基于变分模态分解与特征增强的锂电池健康状态估计方法

doi:10.19799/j.cnki.2095-4239.2025.0033

摘要/Abstract

摘要：

锂电池因其高能量密度、生命周期长等优点，已广泛应用于电动汽车、储能系统和便携设备等领域。然而，锂电池在使用过程中不可避免地会出现容量再生现象，这一现象会影响电池健康状态的评估精度。针对这一问题，本工作提出了一种结合变分模态分解和生成对抗网络的电池健康状态估计方法，以降低容量再生现象对电池健康状态评估精度的影响。首先，通过变分模态分解对锂电池在放电过程中反映容量再生现象的等压降放电时间特征量进行多尺度分解，并根据皮尔逊相关系数分析，分离出主退化趋势分量与局部波动分量，以更好地表征电池健康状态。主退化趋势分量反映了电池整体退化的趋势，而局部波动分量则反映了容量再生现象引起的局部变化特性。接着，为了进一步增强局部波动分量中与容量再生现象相关的特征，对其进行傅里叶变换，提取其中反映容量再生现象的中低频段分量。针对这些频段的分量，使用生成对抗网络进行数据生成，将生成的数据与变分模态分解后的多特征结合，构建新的多特征集；然后，采用支持向量机算法对新的多特征集进行训练，实现对锂电池健康状态的准确估计；最后，基于NASA数据集和CALCE数据集进行验证实验。实验结果表明，所提出的方法相比于传统方法，均方根误差均能控制在4.5%以内，能够有效降低容量再生现象对电池健康评估精度的影响。

关键词: 容量再生, 局部波动分量, 傅里叶变换, 支持向量机

Abstract:

Owing to their high energy density and long life cycle, lithium batteries have been widely used in electric vehicles, energy storage systems, and portable devices. However, capacity regeneration is an inevitable phenomenon during battery use, which influences the accuracy of battery health assessment. To reduce the influence of capacity regeneration on assessment accuracy, a new method combining variational mode decomposition and a generative adversarial network is proposed. First, variational mode decomposition is applied to decompose the iso-pressure-drop discharge-time characteristic, which reflects the capacity regeneration phenomenon during lithium battery discharge. The main degradation-trend component and local fluctuation component are then separated using Pearson correlation coefficient analysis, enabling a better characterization of battery health. The main degradation-trend component represents the overall degradation of the battery, while the local fluctuation component captures the variations caused by capacity regeneration. Second, to further enhance the features related to local wave components and the capacity regeneration phenomenon, a Fourier transform is used to extract the mid- and low-frequency components that reflect capacity regeneration. For components in these frequency bands, a generative adversarial network is employed to generate additional data. These generated data are then combined with the multifeature set obtained from variational mode decomposition to form a new, enriched multifeature set. Next, a support vector machine algorithm is used to train this new multifeature set to achieve accurate estimation of the battery's state of health. Finally, validation experiments are conducted using NASA and CALCE datasets. The experimental results show that, compared with traditional methods, the proposed method keeps the root-mean-square error within 4.5%, effectively reducing the influence of capacity regeneration on battery health assessment accuracy.

Key words: capacity regeneration, local fluctuation component, Fourier transform, support vector machine

中图分类号:

TM 912

张吴哲, 蔡志端, 吴成傲, 郑炜, 童嘉阳. 基于变分模态分解与特征增强的锂电池健康状态估计方法[J]. 储能科学与技术, 2025, 14(9): 3599-3610.

Wuzhe ZHANG, Zhiduan CAI, Chengao WU, Wei ZHENG, Jiayang TONG. State-of-health assessment of lithium batteries using variational mode decomposition and feature enhancement under capacity regeneration phenomena[J]. Energy Storage Science and Technology, 2025, 14(9): 3599-3610.

图/表 18

图1

图2

表1

图3

图4

图5

图6

图7

图8

图9

表2

表3

图10

表4

图11

图12

图13

表5

参考文献 22

[1]	ROMAN D, SAXENA S, ROBU V, et al. Machine learning pipeline for battery state-of-health estimation[J]. Nature Machine Intelligence, 2021, 3(5): 447-456. DOI: 10.1038/s42256-021-00312-3.
[2]	胡晓亚, 郭永芳, 张若可. 锂离子电池健康状态估计方法研究综述[J]. 电源学报, 2022, 20(1): 126-133. DOI: 10.13234/j.issn.2095-2805.2022.1.126.
	HU X Y, GUO Y F, ZHANG R K. Review of state-of-health estimation methods for lithium-ion battery[J]. Journal of Power Supply, 2022, 20(1): 126-133. DOI: 10.13234/j.issn.2095-2805. 2022.1.126.
[3]	王琛, 闵永军. 基于容量增量曲线与GWO-GPR的锂离子电池SOH估计[J]. 储能科学与技术, 2023, 12(11): 3508-3518. DOI: 10.19 799/j.cnki.2095-4239.2023.0458.
	WANG C, MIN Y J. SOH estimation of lithium-ion batteries based on capacity increment curve and GWO-GPR[J]. Energy Storage Science and Technology, 2023, 12(11): 3508-3518. DOI: 10.197 99/j.cnki.2095-4239.2023.0458.
[4]	LI J, ADEWUYI K, LOTFI N, et al. A single particle model with chemical/mechanical degradation physics for lithium ion battery State of Health (SOH) estimation[J]. Applied Energy, 2018, 212: 1178-1190. DOI: 10.1016/j.apenergy.2018.01.011.
[5]	YANG J F, CAI Y F, PAN C F, et al. A novel resistor-inductor network-based equivalent circuit model of lithium-ion batteries under constant-voltage charging condition[J]. Applied Energy, 2019, 254: 113726. DOI: 10.1016/j.apenergy.2019.113726.
[6]	BEZHA M, BEZHA K, NAGAOKA N. A Practical SoH Estimation using Adaptive ANN algorithm for the embedded EIS diagnosis in Industrial Applications[C]//2022 IEEE International Conference on Consumer Electronics, July 6-8, 2022, Taipei, China. IEEE, 2022: 571-572. DOI: 10.1109/ICCE-55306.2022.9869073.
[7]	韦荣阳, 毛阗, 高晗, 等. 基于TWP-SVR的锂离子电池健康状态估计[J]. 储能科学与技术, 2022, 11(8): 2585-2599. DOI: 10.19799/j.cnki.2095-4239.2022.0184.
	WEI R Y, MAO T, GAO H, et al. Health state estimation of lithium ion battery based on TWP-SVR[J]. Energy Storage Science and Technology, 2022, 11(8): 2585-2599. DOI: 10.19799/j.cnki.2095-4239.2022.0184.
[8]	LYU Z Q, WANG G, GAO R J. Synchronous state of health estimation and remaining useful lifetime prediction of Li-ion battery through optimized relevance vector machine framework[J]. Energy, 2022, 251: 123852. DOI: 10.1016/j.energy.2022.123852.
[9]	SPOTNITZ R. Simulation of capacity fade in lithium-ion batteries[J]. Journal of Power Sources, 2003, 113(1): 72-80. DOI: 10.1016/S0378-7753(02)00490-1.
[10]	ZHAO L, WANG Y P, CHENG J H. A hybrid method for remaining useful life estimation of lithium-ion battery with regeneration phenomena[J]. Applied Sciences, 2019, 9(9): 1890. DOI: 10.3390/app9091890.
[11]	YUAN Z F, TIAN T, HAO F C, et al. A hybrid neural network based on variational mode decomposition denoising for predicting state-of-health of lithium-ion batteries[J]. Journal of Power Sources, 2024, 609: 234697. DOI: 10.1016/j.jpowsour. 2024.234697.
[12]	GAO K P, HUANG Z Y, LYU C T, et al. Multi-scale prediction of remaining useful life of lithium-ion batteries based on variational mode decomposition and integrated machine learning[J]. Journal of Energy Storage, 2024, 99: 113372. DOI: 10.1016/j.est.2024. 113372.
[13]	ZHU M Y, OUYANG Q, WAN Y, et al. Remaining useful life prediction of lithium-ion batteries: A hybrid approach of grey-Markov chain model and improved Gaussian process[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2021, 11(1): 143-153. DOI: 10.1109/JESTPE.2021.3098378.
[14]	WEI M, YE M, ZHANG C W, et al. A multi-scale learning approach for remaining useful life prediction of lithium-ion batteries based on variational mode decomposition and Monte Carlo sampling[J]. Energy, 2023, 283: 129086. DOI: 10.1016/j.energy.2023.129086.
[15]	胡天中, 余建波. 基于多尺度分解和深度学习的锂电池寿命预测[J]. 浙江大学学报(工学版), 2019, 53(10): 1852-1864. DOI: 10.3785/j.issn.1008-973X.2019.10.002.
	HU T Z, YU J B. Life prediction of lithium-ion batteries based on multiscale decomposition and deep learning[J]. Journal of Zhejiang University (Engineering Science), 2019, 53(10): 1852-1864. DOI: 10.3785/j.issn.1008-973X.2019.10.002.
[16]	PAN H H, LÜ Z Q, WANG H M, et al. Novel battery state-of-health online estimation method using multiple health indicators and an extreme learning machine[J]. Energy, 2018, 160: 466-477. DOI: 10.1016/j.energy.2018.06.220.
[17]	谢旭, 蒲娴怡, 毕贵红, 等. 基于二层分解技术的锂离子电池容量评估方法[J]. 电源技术, 2022, 46(6): 647-651.
	XIE X, PU X Y, BI G H, et al. Capacity estimation method of lithium-ion batteries based on two-layer decomposition technique[J]. Chinese Journal of Power Sources, 2022, 46(6): 647-651.
[18]	LIN C P, XU J, SHI M J, et al. Constant current charging time based fast state-of-health estimation for lithium-ion batteries[J]. Energy, 2022, 247: 123556. DOI: 10.1016/j.energy.2022.123556.
[19]	李嘉波, 王志璇, 田迪, 等. 变模态分解下SSA-LSTM组合的锂离子电池剩余使用寿命预测方法[J].储能科学与技术, 2025, 14 (2): 659-670. DOI: 10.19799/j.cnki.2095-4239.2024.0732.
	LI J B, WANG Z X, TIAN D, et al. The remaining service life prediction method of lithium-ion batteries with SSA-LSTM combination under variable mode decomposition[J]. Energy Storage Science and Technology, 2025, 14 (2): 659-670. DOI: 10.19799/j.cnki.2095-4239.2024.0732.
[20]	孙中麟, 李嘉波, 田迪, 等. 基于COA-LSTM和VMD的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2024, 13(9): 3254-3265. DOI: 10.19799/j.cnki.2095-4239.2024.0157.
	SUN Z L, LI J B, TIAN D, et al. Useful life prediction for lithium-ion batteries based on COA-LSTM and VMD[J]. Energy Storage Science and Technology, 2024, 13(9): 3254-3265. DOI: 10.19799/j.cnki.2095-4239.2024.0157.
[21]	张岸, 杨春德. 基于GAN-CNN-LSTM的锂电池SOH估计[J]. 电源技术, 2021, 45(7): 902-906. DOI: 10.3969/j.issn.1002-087X.2021.07.019.
	ZHANG A, YANG C D. SOH estimation of lithium batteries based on GAN-CNN-LSTM[J]. Chinese Journal of Power Sources, 2021, 45(7): 902-906. DOI: 10.3969/j.issn.1002-087X.2021.07.019.
[22]	朱冰, 夏天. 多元宇宙优化估算锂离子电池的SOC与SOH[J]. 电池, 2024, 54(5): 688-692.DOI:10.19535/j.1001-1579.2024.05.017.
	ZHU B, XIA T. Estimation of SOC and SOH for Li-ion battery by multi-verse optimization[J]. Dianchi(Battery Bimonthly), 2024, 54(5): 688-692. DOI:10.19535/j.1001-1579.2024.05.017.