Machine learning-driven insights into phase prediction for high entropy alloys

The unique properties of high-entropy alloys (HEAs) have attracted considerable attention, largely due to their dependence on the choice among three distinct phases: solid solution (SS), intermetallic compound (IM), or a blend of both (SS + IM). For this reason, precise phase prediction is key to id...

Full description

Saved in:
Bibliographic Details
Main Authors: Reliance Jain, Sandeep Jain, Sheetal Kumar Dewangan, Lokesh Kumar Boriwal, Sumanta Samal
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Journal of Alloys and Metallurgical Systems
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949917824000579
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255646094524416
author Reliance Jain
Sandeep Jain
Sheetal Kumar Dewangan
Lokesh Kumar Boriwal
Sumanta Samal
author_facet Reliance Jain
Sandeep Jain
Sheetal Kumar Dewangan
Lokesh Kumar Boriwal
Sumanta Samal
author_sort Reliance Jain
collection DOAJ
description The unique properties of high-entropy alloys (HEAs) have attracted considerable attention, largely due to their dependence on the choice among three distinct phases: solid solution (SS), intermetallic compound (IM), or a blend of both (SS + IM). For this reason, precise phase prediction is key to identifying the optimal element combinations needed to develop HEAs with the required characteristics. Due to large compositional domain of HEAs is opportune to design new HEAs with desired output. A machine learning tool is exploited to discover and characterize high entropy alloys with satisfying targets. Herein, a method of designing substitutional high entropy alloys with optimization of input features and predict their phase formation, using different ML algorithms are proposed. The ML models such as multi layer precreptron MLP, Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), KNN, XGB nad SVM Classifier algorithm were used for the identifying the phase of HEAs. After assessing the accuracy and tuning of each model, an random forest classifier (accuracy = 0.914. precision = 0.916, ROC-AUC score = 0.97) model showed the best predictive capabilities for phase prediction. The new HEA was designed based on prediction and successfully validated with thermodynamic simulation. Data Availability: Data will be made available on request
format Article
id doaj-art-b5886c8acbb04e7f98129b23b4d4c461
institution OA Journals
issn 2949-9178
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Journal of Alloys and Metallurgical Systems
spelling doaj-art-b5886c8acbb04e7f98129b23b4d4c4612025-08-20T01:56:49ZengElsevierJournal of Alloys and Metallurgical Systems2949-91782024-12-01810011010.1016/j.jalmes.2024.100110Machine learning-driven insights into phase prediction for high entropy alloysReliance Jain0Sandeep Jain1Sheetal Kumar Dewangan2Lokesh Kumar Boriwal3Sumanta Samal4Department of Robotics and Automation, Prestige Institute of Engineering Management and Research, Indore, Madhya Pradesh 452010, India; Corresponding author.Department of Advanced Materials Science and Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea; Department of Metallurgical Engineering and Materials Science, Indian Institute of Technology Indore, Simrol, Indore, Madhya Pradesh 453552, India; Corresponding author at: Department of Advanced Materials Science and Engineering, Sungkyunkwan University, Suwon 16419, Republic of KoreaDepartment of Materials Science and Engineering, Ajou University, Suwon 16499, Republic of KoreaDepartment of Mechanical Engineering, Prestige Institute of Engineering Management and Research, Indore, Madhya Pradesh 452010, IndiaDepartment of Metallurgical Engineering and Materials Science, Indian Institute of Technology Indore, Simrol, Indore, Madhya Pradesh 453552, IndiaThe unique properties of high-entropy alloys (HEAs) have attracted considerable attention, largely due to their dependence on the choice among three distinct phases: solid solution (SS), intermetallic compound (IM), or a blend of both (SS + IM). For this reason, precise phase prediction is key to identifying the optimal element combinations needed to develop HEAs with the required characteristics. Due to large compositional domain of HEAs is opportune to design new HEAs with desired output. A machine learning tool is exploited to discover and characterize high entropy alloys with satisfying targets. Herein, a method of designing substitutional high entropy alloys with optimization of input features and predict their phase formation, using different ML algorithms are proposed. The ML models such as multi layer precreptron MLP, Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), KNN, XGB nad SVM Classifier algorithm were used for the identifying the phase of HEAs. After assessing the accuracy and tuning of each model, an random forest classifier (accuracy = 0.914. precision = 0.916, ROC-AUC score = 0.97) model showed the best predictive capabilities for phase prediction. The new HEA was designed based on prediction and successfully validated with thermodynamic simulation. Data Availability: Data will be made available on requesthttp://www.sciencedirect.com/science/article/pii/S2949917824000579High entropy alloysPhase predictionMachine learning. Model validationNew alloy design
spellingShingle Reliance Jain
Sandeep Jain
Sheetal Kumar Dewangan
Lokesh Kumar Boriwal
Sumanta Samal
Machine learning-driven insights into phase prediction for high entropy alloys
Journal of Alloys and Metallurgical Systems
High entropy alloys
Phase prediction
Machine learning. Model validation
New alloy design
title Machine learning-driven insights into phase prediction for high entropy alloys
title_full Machine learning-driven insights into phase prediction for high entropy alloys
title_fullStr Machine learning-driven insights into phase prediction for high entropy alloys
title_full_unstemmed Machine learning-driven insights into phase prediction for high entropy alloys
title_short Machine learning-driven insights into phase prediction for high entropy alloys
title_sort machine learning driven insights into phase prediction for high entropy alloys
topic High entropy alloys
Phase prediction
Machine learning. Model validation
New alloy design
url http://www.sciencedirect.com/science/article/pii/S2949917824000579
work_keys_str_mv AT reliancejain machinelearningdriveninsightsintophasepredictionforhighentropyalloys
AT sandeepjain machinelearningdriveninsightsintophasepredictionforhighentropyalloys
AT sheetalkumardewangan machinelearningdriveninsightsintophasepredictionforhighentropyalloys
AT lokeshkumarboriwal machinelearningdriveninsightsintophasepredictionforhighentropyalloys
AT sumantasamal machinelearningdriveninsightsintophasepredictionforhighentropyalloys