Virtual Prediction of Material Properties

To start working with materials, it is most important to determine the properties to ensure its suitability but sometimes it is not only difficult but also time consuming and costly affair to arrange an experimentation with the materials. To overcome this problem some free libraries of python like p...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Materials today : proceedings Ročník 62; s. 2774 - 2779
Hlavný autor: Kumar, Arpan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 2022
Predmet:
Classification
Machine Learning
MAPI
Materials
Matminer
Matplotlib
Pymatgen
Python
Scikit-Learn
Seaborn
Sklearn
Support Vector Machine
Sklearn
Matplotlib
Pymatgen
Matminer
Materials
Classification
Support Vector Machine
Seaborn
Machine Learning
MAPI
Scikit-Learn
Python
ISSN:2214-7853, 2214-7853
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:To start working with materials, it is most important to determine the properties to ensure its suitability but sometimes it is not only difficult but also time consuming and costly affair to arrange an experimentation with the materials. To overcome this problem some free libraries of python like pymatgen, matminer etc. are used with Materials Application Programming Interface (API)to gather and process datasets and when combined with Machine learning libraries like Sklearn, a machine Learning Model can be built. In the present work, with the aid of glass_ternary_hipt dataset, a metallic glass formation dataset for Co-Fe-Zr, Co-Ti-Zr, Co-V-Zr and Fe-Ti-Nb ternary alloy systems, a Support Vector Machine Classifier, is built as an example to predict the glass forming ability of the alloys. The accuracy of the model is checked and a heatmap is generated to show the correlation between the features and the target. The development of these program is very intuitive with these packages and python for prediction of material properties virtually.
ISSN:2214-7853
2214-7853
DOI:10.1016/j.matpr.2022.01.355