基于小波降噪-支持矢量机的锂离子电池剩余使用寿命预测模型  

The remaining life prediction model of lithium battery based on wavelet noise reduction and support vector machine

作　　者：曲杰[1] 赵小涵 甘伟 Qu Jie;Zhao Xiaohan;Gan Wei(School of Mechanical and Automotive Engineering,South China University of Technology,Guangdong Guangzhou,510641,China)

机构地区：[1]华南理工大学机械与汽车工程学院

出　　处：《机械设计与制造工程》2020年第1期81-84,共4页Machine Design and Manufacturing Engineering

基　　金：国家重点研发计划项目(2018YFB0104100)

摘　　要：针对锂电池充放电数据中夹杂噪声从而影响剩余使用寿命预测的问题,首先基于多分辨率的小波降噪方法,提出了锂电池充放电曲线降噪方法。然后采用支持矢量机回归方法建立了基于降噪数据的支持矢量机预测模型。最后用实验的方法采集锂电池容量保持率-充放电次数数据,对数据进行降噪并应用支持矢量机回归方法对其进行了寿命预测。结果显示基于降噪数据建立的支持矢量机回归模型预测性能优于基于原始数据建立的支持矢量机回归模型的预测性能,该方法预测结果与实际实验数据相对偏差在2.1%以内。Aiming at the noise in the charge and discharge data of lithium battery which affects the prediction of the remaining life,it presents a noise reduction method for lithium battery charge and discharge curve based on the multi-resolution wavelet noise reduction method.It uses the support vector machine regression method to establish a support vector machine prediction model based on noise reduction data.It applies the support vector machine regression to deal with experiments data such as the lithium battery capacity retention rate-charge and discharge times data,denoise data.and predicts the lithium battery life.The results show that the prediction performance of the support vector machine regression model based on the noise reduction data is better than the prediction performance of the support vector machine regression model based on the original data.The prediction result of this method is within 2.1%of the actual experimental data.

关 键 词：剩余使用寿命预测 小波降噪 支持矢量机 锂电池 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]