摘要
锂电池组的健康状态(SOH:State of Health)是电池寿命预测中最重要的参数。由于电池组内部单体电池的相互影响,使电池组SOH难以准确预测。因此,采取了一种基于门控循环单元(GRU:Gated Recurrent Unit)的锂电池组SOH的预测模型,在不同连接结构下,使用充电周期序列、电池容量序列和电池温度序列单体电池和电池组指标预测电池组的健康状态。研究结果表明,在串联和并联连接方式下,使用单体电池指标的预测曲线可以更好地体现电池的退化过程,预测结果优于使用电池组指标的预测曲线,具有较低的预测误差。
The most important parameter in the life prediction of lithium battery is SOH(State Of Health). Due to the interaction between individual cells in the battery pack, it is difficult to accurately predict the SOH of battery pack. Therefore, we propose a prediction model for SOH of lithium battery pack based on GRU(Gating Recurrent Unit). Under different connection structures, charge cycle series, battery capacity series and battery temperature series are used to predict the health status of battery pack. The results show that in series and parallel connection mode, the prediction curves of single battery index show better degradation process of batteries, the prediction result is better than that of battery pack index and has lower pridiction error.
作者
曹广华
赵中林
许昀昊
CAO Guanghua;ZHAO Zhonglin;XU Yunhao(College of Electrical Engineering and Information,Northeast Petroleum University,Daqing 163318,China)
出处
《吉林大学学报（信息科学版）》
CAS
2022年第2期181-187,共7页
Journal of Jilin University（Information Science Edition）
关键词
健康状态
门控循环单元
电池容量
电池温度
state of health
gated recurrent unit
battery capacity
battery temperature
