全球能源互联网（英文）2023，Vol.6Issue(2)：228-237,10.DOI:10.1016/j.gloei.2023.04.009
基于充电特征与改进原子搜索算法优化反向传播神经网络的健康状态估计方法
Estimation of state of health based on charging characteristics and back-propagation neural networks with improved atom search optimization algorithm
摘要
Abstract
With the rapid development of new energy technologies,lithium batteries are widely used in the field of energy storage systems and electric vehicles.The accurate prediction for the state of health(SOH)has an important role in maintaining a safe and stable operation of lithium-ion batteries.To address the problems of uncertain battery discharge conditions and low SOH estimation accuracy in practical applications,this paper proposes a SOH estimation method based on constant-current battery charging section characteristics with a back-propagation neural network with an improved atom search optimization algorithm.A temperature characteristic,equal-time temperature variation(Dt_DT),is proposed by analyzing the temperature data of the battery charging section with the incremental capacity(IC)characteristics obtained from an IC analysis as an input to the data-driven prediction model.Testing and analysis of the proposed prediction model are carried out using publicly available datasets.Experimental results show that the maximum error of SOH estimation results for the proposed method in this paper is below 1.5％.关键词
电池健康状态/锂离子电池/等时间的温度变化量/改进的原子搜索优化算法Key words
State of health/Lithium-ion battery/Dt_DT/Improved atom search optimization algorithm引用本文复制引用
张宇,张宇航,吴铁洲..基于充电特征与改进原子搜索算法优化反向传播神经网络的健康状态估计方法[J].全球能源互联网（英文）,2023,6(2):228-237,10.基金项目
This study was supported by National Natural Science Foundation of China (Grant No. 51677058). （Grant No. 51677058）
