胡娜,张梅,殷俊

• 1:淮南师范学院应用技术学院
• 2:安徽理工大学电气与信息工程学院
• 3:国网安徽省电力有限公司广德市供电公司

摘要(Abstract)：

为解决锂离子电池特征工程建立困难导致SOH估计精度低的问题，提出一种锂电池SOH预测方法。先利用电池测试仪对NCM三元锂电池进行充放电实验，获取恒流、恒功率放电工况下的容量衰退数据集；针对充放电曲线信息重叠现象，将曲线划分为相似和特征片段，保留有效特征片段以保留样本特征并缩短样本长度；接着提出加权多尺度样本熵方法，以指数衰减函数为权重函数，对特征片段提取特征；最后将特征数据输入LightGBM模型进行SOH估计。实验验证结果显示，两组不同工况的电池R~2均高于0.99,RMSE均值为0.4043，表现优于GBDT、XGBoost模型。

关键词(KeyWords)： 锂离子电池;健康状态;特征片段;特征提取;加权多尺度样本熵;LightGBM

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目（52374154）

作者(Author): 胡娜,张梅,殷俊

DOI: 10.19356/j.cnki.1001-3997.20260402.013

参考文献(References)：

• [1]王若琦，王晓佳，杨淇，等.基于双自适应无迹卡尔曼滤波算法的锂电SOC/SOH联合估计[J].机械设计与制造，2023(1):1-4+8.(Wang Ruoqi,Wang Xiaojia,Yang Qi,et al.Joint estimation of lithium battery SOC/SOH based on double adaptive untracked kalman filtering algorithm[J].Machinery Design&Manufacture,2023(1):1-4+8.)
• [2]Yu X,Ma Z,Wen J.Joint estimation of SOH and RUL for lithium batteries based on variable frequency and model integration[J].International Journal of Electrochemical Science,2024(11):100842-100842.
• [3]Zhang Z,Liu X,Zhang R,et al. Lithium-ion battery SOH estimation method based on multi-feature and CNN-KAN[J].Frontiers in Energy Research,2024(12):1494473-1494473.
• [4]申江卫，折亦鑫，舒星，等.基于短时随机充电数据和优化卷积神经网络的锂电池健康状态估计[J].储能科学与技术，2025(4):1585-1594.(Shen Jiangwei,She Yixin,Shu Xing,et al.State of health estimation for lithium batteries based on short-term random charging data and optimized convolutional neural network[J].Energy Storage Science and Technology,2025(4):1585-1594.)
• [5]樊亚翔，肖飞，许杰，等.基于充电电压片段和核岭回归的锂离子电池SOH估计[J].中国电机工程学报，2021(16):5661-5670.(Fan Yaxiang,Xiao Fei,Xu Jie,et al.State of health estimation of lithiumion batteries based on the partial charging voltage segment and kernel ridge regression[J].Proceedings of the CSEE,2021(16):5661-5670.)
• [6]肖迁，穆云飞，焦志鹏，等.基于改进LightGBM的电动汽车电池剩余使用寿命在线预测[J].电工技术学报，2022(17):4517-4527.(Xiao Qian,Mu Yunfei,Jiao Zhipeng,et al.Improved LightGBM based remaining useful life prediction of lithium-ion battery under driving conditions[J].Transactions of China Electrotechnical Society,2022(17):4517-4527.)
• [7]史永胜，翟欣然，栾飞，等.基于特征选择的LightGBM算法预测钠离子电池剩余寿命[J].陕西科技大学学报，2024(2):174-181.(Shi Yongsheng,Zhai Xinran,Luan Fei,et al.Predicting remaining useful life of sodium-ion batteries using feature selection-based LightGBM algorithm[J]. Journal of Shaanxi University of Science&Technology,2024(2):174-181.)
• [8]伍毅平，杨傲然，陈家源，等.基于LightGBM的电动汽车动力电池故障双层诊断模型[J].北京工业大学学报，2025(2):183-191.(Wu Yiping,Yang Aoran,Chen Jiayuan,et al.Double-layer diagnosis model for electric vehicle powerbattery faults based on LightGBM[J]. Journal of Beijing University of Technology,2025(2):183-191.)
• [9]寇发荣，杨天祥，罗希，等.基于特征重构与多时间尺度的锂电池SOH和RUL联合估计[J].太阳能学报，2025(6):68-78.(Kou Farong,Yang Tianxiang,Luo Xi,et al.Joint estimation of SOH and RUL for lithium batteries based on feature reconstruction and multiple times scales[J].Acta Energiae Solaris Sinica,2025(6):68-78.)
• [10]王振亚，姚立纲.广义精细复合多尺度样本熵与流形学习相结合的滚动轴承故障诊断方法[J].中国机械工程，2020(20):2463-2471.(Wang Zhenya,Yao Ligang.Rolling bearing fault diagnosis method based on generalized refined composite multiscale sample entropy and manifoldlearning[J].ChinaMechanicalEngineering,2020(20):2463-2471.)
• [11]赵泉华，张杰，李玉.多尺度样本熵高光谱图像分类[J].测绘科学，2023(1):117-126.(Zhao Quanhua,Zhang Jie,Li Yu.Multi-scale sample entropy hyperspectral image classification[J]. Science of Surveying and Mapping,2023,48(1):117-126.)
• [12]Zhang M,Yin J,Feng T.Lithium battery SOH estimation based on manifold learning and LightGBM[J].Applied Sciences,2023(11):6540.
• [13]金建新，虞儒新，刘刚，等.锂离子电池健康状态估算方法研究进展[J].电气工程学报，2024(1):33-48.(Jin Jianxin,Yu Ruxin,Liu Gang,et al.Research progress on state-ofhealth estimating method for lithium-ion batteries[J].Joumal of Electrical Engineering,2024(1):33-48.)
• [14]孙丙香，任鹏博，陈育哲，等.锂离子电池在不同区间下的衰退影响因素分析及任意区间的老化趋势预测[J].电工技术学报，2021(3):666-674.(Sun Bingxiang,Ren Pengbo,Chen Yuzhe,et al.Analysis of influencing factors of degradation under different interval stress and prediction of aging trend in any interval for lithium-lon battery[J].Transactions of China Electrotechnical Society,2021(3):666-674.)
• [15]潘大为，师杰，杜宇航，等.基于BNN-PF的卫星锂离子电池多工况SOH估计[J].电子测量与仪器学报，2024(9):104-115.(Pan Dawei,Shi Jie,Du Yuhang,et al.BNN-PF-based SOH estimation of satellite lithium-ion batteries under different operating conditions[J].Journal of Electronic Measurement and Instrumentation,2024(9):104-115.)