Exploration of characteristic temperature contributions to metallic glass forming ability

Schultz, L.; Afflerbach, Benjamin; Francis, Carter; Voyles, Paul M.; Szlufarska, Izabela; Morgan, Dane

doi:10.1016/j.commatsci.2021.110494

Cited by 9 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset was extracted from various available data sources, including Schultz's dataset, 30 Ren's dataset, 31 Peng's dataset, 32 and Deng's dataset. 12 2663 pieces of MG data that contained D max values, chemical compositions, and three characteristic temperatures ( T g , T x , and T l ) were used.…”

Section: Methodsmentioning

confidence: 99%

“…In this work, a large T g dataset containing 1764 pieces of data and a large D max dataset containing 1296 pieces of data were created by the acquisition of open-source datasets 12,[30][31][32] and manual gathering from published literature reports. Mathematical formulas were employed to establish 129 and 133 features for T g and the D max dataset, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven machine learning prediction of glass transition temperature and the glass-forming ability of metallic glasses

Zhang,

Zhao,

Zhong

et al. 2023

Nanoscale

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Data-driven machine learning prediction of glass transition temperature and the glass-forming ability of metallic glasses

Zhang,

Zhao,

Zhong

et al. 2023

Nanoscale

View full text Add to dashboard Cite

show abstract

“…Table 4 [319][320][321][322][323][324][325][326][342][343][344][345][346][347][350][351][352]357,362,[368][369][370][371][372][373][374][375][376][377][378] lists AI efforts in predicting properties, classifying new sets of materials, and creating new types of amorphous alloys. Each of the algorithms described in this table is used with a training set formed by a certain number of features (descriptors of alloy composition), or input parameters, specified by each relevant publication.…”

Section: Artificial Intelligence Algorithmsmentioning

confidence: 99%

Latest Advances in Manufacturing and Machine Learning of Bulk Metallic Glasses

et al. 2023

View full text Add to dashboard Cite

In this review, two interrelated areas are focused on for the development of novel amorphous metallic alloys, namely, materials processing and machine learning techniques for the design of new alloy compositions. Findings, barriers, and opportunities are described, targeting powder production and sintering, additive manufacturing, and postprocessing techniques, followed by the latest developments in artificial intelligence algorithms for both the design of new alloys and for alloy classification tasks.

show abstract

“…To construct the PRSD features, we follow the approach of Ref. [37]. We start with a set of characteristic temperatures defined as A = {T gm , T * g , T * , T * A , T g , T , T A , T l }.…”

Section: Datamentioning

confidence: 99%

“…Model types included are Gradient Boosting (GB), eXtreme Gradient Boosting (XGBoost), and Random Forest (RF) which are ensemble models [41,43,44]. We used ensemble models because of their tendency to outperform linear models in D max predictions in our past research [37]. Models were trained on PRSD feature and original characteristic temperature feature sets.…”

Section: Machine Learningmentioning

confidence: 99%

Molecular Dynamic Characteristic Temperatures for Predicting Metallic Glass Forming Ability

Schultz¹,

Afflerbach²,

Szlufarska³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We explore the use of characteristic temperatures derived from molecular dynamics to predict aspects of metallic Glass Forming Ability (GFA). Temperatures derived from cooling curves of self-diffusion, viscosity, and energy were used as features for machine learning models of GFA. Multiple target and model combinations with these features were explored. First, we use the logarithm of critical casting thickness, log 10 (D max ), as the target and trained regression models on 21 compositions. Application of 3-fold cross-validation on the 21 log 10 (D max ) alloys showed only weak correlation between the model predictions and the target values. Second, the GFA of alloys were quantified by melt-spinning or suction casting amorphization behavior, with alloys that showed crystalline phases after synthesis classified as Poor GFA and those with pure amorphous phases as Good GFA. Binary GFA classification was then modeled using decision tree-based methods (random forest and gradient boosting models) and were assessed with nested-cross validation. The maximum F1 score for the precision-recall with Good Glass Forming Ability as the positive class was 0.82 ± 0.01 for the best model type. We also compared using simple functions of characteristic temperatures as features in place of the temperatures themselves and found no statistically significant difference in predictive abilities. Although the predictive ability of the models developed here are modest, this work demonstrates clearly that one can use molecular dynamics simulations and machine learning to predict metal glass forming ability.

show abstract

Exploration of characteristic temperature contributions to metallic glass forming ability

Cited by 9 publications

References 9 publications

Data-driven machine learning prediction of glass transition temperature and the glass-forming ability of metallic glasses

Data-driven machine learning prediction of glass transition temperature and the glass-forming ability of metallic glasses

Latest Advances in Manufacturing and Machine Learning of Bulk Metallic Glasses

Molecular Dynamic Characteristic Temperatures for Predicting Metallic Glass Forming Ability

Contact Info

Product

Resources

About