Theory-guided ML models achieve R²=0.98 for temperature-dependent yield strength in RCCAs and evaluate element impacts on phase stability and ductility, supporting an on-demand composition predictor and screener.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Composition design of refractory compositionally complex alloys using machine learning models
Theory-guided ML models achieve R²=0.98 for temperature-dependent yield strength in RCCAs and evaluate element impacts on phase stability and ductility, supporting an on-demand composition predictor and screener.