基于电化学阻抗谱的锂离子电池健康状态预测
State of health prediction of lithium-ion battery based on electrochemical impedance spectroscopy
在本文中，使用电化学阻抗谱（EIS）作为健康状态（SOH）预测的特征。EIS包含丰富的信息，如材料性质和电化学反应，直接反映锂离子电池的老化状态。从电化学的角度提出了一种新的特征提取方法，然后将基于Transformer的神经网络应用于SOH预测。通过特征提取，预测结果的平均绝对百分比误差在整个生命周期中降低到1.632%，与特征提取之前的原始数据相比降低了70%。
In this paper, electrochemical impedance spectroscopy (EIS) is used as the feature for the state of health (SOH) prediction. EIS contains rich information such as material properties and electrochemical reactions, which directly reflects the aging state of LIBs. A new feature extraction method is proposed from the perspective of electrochemistry, and then apply the Transformer-based neural network for SOH prediction. Through feature extraction, the mean absolute percentage error of the prediction is reduced to 1.632% in the whole life cycle, which is decreased by 70% compared to the original data before feature extraction.
施志聪、罗锴
电工基础理论电气测量技术、电气测量仪器计算技术、计算机技术
锂离子电池健康状态电化学阻抗谱ransformer神经网络数据驱动
lithium-ion batterystate of healthelectrochemical impedance spectroscopyTransformer neural networkdata-driven
施志聪,罗锴.基于电化学阻抗谱的锂离子电池健康状态预测[EB/OL].(2023-01-16)[2025-08-02].http://www.paper.edu.cn/releasepaper/content/202301-44.点此复制
评论