锂离子电池SEI多尺度建模研究展望  

Multiscale modeling of the SEI of lithium-ion batteries

作　　者：张慧敏 王京 王一博 郑家新 邱景义[1] 曹高萍[1] 张浩[1] ZHANG Huimin;WANG Jing;WANG Yibo;ZHENG Jiaxin;QIU Jingyi;CAO Gaoping;ZHANG Hao(Beijing Key Lab of Advanced Chemical Energy Storage and Materials,Research Institute of Chemical Defense,Beijing 100191,China;296734 Units of PLA,Yueyang 414000,Hunan,China;School of Advanced Materials,Peking University Shenzhen Graduate School,Shenzhen 518055,Guangdong,China)

机构地区：[1]防化研究院,先进化学蓄电技术与材料北京市重点实验室,北京100191 [2]96734部队,湖南岳阳414000 [3]北京大学深圳研究生院新材料学院,广东深圳518055

出　　处：《储能科学与技术》2023年第2期366-382,共17页Energy Storage Science and Technology

基　　金：国家自然科学基金(51903177,21871036,52073274)。

摘　　要：锂离子电池高还原性负极表面的固体电解质界面膜(SEI)是影响电池电化学性能与稳定性的关键组分,但SEI的形成涉及多尺度、多物理场下的复杂过程,且组分异常复杂。在电池外壳“黑箱”环境下,现有的非原位技术对其表征无能为力,而原位技术又难以得到较高真实度的结果,难以深入理解SEI的相关机制。采用数学的方法对SEI进行建模研究,有望将复杂的物理场进行解耦,进而精准描述SEI的形成和演化的机制与过程,是近年来电池领域的研究热点。本文按对象尺度由小到大从原子到介观尺度逐渐增大的顺序分别总结了第一性原理分子动力学、反应力场分子动力学、经典分子动力学、蒙特卡罗算法、宏观性质建模在SEI建模研究中的应用进展,介绍其在指导电极材料开发及电解液改性方面的成功案例,着重讨论分析了多尺度建模研究SEI的难点与不足。并提出针对SEI的电化学势场特性建立力场算法平台,采用动力学蒙特卡罗方法和机器学习辅助将模型拓展到数万直至数亿原子,并通过逐级计算结合试验验证及专家评估促使收敛,获得具有量子力学精度且带电化学势场的SEI模型,有望实现SEI的长时域建模。The solid-electrolyte interface(SEI)on the highly reductive negative electrode surface of lithium-ion batteries is a key component affecting the electrical performance and stability;however,the formation of SEI involves complex processes in multiscale and multiphysical fields with extremely complex components.In the"black box"environment of a battery shell,the existing technology cannot characterize SEI,and in situ technology is difficult to obtain highly precise results.Using mathematical methods to model SEI is expected to decouple the complex physical fields and accurately describe the mechanisms and processes of SEI formation and evolution,which is a research hotspot in the field of battery.In this study,first,we describe the main methods and progress of SEI modeling from the atomic scale to mesoscale,including first-principles classical molecular dynamics,reactive molecular dynamics,classical molecular dynamics,Monte Carlo simulations,and macroscopic models.We also summarize some modeling applications in guiding electrode material synthesis and electrolyte modification,focusing on the difficulties and shortcomings of multiscale modeling.Next,we propose a force field algorithm platform based on the electrochemical potential field characteristics of SEI,expanding the modeling to tens of thousands or even hundreds of millions of atoms using the kinetic Monte Carlo simulations and machine learning assistance.Then,calculations are performed step by step,combining experimental verification and expert evaluation to promote convergence.Finally,we obtain an SEI model with quantum mechanical accuracy and electrochemical potential field,which is expected to realize SEI modeling at various lengths and timescales.

关 键 词：锂离子电池 多尺度模拟 分子动力学模拟 反应力场 固体电解质界面膜 

分 类 号：O646[理学—物理化学]