Machine learning potential-driven prediction of high-entropy ceramics with ultra-high melting points
Abstract
Developing high-entropy ceramics (HECs) with ultra-high melting points (Tm) is crucial for their applications in ultra-high-temperature environments. However, related research has seldom been reported. Here, taking high-entropy diborides (HEBs) as an example, we develop a data-driven method to efficiently explore HEBs with ultra-high Tm via transferable machine-learning-potential-based molecular dynamics (MD). Specifically, a moment tensor potential (MTP) for HEBs with nine transition metal elements of group IVB, VB, and VIB is first constructed based on unary and binary diborides. Further studies on the performance of our constructed MTP have confirmed its remarkable accuracy, transferability, and reliability across both equimolar and non-equimolar HEB systems. Tm of HEBs are then accurately simulated through MD simulations based on the constructed MTP, and 24 features are simultaneously collected to enable reliable machine learning training. Five descriptors with the gradient boosting regression model are derived as the optimal combination for accurate Tm predictions in HEBs with genetic algorithms. Based on our established model, Tm of 32563 HEBs are eventually determined, achieving the maximum Tm of 3688 K in (Ti0.1Zr0.1Hf0.6Ta0.2)B2. The work presents a feasible approach to develop HECs with ultra-high Tm.
AI-Generated Overview
-
Research Focus: The study investigates the prediction of high-entropy diborides (HEBs) with ultra-high melting points (Tm) using machine learning techniques in the context of developing high-entropy ceramics (HECs) suitable for extreme environments.
-
Methodology: A transferable moment tensor potential (MTP) was constructed for HEBs and used in molecular dynamics (MD) simulations to simulate Tm. A total of 24 descriptors were generated and optimized using genetic algorithms with different machine learning models to accurately predict the Tm of 32,563 HEBs.
-
Results: The predicted maximum Tm achieved was 3688 K in the HEB composition (Ti₀.₁Zr₀.₁Hf₀.₆Ta₀.₂)B₂, with a processed dataset for effectively screening potential HEBs with ultra-high Tm.
-
Key Contribution(s): The study introduces a robust and transferable MTP enabling the accurate prediction of the thermal properties of HEBs, facilitating the discovery of ultra-high Tm ceramics through a data-driven approach.
-
Significance: This work addresses the challenge of discovering HECs with ultra-high Tm amid significant compositional variety by employing advanced machine learning methodologies, thus laying groundwork for future material design.
-
Broader Applications: The methodology developed could be adapted for discovering various materials with desired properties, extending beyond high-entropy ceramics to other fields such as catalysis, battery materials, and structural components designed for extreme conditions.