidence: 99%

“…In the field of properties prediction in HECs, recently, Xu et al 34 developed a random forest (RF) model to predict the hardness of HEC coatings and optimized this model by active learning. As a result, a new (Al, Cr, Nb, Ta, Ti) N coating with a hardness of 40.1 GPa, which was 9% higher than the optimal hardness of the original quinary system, was successfully prepared.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning‐based crystal structure prediction for high‐entropy oxide ceramics

Liu,

Wang,

Gao

et al. 2023

J Am Ceram Soc.

View full text Add to dashboard Cite

Predicting the crystal structure is essential to address the reliance on serendipity for facilitating the discovery and design of high‐performance high‐entropy oxides (HEOs). Here, three classic algorithms‐based machine learning models to predict the crystal structure of HEOs are successfully established and analyzed by combining five metrics, and the XGBoost classifier shows excellent accuracy and robustness with ACC and F1 scores up to 0.977 and 0.975, respectively. SHAP summary plot indicates that the anion‐to‐cation radius ratio (rA/rC) has the greatest impact on crystal structure, followed by difference in Pauling and Mulliken electronegativities (ΔχPauling and ΔχMulliken). It is noteworthy that the rA/rC, ΔχPauling, and ΔχMulliken lower than 0.35, 0.1, and 0.2, respectively, tend to lead to a fluorite crystal structure, whereas rock‐salt and spinel crystal structures are always formed. This work is expected to facilitate the discovery and design of HEOs with tailorable crystal structures and properties.

show abstract

“…A gradient‐enhanced regression model that integrates environmental and chemical descriptors to forecast the corrosion resistance of HEAs was developed by Roy [25] . Xu et al [26] . employed a random forest (RF) model with the accuracy ( R 2 ) of 0.92 to create a super‐hard high‐entropy ceramic coating.…”

Section: Introductionmentioning

confidence: 99%

Data mining accelerated the design strategy of high‐entropy alloys with the largest hardness based on genetic algorithm optimization

Jin,

Luo,

Wang

et al. 2024

Materials Genome Engineering Advances

View full text Add to dashboard Cite

This article proposed a design strategy that integrated machine learning models based on random forest and genetic algorithm (GA) for the rapid screening of hardness in the AlCoCrCuFeMoNiTi high‐entropy alloys system. Through feature engineering and modeling, valence electron concentration, atomic size difference (δr), Pauling electronegativity difference (Δχ), geometric parameters (Λ), and the Cr content were identified as the five key features in the database. The GA was employed to search for alloys with superior hardness and guided synthesis. After three iterations, the HEA Al18Co21Cr23Fe23Mo15 exhibiting the highest predicted hardness (868.8 HV) was identified. The alloy was predominantly composed of BCC, ordered B2, and σ phases, with an experimental hardness of 899.8 ± 9.9 HV, which as approximately 5.38% greater than the maximum hardness observed in the original dataset. The design strategy can also solve other regression problems and pave the way for optimizing material performance in various engineering applications.

show abstract

Design of super-hard high-entropy ceramics coatings via machine learning

Cited by 17 publications

References 56 publications

Advances in data‐assisted high‐throughput computations for material design

Advances in data‐assisted high‐throughput computations for material design

Machine learning‐based crystal structure prediction for high‐entropy oxide ceramics

Data mining accelerated the design strategy of high‐entropy alloys with the largest hardness based on genetic algorithm optimization

Contact Info

Product

Resources

About