Machine learning driven rationally design of amorphous alloy with improved elastic models

Li, Zhuang; Long, Zhilin; Lei, Shan; Tang, Yawen

doi:10.1016/j.matdes.2022.110881

Cited by 13 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML regression algorithms are methodologies to construct mathematical models that predict numerical variables as a function of other variables, called descriptors or features. In the context of catalyst informatics, descriptors can be broadly classified in two categories: those related to the catalyst materials (for example, composition, structural, thermal, , electronic, physical, or chemical properties − ) and those related to the process itself, such as reaction conditions . In other words, descriptors are numerical representations of the various components of the process as understood by a machine.…”

Section: Introductionmentioning

confidence: 99%

MonteCat: A Basin-Hopping-Inspired Catalyst Descriptor Search Algorithm for Machine Learning Models

Garcia-Escobar,

Taniike,

Takahashi

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Proposing relevant catalyst descriptors that can relate the information on a catalyst's composition to its actual performance is an ongoing area in catalyst informatics, as it is a necessary step to improve our understanding on the target reactions. Herein, a small descriptor-engineered data set containing 3289 descriptor variables and the performance of 200 catalysts for the oxidative coupling of methane (OCM) is analyzed, and a descriptor search algorithm based on the workflow of the Basin-hopping optimization methodology is proposed to select the descriptors that better fit a predictive model. The algorithm, which can be considered wrapper in nature, consists of the successive generation of randombased modifications to the descriptor subset used in a regression model and adopting them depending on their effect on the model's score. The results are presented after being tested on linear and Support Vector Regression models with average cross-validation r 2 scores of 0.8268 and 0.6875, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

MonteCat: A Basin-Hopping-Inspired Catalyst Descriptor Search Algorithm for Machine Learning Models

Garcia-Escobar,

Taniike,

Takahashi

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…But good physical, chemical, and mechanical properties have been reported in using these alloys as coatings. Research that has been done in recent years focuses on the process of how to make amorphous Fe-based coatings [4,5]. It is stated in the literature that selective laser welding (SLM), and thermal spraying processes are instrumental methods for preparing Fe-based amorphous coatings due to fast solidification speed, high deposition rate, and low cost [6].…”

Section: Introductionmentioning

confidence: 99%

The effect of ultrasonic field on the microstructure and corrosion behavior of Fe-based amorphous coating applied to selective laser melting

Taheri

Razavi

2023

Mater. Res. Express

View full text Add to dashboard Cite

This study was conducted to investigate the effect of the ultrasonic field on the preparation of amorphous/crystalline Fe-based coatings. For this purpose, Fe86.3Si 5.9B3.2Cr4.6 (wt.%) powder was deposited on GTD-111 superalloy substrate with and without ultrasonic field by selective laser melting method. After coating, the corrosion behavior, microstructure, and hardness of the amorphous coating were investigated. The results showed that in conditions without ultrasonic vibration, the growth of grains starts in columnar form. At the same time, the use of an ultrasonic field inhibits columnar growth and creates equiaxed grains. In addition, the ultrasonic field increased the amorphous phase by 34.5%. This is attributed to the increased solidification rate caused by the cavitation effect. The experimental results of corrosion show that the self-corrosion current density of 6.83×10-7 A⋅cm2 is obtained due to the refinement of the microstructure and the increase of the amorphous phase. The wear results showed that the increase in the amorphous phase, as well as the decrease in the grain size, reduction in the grain ratio, and the increase in the tendency to equiaxed grains when using the ultrasonic field, reduce the coefficient of friction by 97%.

show abstract

A review of the preparation and prospects of amorphous alloys by mechanical alloying

Yuan,

Zhang,

et al. 2024

Journal of Materials Research and Technology

View full text Add to dashboard Cite

Machine learning driven rationally design of amorphous alloy with improved elastic models

Cited by 13 publications

References 47 publications

MonteCat: A Basin-Hopping-Inspired Catalyst Descriptor Search Algorithm for Machine Learning Models

MonteCat: A Basin-Hopping-Inspired Catalyst Descriptor Search Algorithm for Machine Learning Models

The effect of ultrasonic field on the microstructure and corrosion behavior of Fe-based amorphous coating applied to selective laser melting

A review of the preparation and prospects of amorphous alloys by mechanical alloying

Contact Info

Product

Resources

About