基于Box-Cox和Informer的锂离子电池寿命预测

Life prediction of lithium-ion batteries based on Box-Cox and Informer

针对锂离子电池不同老化过程中隐含的噪声序列和强非线性特点,提出一种基于Box-Cox数据处理和Informer模型进行锂电池剩余使用寿命预测的方法。对新威电池检测仪采取的电池数据进行分析,确定数据特征进而健康指标,利用Box-Cox对数据进行预处理剔除部分噪声信号,使数据线性化;利用Informer模型输出的全连接层代替解码器层,建立锂离子电池RUL预测模型,并通过两组不同工况电池数据验证所提方法的有效性和泛化性。结果表明:该方法能够克服数据测量噪声的影响,有效地预测锂离子电池的剩余使用寿命,泛化性良好且精度较高。

At present,lithium-ion batteries are widely used in various fields,so accurate prediction of the remaining service life of lithium-ion batteries is of great significance.This article proposes a method for predicting the remaining service life of lithium-ion batteries based on Box Cox data processing and Informer model,aiming at the hidden noise sequences and strong nonlinear characteristics during different aging processes of lithium-ion batteries.Firstly,analyze the battery data taken by the Xinwei battery tester,determine the data characteristics and health indicators,and use Box Cox to preprocess the data to eliminate some noise signals,so as to linearize the data;Finally,using the fully connected layer output from the Informer model to replace the decoder layer,a lithium ion battery RUL prediction model was established,and the effectiveness and generalization of the proposed method were verified through two sets of battery data under different operating conditions.The results show that this method can overcome the influence of data measurement noise,effectively predict the remaining service life of lithium-ion batteries,and has good generalization and high accuracy.