| Project/Area Number |
19K14902
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 19020:Thermal engineering-related
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
JU SHENGHONG 東京大学, 大学院工学系研究科(工学部), 客員研究員 (30809645)
|
|---|
| Project Period (FY) |
2019-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2021: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
|---|
| Keywords | マテリアルズ・インフォマティクス / 伝熱機能材料 / ベイズ最適化 / 機械学習 / モンテカルロ木探索 |
|---|
| Outline of Research at the Start |
This project aims to realize high-efficiency designing of materials with ultimate high/low thermal conductivity by combining traditional thermal simulation with novel informatics algorithm. Two directions will be conducted: (1) High throughput screening of high/low thermal conductivity crystals via hierarchical screening and transfer learning. (2) Nanostructure designing via Bayesian optimization and Monte Carlo tree search. The design methodology developed in this project is expected to improve the developing efficiency of thermal materials greatly and help to explore new physics behind.
|
| Outline of Final Research Achievements |
Designing functionalized materials with desired thermal property holds its critical importance in applications of heat exchanger, thermal interface materials, thermoelectrics, thermal barrier coating and insulators. In this project, materials informatics methods including high-throughput screening and Bayesian optimization have been developed to design thermal functional materials. The key of designing thermal functional materials via materials informatics is to build communications between materials’simulations/experiments and machine learning tools. By setting the objective function, descriptor selection, property calculator to evaluate the objective function, and an informatics optimization method, we have successfully explored the high thermal conductivity crystals, highly selective radiative cooling materials, thermoelectric films and magnetic tunnel junctions. Those results have shown great advantage of materials informatics to design thermal functional materials.
|
| Academic Significance and Societal Importance of the Research Achievements |
The target of this research is to develop high efficiency and novel materials informatics method for designing thermal functionalized materials. The developed method can be easily extended to other transport property designing, which is expected to contribute to both research and industry society.
|
