首页|机器学习加速固态电解质的筛选

机器学习加速固态电解质的筛选

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
电动汽车和电化学储能领域的快速发展使得固态电池技术备受研究和关注.固态电解质作为下一代电池技术的关键组成部分,以其高安全性、高能量密度和长寿命而备受青睐.然而,寻找高性能固态电解质是固态电池应用的首要挑战.本文以无机固态电解质为重点,强调理想的固态电解质必须具有低电子电导率、良好的热稳定性以及结构和相稳定性.传统的实验和理论计算方法效率低下,因此机器学习方法成为通过分析大量无机结构特性和特征来智能预测材料性能的新途径.通过基于梯度下降的XGBoost算法,本文成功预测了材料的能带结构和稳定性,并从6000多种结构中仅筛选出194种理想的固态电解质结构,同时满足了低电子电导率和稳定性的要求,大大加速了固态电池的发展.
Machine Learning Approach Accelerates Search for Solid State Electrolytes
In the current aera of rapid de-velopment in the field of elec-tric vehicles and electrochemi-cal energy storage,solid-state battery technology is attracting much research and attention.Solid-state electrolytes,as the key component of next-genera-tion battery technology,are fa-vored for their high safety,high energy density,and long life.However,finding high-perfor-mance solid-state electrolytes is the primary challenge for solid-state battery applications.Focusing on inorganic solid-state electrolytes,this work highlights the need for ideal solid-state electrolytes to have low elec-tronic conductivity,good thermal stability,and structural and phase stability.Traditional experimental and theoretical computational methods suffer from inefficiency,thus machine learning methods become a novel path to intelligently predict material properties by analyz-ing a large number of inorganic structural properties and characteristics.Through the gradi-ent descent-based XGBoost algorithm,we successfully predicted the energy band structure and stability of the materials,and screened out only 194 ideal solid-state electrolyte struc-tures from more than 6000 structures that satisfy the requirements of low electronic conduc-tivity and stability simultaneously,which greatly accelerated the development of solid-state batteries.

Solid-state batterySolid-state electrolyteXGBoost algorithmLow electronic conductivityThermal stability

汤乐、张国桢、江俊

展开 >

中国科学技术大学化学物理系,合肥 230026

中国科学技术大学合肥微尺度物理科学国家研究中心,合肥 230026

固态电池 固态电解质 XGBoost算法 低电子电导率 热稳定性

National Natural science Foundation of ChinaNational Natural science Foundation of ChinaNational Natural science Foundation of ChinaNational Natural science Foundation of ChinaNational Natural science Foundation of ChinaNational Natural science Foundation of ChinaNational Natural science Foundation of ChinaChinese Academy of SciencesAnhui Initiative in Quantum Information TechnologiesUSTC-NSRL Joint FundsAnhui Provincial Natural Science Foundation

21421063214731662157321121633007217903502180306791950207QYZDB-SSW-SLH018AHY090200UN2018LHJJ2108085QB63

2024

10.1063/1674-0068/cjcp2402020

化学物理学报(英文版)
中国物理学会

化学物理学报(英文版)

CSTPCDEI
影响因子：0.162
ISSN：1674-0068
年,卷(期)：2024.37(4)