PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 9, 2026Modern Physics Letters B0 citations

Physically Interpretable AI for Predicting Mechanical Properties of High-Entropy Alloys

View Full Paper
HSHongchul ShinSJSoonyeong JungHJHyeonjin Jo

Key Points

  • The aim is to develop a machine learning model that accurately predicts the mechanical properties of high-entropy alloys by preserving element-specific information.
  • Developed a composition-aware surrogate model using 13-dimensional tokens for each element.
  • Leveraged multi-head self-attention to learn inter-element interactions.
  • Applied the model to 232 molecular dynamics simulation samples of the CoCrCuFeNi HEA system.
  • Achieved ultimate tensile strength R² = 0.929 and Young's modulus R² = 0.982.
  • Model outperformed existing machine learning baselines under the same hyperparameter conditions.
  • Identified that Ni positively contributes to tensile strength while Cu negatively impacts Young's modulus.

Abstract

Existing machine learning studies on high-entropy alloys (HEAs) compress multi-element compositions into aggregate scalar descriptors thereby discarding element-specific physicochemical information and limiting both predictive accuracy and post-hoc interpretability. This study proposes a composition-aware surrogate model that represents each element as a 13-dimensional token combining 12 physicochemical descriptors with its mole fraction, and learns inter-element interactions through multi-head self-attention. Applied to 232 molecular dynamics simulation samples of the CoCrCuFeNi quinary HEA system, the model achieves ultimate tensile strength R 2 = 0.929 and Young's modulus R 2 = 0.982, outperforming machine learning baselines under identical hyperparameter optimization conditions. Shapley Additive explanations applied over the five-variable composition space reveal model-consistent trends including a positive contribution of Ni to ultimate tensile strength and a negative contribution of Cu to Young's modulus. The framework demonstrates that element representation design is critical for both prediction accuracy and interpretability on small-scale embedded-atom method molecular dynamics data and can be extended to higher-order multi-component HEA composition screening by simply adding element tokens.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Shin et al. (2026) studied this question.

synapsesocial.com/papers/69fecf94b9154b0b828767f9https://doi.org/10.1142/s0217984926501460
Ask AI
Helpful
Bookmark
Share
View Full Paper