基于非晶态结构筛选硫系相变存储材料的机器学习方法
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUAZHONG UNIV OF SCI & TECH
- Filing Date
- 2024-05-23
- Publication Date
- 2026-07-17
AI Technical Summary
Existing phase change memory (PCM) development solutions rely on manually defined screening criteria, resulting in poor screening efficiency, long cycles, and high costs. Furthermore, they primarily target crystalline phase change materials, limiting the comprehensive description of the structure and properties of PCM materials.
A machine learning approach based on amorphous structures is employed, using first-principles calculations, molecular dynamics simulations, and machine learning models to construct a dataset, optimize model parameters, and screen chalcogenide phase change storage materials. This process includes modeling, molecular dynamics simulations, feature data extraction, and machine learning model training.
It improves the accuracy and efficiency of phase change material screening, shortens the screening cycle of new materials, reduces costs, enables more accurate prediction of material properties and behavior, and improves the description method of phase change materials.
Smart Images
Figure CN118522374B_ABST