Predicting battery life with early cyclic data by machine learning

Predicting battery life with early cyclic data by machine learning
复制标题

通过机器学习利用早期循环数据预测电池寿命

DOI:
10.1002/est2.98
复制
发表时间:
2019-11
期刊:
影响因子:
3.2
通讯作者:
Junwei Sha
Junwei Sha
中科院分区:
--
文献类型:
--
作者:
Shan Zhu;Naiqin Zhao;Junwei Sha

文献摘要

参考文献

相似文献

这项工作应用机器学习工具来实现对商业电池寿命的早期预测。比较了不同机器学习算法对电池数据库的预测精度。在各种算法中,决策树(DT)方法预测电池在550次 循环后是否能保持80%以上的初始容量的准确率最高,为95.2%。利用最初的两个周期的数据,DT提出放电容量的变化是估计电池寿命类型的主要特征。给定前100次 循环后,权重最大的系数会转化为用于估计电池寿命的内阻。
This work applies machine learning tools to achieve the early prediction of commercial battery life. We compared the prediction accuracy of different machine learning algorithms to the battery database. Among various algorithms, the decision tree (DT) method exhibits the highest accuracy of 95.2% to predict whether the battery can maintain above 80% initial capacity after 550 cycles. Using the initial two cycles of data, DT proposes that the change of discharge capacity is the main feature to estimate the lifetime type of batteries. Given the first 100 cycles, the factor with the maximum weight turns to the internal resistance for estimating the battery lifetime.
DOI: 10.13700/j.bh.1001-5965.2018.0181
发表时间: 2018-09
期刊: Journal of Beijing University of Aeronautics and Astronautics
影响因子: --
作者:
Wang Chunlei;Zhao Qi;Qin Xiaoli;Feng Wenquan
通讯作者: Wang Chunlei;Zhao Qi;Qin Xiaoli;Feng Wenquan
DOI: 10.1016/j.est.2019.100819
发表时间: 2019-10
影响因子: 9.4
作者:
M. Varini;P. Campana;G. Lindbergh
通讯作者: M. Varini;P. Campana;G. Lindbergh
DOI: 10.1016/s0378-7753(01)00783-2
发表时间: 2001-10-15
影响因子: 9.2
作者:
Bloom, I;Cole, BW;Case, HL
通讯作者: Case, HL
DOI: 10.1038/nature17439
发表时间: 2016-05-05
期刊: NATURE
影响因子: 64.8
作者:
Raccuglia, Paul;Elbert, Katherine C.;Norquist, Alexander J.
通讯作者: Norquist, Alexander J.
DOI: 10.1149/2.044302jes
发表时间: 2013-01-01
影响因子: 3.9
作者:
Pinson, Matthew B.;Bazant, Martin Z.
通讯作者: Bazant, Martin Z.