logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

The γ/γ' microstructure in CoNiAlCr-based superalloys using triple-objective optimization

delete2023-08-10
delete2
delete
OA
AI
P
Pei Liu
黄
黄海友 (Haiyou Huang)
C
Cheng Wen
T
Turab Lookman *
Y
Yanjing Su *
DOI：10.1038/s41524-023-01090-9delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Optimizing several properties simultaneously based on small data-driven machine learning in complex black-box scenarios can present difficulties and challenges. Here we employ a triple-objective optimization algorithm deduced from probability density functions of multivariate Gaussian distributions to optimize the gamma' volume fraction, size, and morphology in CoNiAlCr-based superalloys. The effectiveness of the algorithm is demonstrated by synthesizing alloys with desired gamma/gamma' microstructure and optimizing gamma' microstructural parameters. In addition, the method leads to incorporating refractory elements to improve gamma/gamma' microstructure in superalloys. After four iterations of experiments guided by the algorithm, we synthesize sixteen alloys of relatively high creep strength from similar to 120,000 candidates of which three possess high gamma' volume fraction (>54%), small gamma' size (<480 nm), and high cuboidal gamma' fraction (>77%).
Keywords:
SINGLE-CRYSTAL SUPERALLOY
LATTICE MISFIT
CREEP-PROPERTIES
GAMMA'-PHASE
BEHAVIOR
DESIGN

Journal

npj Computational Materials cover
npj Computational Materials
IF:
11.9
Papers:
2.4K
Citations:
1.7W

Organization

No organization information available