当前位置:科学网首页 > 小柯机器人 >详情
利用可解释混合机器学习阐明锂-硫电池的降解化学
作者:小柯机器人 发布时间:2022/10/15 9:43:12

华东理工大学彭翃杰研究团队报道了利用可解释混合机器学习阐明锂-硫电池的降解化学。相关研究成果于2022年10月10日发表于国际一流学术期刊《德国应用化学》。

新兴可充电电池的发展往往受到化学认识的限制,这些认识是由在巨大空间中纠缠在一起的图案组成。

该文中,研究人员提出了一个可解释的混合机器学习框架,以解决转换型电池难以解决的降解化学问题。该框架不是一个黑匣子,它不仅证明了准确预测锂硫电池的能力(寿命终止预测的测试平均绝对误差为8.9%),而且还产生了有用的物理理解,阐明了未来电池的设计和优化。该框架还发现了一个未知的性能指标,即首次放电时电解质比与高压区容量的比值,用于符合实际优点的锂硫电池。由于模块和输入的多功能性和灵活性,目前的数据驱动方法很容易适用于其他储能系统。

附:英文原文

Title: Untangling Degradation Chemistries of Lithium–Sulfur Batteries Through Interpretable Hybrid Machine Learning

Author: Xinyan Liu, Hong-Jie Peng, Bo-Quan Li, Xiang Chen, Zheng Li, Jia-Qi Huang, Qiang Zhang

Issue&Volume: 2022-10-10

Abstract: The development of emerging rechargeable batteries is often hindered by limited chemical understanding composing of entangled patterns in an enormous space. Herein, we propose an interpretable hybrid machine learning framework to untangle intractable degradation chemistries of conversion-type batteries. Rather than being a black box, this framework not only demonstrates an ability to accurately forecast lithium–sulfur batteries (with a test mean absolute error of 8.9% for the end-of-life prediction) but also generate useful physical understandings that illuminate future battery design and optimization. The framework also enables the discovery of an unknown performance indicator, the ratio of electrolyte ratio to high-voltage-region capacity at the first discharge, for lithium–sulfur batteries complying practical merits. The present data-driven approach is readily applicable to other energy storage systems due to its versatility and flexibility in modules and inputs.

DOI: 10.1002/anie.202214037

Source: https://onlinelibrary.wiley.com/doi/10.1002/anie.202214037

期刊信息

Angewandte Chemie:《德国应用化学》,创刊于1887年。隶属于德国化学会,最新IF:12.959
官方网址:https://onlinelibrary.wiley.com/journal/15213773
投稿链接:https://www.editorialmanager.com/anie/default.aspx