Back to search

Cornell University

HIGH YIELD STRENGTH IN HIGH-ENTROPY ALLOYS DESIGNED WITH MACHINE-LEARNING METHODS

Abstract

dc:description.abstract

High Entropy Alloys (HEAs) have emerged as a novel paradigm in alloy design due to their superior material properties compared to the normal alloys. However, designing the HEAs with multiple metallic elements and their molar fractions is a challenging task. To resolve this issue, this project proposes a modern approach for designing new HEAs with high yield strength by utilizing machine learning techniques. The study outlines a comprehensive process for collecting and pre processing dataset from online resources, and explores the application of five different machine learning models, two hyperparameter tuning methods, and two optimization algorithms to design HEAs. The effectiveness of each approach is evaluated based on their ability to predict the yield strength of HEAs and determine the required molar fractions of metallic elements to obtain high yield strength. The findings of this study suggest that the proposed method can serve as a valuable reference in the experimental design process of HEAs.

Degree

thesis:*
Name thesis:degree_name
M.S., Mechanical Engineering
Level thesis:degree_level
Master of Science
Discipline thesis:degree_discipline
Mechanical Engineering
Grantor
Cornell University
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Han, Changhwi
Chair dc:contributor.chair
  • Yeo, Jingjie
Committee member dc:contributor.committeemember
  • Moridi, Atieh

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
16176435
Dc Identifier Other
ProQuest Submission ID: 11688
ProQuest Publication ID: 30419459

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Han, Changhwi. HIGH YIELD STRENGTH IN HIGH-ENTROPY ALLOYS DESIGNED WITH MACHINE-LEARNING METHODS. Master of Science thesis, Cornell University, 2023. https://hdl.handle.net/1813/113894