Synthesis of Lithium-ion Conducting Polymers Designed by Machine Learning-based Prediction and Screening

被引：39

作者：

Hatakeyama-Sato, Kan ^{[1
,2
]}

Tezuka, Toshiki ^{[1
,2
]}

Nishikitani, Yoshinori ^{[1
,2
]}

Nishide, Hiroyuki ^{[1
,2
]}

Oyaizu, Kenichi ^{[1
,2
]}

机构：

[1] Waseda Univ, Dept Appl Chem, Tokyo 1698555, Japan

[2] Waseda Univ, Res Inst Sci & Engn, Tokyo 1698555, Japan

来源：

CHEMISTRY LETTERS | 2019年 / 48卷 / 02期

关键词：

Solid polymer electrolyte; Lithium-ion battery; Machine learning; ELECTROLYTE;

D O I：

10.1246/cl.180847

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

A database for 240 types of lithium-ion conducting solid polymer electrolytes was newly constructed and analyzed by machine learning. Despite the complexity of the polymer composites as electrolytes, accurate prediction was achieved by the appropriate learning model. Inspired by the analyses, poly(glycidyl ether) derivatives were synthesized to yield higher conductivity. Screening of single-ion conducting polymers with de novo design (>15000 candidates) was also conducted based on the established database.

引用

页码：130 / 132

页数：3