Supervised machine learning-based multi-class phase prediction in high-entropy alloys using robust databases

Primer Autor
Onate, Angelo
Co-autores
Sanhueza, Juan Pablo
Zegpi, Diabb
Tuninetti, Victor
Ramirez, Jesus
Medina, Carlos
Melendrez, Manuel
Rojas, David
Título
Supervised machine learning-based multi-class phase prediction in high-entropy alloys using robust databases
Editorial
ELSEVIER SCIENCE SA
Revista
JOURNAL OF ALLOYS AND COMPOUNDS
Lenguaje
en
Resumen
This work evaluated the phase prediction capability of high entropy alloys using four supervised machine learning models K-Nearest Neighbors (KNN), Multinomial Regression, Extreme Gradient Boosting (XGBoost), and Random Forest. The study addresses the challenge of predicting multicomponent alloys by considering the overlapping of multicategorical stability parameters. Eight prediction classes (FCC, BCC, FCC+BCC, FCC+Im, BCC+Im, FCC+BCC+Im, Im and AM) were used. Finally, the predicted results were compared with those of two new alloys fabricated by induction melting in a controlled atmosphere using X-ray diffraction (XRD). The results indicate that with a robust database, appropriate data treatment, and training, satisfactory and competitive prediction indicators can be obtained with traditional machine learning predictions based on four prediction classes: Solid Solution (SS), Solid Solution with Intermetallic (SS+Im), intermetallic (Im), and amorphous (AM). The best predictive model obtained from the four evaluated models was Random Forest, with an accuracy of 72.8% and ROC AUC of 93.1%.
Fecha Publicación
2023
Tipo de Recurso
artículo original
doi
10.1016/j.jallcom.2023.171224
Formato Recurso
PDF
Palabras Claves
Phase prediction
High entropy alloys
Machine Learning
Intermetallics prediction
Ubicación del archivo
http://dx.doi.org/10.1016/j.jallcom.2023.171224
Categoría OCDE
Química
Ciencia de Materiales
Metalurgia e Ingeniería Metalúrgica
Materias
Predicción de fase
Aleaciones de alta entropía
Aprendizaje automático
Predicción de intermetálicos
Identificador del recurso (Mandatado-único)
artículo original
Versión del recurso (Recomendado-único)
versión publicada
Derechos de acceso
metadata
Access Rights
metadata
Id de Web of Science
WOS:001036419600001
ISSN
0925-8388
Tipo de ruta
hibrida
Categoría WOS
Química
Ciencia de Materiales
Metalurgia e Ingeniería Metalúrgica
Referencia del Financiador (Mandatado si es aplicable-repetible)
ANID-FONDECYT 1221600
UdeC 220.098.005-INV
WBI/AGCID RI02 (DIE23-0001)
UFRO DI22-0067
ANID FONDECYT 1221600
Colecciones
Colección Publicaciones Científicas
Colección ANID
Revisa las metricas alternativas de Almetrics
Revisa las citaciones de Dimensions