Modeling glass-forming ability of bulk metallic glasses using computational intelligent techniques

Majid, Abdul; Ahsan, Syed Bilal; Tariq, Naeem ul Haq

doi:10.1016/j.asoc.2014.11.037

Cited by 19 publications

(12 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the established dataset, people have applied a variety of ML algorithms to study MGs with a good glass-forming likelihood [17, 71, 74-76, 78, 79, 85-87] (see figures 3(b), (c) and (e)) or a good GFA [17,[74][75][76][87][88][89][90][91][92] (see figures 3(b), (d) and (f)). These mainly include support vector machine (SVM) [17,74,78,79,92], random forest (RF) [17,66,75,76,90], Gaussian process regression (GPR) [17,74] and artificial neural network (ANN) [17,71,79,87,89]. However, to effectively train an ML model, one has to design proper 'fingerprints' or descriptors for their data (data featurization), as shown in figure 3(b).…”

Section: Data Driven Design Approachmentioning

confidence: 99%

Recent development of chemically complex metallic glasses: from accelerated compositional design, additive manufacturing to novel applications

et al. 2022

View full text Add to dashboard Cite

Metallic glasses or amorphous alloys are an important engineering material that has a history of research of about 80-90 years. While different fast cooling methods were developed for multi-component metallic glasses between 1960s and 1980s, 1990s witnessed a surge of research interest in the development of bulk metallic glasses. Since then, one central theme of research in the metallic-glass community has been compositional design that aims to search for metallic glasses with a better glass forming ability, a larger size and/or more interesting properties, which can hence meet the demands from more important applications. In this review article, we focus on the recent development of chemically complex metallic glasses, such as high entropy metallic glasses, with new tools that were not available or mature yet until recently, such as the state-of-the-art additive manufacturing technologies, high throughput materials design techniques and the methods for big data analyses (e.g. machine learning and artificial intelligence). We also discuss the recent use of metallic glasses in a variety of novel and important applications, from personal healthcare, electric energy transfer to nuclear energy that plays a pivotal role in the battle against global warming.

show abstract

Section: Data Driven Design Approachmentioning

confidence: 99%

Recent development of chemically complex metallic glasses: from accelerated compositional design, additive manufacturing to novel applications

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Interestingly, configurational entropy was not considered in any of their models which turned out to be most important feature in this study. Another independent investigation by Majid et al [12] demonstrated few algorithms, viz., support vector regression (SVR), artificial neural network (ANN), general regression neural network (GRNN) using the characteristic temperatures of the BMGs as the input parameters. However, the accuracies of the models developed were not satisfying.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Glass Forming Ability of Bulk Metallic Glasses Using Machine Learning

Reddy

Kandavalli

Saboo

et al. 2021

Integr Mater Manuf Innov

View full text Add to dashboard Cite

Bulk metallic glass has been a fascinating class of metallic systems with remarkable corrosion resistance, elastic modulus, and wear resistance, while evaluating the glass forming ability has been a very interesting aspect for decades. Machine learning techniques, viz., artificial neural networks and KNearest Regressor-based models have been developed in this work to predict the glass forming ability, given the composition of the bulk metallic glassy alloy. A new criterion of classification of atoms present in a bulk metallic glass is proposed. Feature importance analysis confirmed that the accuracy of the prediction depends mainly on change in enthalpy of mixing and change in entropy of mixing. However, among the artificial neural network models and KNearest Regressor models developed, the former showed a promising performance in prediction of the glass formation ability (critical thickness). It has been successfully demonstrated and validated with experimental critical thickness that the glass forming ability can be predicted using an artificial neural network given the elemental composition alone. A computational algorithm was also developed to classify the atoms as big/small in each given alloy. The outcome of this algorithm is used as input parameters to the ANN and other machine learning models used in this work.

show abstract

“…Another independent investigation by Majid et.al. [12] demonstrated few algorithms viz., support vector regression (SVR), artificial neural network (ANN), general regression neural network (GRNN) using the characteristic temperatures of the BMGs as the input parameters. However, the accuracies of the models developed weren't satisfying.…”

Section: Introductionmentioning

confidence: 99%

“…Hence the prediction model proposed by Majid et.al. [12] cannot be used for designing virtual BMG alloys.…”

Section: Introductionmentioning

confidence: 99%

“…al. 's[12] cannot be applied without conducting experiments, as the characteristic temperatures (glass transition temperature, undercooling range etc.,), the inputs for such a model are to be measured for a synthesized a BMG, hence cannot be used for designing virtual BMGs. In contrast, the model demonstrated in this work successfully predicts the GFA, i.e., the Dmax for virtual alloys, just by considering their chemical composition as input, with an accuracy above 85%.Further, earlier studies neither analysed multicollinearity nor conducted feature importance, which are crucial to identify the parameters which are highly influential on the GFA or Dmax of a BMG.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Glass Forming Ability of Bulk Metallic Glasses-Machine-Learning

Gedi

Saboo

Ayyagari

2021

Preprint

View full text Add to dashboard Cite

Bulk-Metallic-Glass has been a fascinating class of metallic systems with remarkable corrosion resistance, elastic modulus and wear resistance, while evaluating the glass forming ability has been a very interesting aspect for decades. Machine learning techniques viz., artificial neural networks and random-forest based models have been developed in this work to predict the glass forming ability, given the composition of the bulk metallic glassy alloy. A new criterion of classification of atoms present in a bulk metallic glassy alloy is proposed. Feature importance analysis confirmed that the accuracy of the prediction depends mainly on change in enthalpy of mixing and change in entropy of mixing. However, among the artificial neural network random forest models developed, the former showed a promising accuracy in prediction of the glass formation ability (critical thickness). It has been successfully demonstrated and validated with experimental critical thickness that the glass forming ability can be predicted using an artificial neural network given the elemental composition alone. A computational algorithm was also developed to classify the atoms as big/ small in a given alloy. The outcome of this algorithm was used by models developed by training with experimental data.

show abstract

Modeling glass-forming ability of bulk metallic glasses using computational intelligent techniques

Cited by 19 publications

References 26 publications

Recent development of chemically complex metallic glasses: from accelerated compositional design, additive manufacturing to novel applications

Recent development of chemically complex metallic glasses: from accelerated compositional design, additive manufacturing to novel applications

Prediction of Glass Forming Ability of Bulk Metallic Glasses Using Machine Learning

Prediction of Glass Forming Ability of Bulk Metallic Glasses-Machine-Learning

Contact Info

Product

Resources

About