Scholarlink

The success of safe, long cycle life, and high-capacity solid-state lithium-ion batteries (LIBs) depends on the use of appropriate solid-state electrolytes (SSEs). Among various SSEs, Li7La3Zr2O12 (LLZO) garnet-type SSE has been extensively studied due to its high ionic conductivity and stability. The type and stoichiometry of dopants greatly influence the ionic conductivity of LLZO. In this work, machine learning algorithms were employed to identify the optimal dopants and their stoichiometric range for achieving high ionic conductivity in LLZO. The results show that the Ga dopant with a concentration range of 0.05–0.40 is suitable for the Li-ion site, while Nb and Ta dopants with a concentration range of 0.20–0.62 and 0.20–0.70, respectively, are appropriate for the Zr-ion site in LLZO for achieving high ionic conductivity. This study contributes to the design and selection of dopants for LLZO, which is essential for the development of high-performance LIBs. The findings presented in this research are crucial for the optimization of LLZO garnet for use in high-performance SSBs. The data used in this study were obtained from a comprehensive review of the available literature on LLZO garnet. Machine learning algorithms such as LGBM and Random Forest were then employed to predict the optimal dopants and their stoichiometric range for achieving high ionic conductivity in LLZO. This research demonstrates the potential of machine learning in materials science research and highlights the importance of dopant selection in achieving high ionic conductivity in LLZO garnet. The findings presented in this study are valuable for the design and optimization of LLZO garnet for use in high-performance SSBs.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine-Learning-Guided Selection of Optimal Dopants for Solid-State Electrolyte in Lithium-Ion Batteries

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jayesh Sharma,
  • Kartik Kumar,
  • Ramdutt Arya,
  • Kapil Pareek

摘要

The success of safe, long cycle life, and high-capacity solid-state lithium-ion batteries (LIBs) depends on the use of appropriate solid-state electrolytes (SSEs). Among various SSEs, Li7La3Zr2O12 (LLZO) garnet-type SSE has been extensively studied due to its high ionic conductivity and stability. The type and stoichiometry of dopants greatly influence the ionic conductivity of LLZO. In this work, machine learning algorithms were employed to identify the optimal dopants and their stoichiometric range for achieving high ionic conductivity in LLZO. The results show that the Ga dopant with a concentration range of 0.05–0.40 is suitable for the Li-ion site, while Nb and Ta dopants with a concentration range of 0.20–0.62 and 0.20–0.70, respectively, are appropriate for the Zr-ion site in LLZO for achieving high ionic conductivity. This study contributes to the design and selection of dopants for LLZO, which is essential for the development of high-performance LIBs. The findings presented in this research are crucial for the optimization of LLZO garnet for use in high-performance SSBs. The data used in this study were obtained from a comprehensive review of the available literature on LLZO garnet. Machine learning algorithms such as LGBM and Random Forest were then employed to predict the optimal dopants and their stoichiometric range for achieving high ionic conductivity in LLZO. This research demonstrates the potential of machine learning in materials science research and highlights the importance of dopant selection in achieving high ionic conductivity in LLZO garnet. The findings presented in this study are valuable for the design and optimization of LLZO garnet for use in high-performance SSBs.