基于随机充电片段和DBFN-ML的锂电池健康状态估计

张钰; 赵志衡; 周海睿

doi:10.19799/j.cnki.2095-4239.2025.1021

您当前的位置：

首页 >

文章列表页 >

基于随机充电片段和DBFN-ML的锂电池健康状态估计

储能测试与评价 | 更新时间：2026-07-13

- 基于随机充电片段和DBFN-ML的锂电池健康状态估计
- Estimation of lithium-ion battery state of health based on random charging segments and DBFN-ML
- 储能科学与技术 2026年15卷第6期页码：2368-2379
- 作者机构：
  
  哈尔滨工业大学电气工程及自动化学院，黑龙江哈尔滨 150001
- 作者简介：
  
  张钰（2001—），男，硕士研究生，研究方向为锂电池状态估计与寿命预测，E-mail：1198708113@qq.com；
  赵志衡，教授，研究方向为锂电池管理系统智能算法，E-mail：zhzhhe@hit.edu.cn。
- 基金信息：
  
  2020年工业互联网创新发展工程项目(TC200H037)
- DOI：10.19799/j.cnki.2095-4239.2025.1021
  中图分类号： TM 912
- 收稿：2025-11-12，
  
  修回：2026-01-04，
  
  纸质出版：2026-06-28
- 稿件说明：
移动端阅览
张钰, 赵志衡, 周海睿. 基于随机充电片段和DBFN-ML的锂电池健康状态估计[J]. 储能科学与技术, 2026, 15(6): 2368-2379.

ZHANG Yu, ZHAO Zhiheng, ZHOU Hairui. Estimation of lithium-ion battery state of health based on random charging segments and DBFN-ML[J]. Energy Storage Science and Technology, 2026, 15(6): 2368-2379.
张钰, 赵志衡, 周海睿. 基于随机充电片段和DBFN-ML的锂电池健康状态估计[J]. 储能科学与技术, 2026, 15(6): 2368-2379. DOI： 10.19799/j.cnki.2095-4239.2025.1021.

ZHANG Yu, ZHAO Zhiheng, ZHOU Hairui. Estimation of lithium-ion battery state of health based on random charging segments and DBFN-ML[J]. Energy Storage Science and Technology, 2026, 15(6): 2368-2379. DOI： 10.19799/j.cnki.2095-4239.2025.1021.

摘要

准确估计锂电池健康状态（state of health，SOH）对保障储能系统的稳定运行至关重要。在实际应用场景中，电池充电过程通常呈现非完整与非固定特性，导致可获取的充电数据多为随机片段，使得传统SOH估计方法难以有效应对。针对该问题，本研究提出一种基于双分支融合网络（dual-branch fusion network，DBFN）与元学习（meta-learning，ML）的SOH估计方法。首先，将原始充电数据划分为多个电压区间片段，从中提取增量容量（incremental capacity，IC）平均值、充电容量及充电时间作为健康特征（health feature，HF），并将初始与结束电压作为片段位置信息特征。其次，构建DBFN模型，通过2个独立分支分别处理上述2类特征，以捕捉与电池退化相关的健康信息及片段上下文位置信息，并借助融合模块实现基于随机充电片段的SOH估计。进一步引入元学习，利用少量样本进行多电池任务学习，从而快速优化DBFN参数并增强模型泛化能力。最后，基于美国国家航空航天局（National Aeronautics and Space Administration，NASA）锂电池数据集进行实验验证，将本研究模型与其他模型进行对比。实验结果表明，所提方法在SOH估计方面表现优异，最优均方误差为0.00012，平均绝对误差为0.00892，平均绝对百分比误差为1.14%。

Abstract

Accurate estimation of the state of health (SOH) lithium batteries is crucial for ensuring the stable operation of energy-storage systems. In practical applications

the battery-charging process often exhibits incomplete and non-stationary characteristics

resulting in predominantly random segments of charging data. This poses significant challenges to traditional SOH-estimation methods. To address this issue

in this paper we propose an SOH-estimation method based on a dual-branch fusion network (DBFN) and meta learning (ML). First

we divide the raw charging data into multiple voltage-interval segments

and we extract from them the average incremental capacity

charging capacity

and charging time as health features. We utilize the initial and terminal voltages of each segment as positional-information features. Subsequently

we construct a DBFN model that includes two independent branches designed to process the aforementioned two types of features. This approach captures both the health-related information associated with battery degradation and the contextual positional information from the segments. We then employ a fusion module to estimate the SOH based on the random charging segments. Furthermore

we introduce ML to facilitate multi-battery task learning with limited samples

thereby rapidly optimizing the DBFN parameters and enhancing the capability for generalizing the model. Finally

we performed experimental validation using the NASA lithium-battery dataset and compared the proposed model with other benchmark models. Our results demonstrate that the proposed method excels in SOH estimation

achieving an optimal mean square error of 0.00012

a mean absolute error of 0.00892

and a mean absolute percentage error of 1.14%.

关键词

Keywords

references

朱振威, 苗嘉伟, 祝夏雨, 等. 基于机器学习方法的锂电池剩余寿命预测研究进展[J]. 储能科学与技术, 2024, 13(9): 3134-3149.

ZHU Z W, MIAO J W, ZHU X Y, et al. Research progress in lithium-ion battery remaining useful life prediction based on machine learning[J]. Energy Storage Science and Technology, 2024, 13(9): 3134-3149.

HE Y, BAI W Y, WANG L L, et al. SOH estimation for lithium-ion batteries: An improved GPR optimization method based on the developed feature extraction[J]. Journal of Energy Storage, 2024, 83: 110678. DOI:10.1016/j.est.2024.110678.

WANG Y J, XU R L, ZHOU C J, et al. Digital twin and cloud-side-end collaboration for intelligent battery management system[J]. Journal of Manufacturing Systems, 2022, 62: 124-134. DOI:10.1016/j.jmsy.2021.11.006.

SUI X, HE S, VILSEN S B, et al. A review of non-probabilistic machine learning-based state of health estimation techniques for Lithium-ion battery[J]. Applied Energy, 2021, 300(C): DOI: 10.1016/j.apenergy.2021.117346.

CHAE S G, BAE S J, OH K Y. State-of-health estimation and remaining useful life prediction of lithium-ion batteries using DnCNN-CNN[J]. Journal of Energy Storage, 2025, 106: 114826. DOI:10.1016/j.est.2024.114826.

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.

XIONG W, MO Y M, YAN C. Online state-of-health estimation for second-use lithium-ion batteries based on weighted least squares support vector machine[J]. IEEE Access, 2021, 9: 1870-1881. DOI:10.1109/ACCESS.2020.3026552.

XI R Y, PENG Y Y, LI J H, et al. Failure-mechanism-driven inverse design and optimization procedure for battery lifetime extension[J]. Angewandte Chemie (International Ed in English), 2025, 64(49): e202518502. DOI:10.1002/anie.202518502.

陈峥, 多功东, 申江卫, 等. 基于容量增量分析与VMD-GWO-KELM的锂电池健康状态估计[J]. 储能科学与技术, 2025, 14(6): 2476-2487.

CHEN Z, DUO G D, SHEN J W, et al. State of health estimation for lithium battery based on incremental capacity analysis and VMD-GWO-KELM[J]. Energy Storage Science and Technology, 2025, 14(6): 2476-2487.

GU X Y, SEE K W, LI P H, et al. A novel state-of-health estimation for the lithium-ion battery using a convolutional neural network and transformer model[J]. Energy, 2023, 262: 125501. DOI:10.1016/j.energy.2022.125501.

戴彦文, 于艾清. 基于健康特征参数的CNN-LSTM&GRU组合锂电池SOH估计[J]. 储能科学与技术, 2022, 11(5): 1641-1649. DOI:10.19799/j.cnki.2095-4239.2021.0623.

DAI Y W, YU A Q. Combined CNN-LSTM and GRU based health feature parameters for lithium-ion batteries SOH estimation[J]. Energy Storage Science and Technology, 2022, 11(5): 1641-1649. DOI:10.19799/j.cnki.2095-4239.2021.0623.

周頔, 宋显华, 卢文斌, 等. 基于日常片段充电数据的锂电池健康状态实时评估方法研究[J]. 中国电机工程学报, 2019, 39(1): 105-111. DOI:10.13334/j.0258-8013.pcsee.181026.

ZHOU D, SONG X H, LU W B, et al. Real-time SOH estimation algorithm for lithium-ion batteries based on daily segment charging data[J]. Proceedings of the CSEE, 2019, 39(1): 105-111. DOI:10.13334/j.0258-8013.pcsee.181026.

ZHU J G, WANG Y X, HUANG Y, et al. Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation[J]. Nature Communications, 2022, 13: 2261. DOI:10.1038/s41467-022-29837-w.

LU J H, XIONG R, TIAN J P, et al. Deep learning to estimate lithium-ion battery state of health without additional degradation experiments[J]. Nature Communications, 2023, 14: 2760. DOI:10.1038/s41467-023-38458-w.

ZHANG M, YANG D F, DU J X, et al. A review of SOH prediction of Li-ion batteries based on data-driven algorithms[J]. Energies, 2023, 16(7): 3167. DOI:10.3390/en16073167.

CHE Y H, HU X S, LIN X K, et al. Health prognostics for lithium-ion batteries: Mechanisms, methods, and prospects[J]. Energy & Environmental Science, 2023, 16(2): 338-371.

ZHANG C L, ZHAO S S, YANG Z, et al. A reliable data-driven state-of-health estimation model for lithium-ion batteries in electric vehicles[J]. Frontiers in Energy Research, 2022, 10: 1013800. DOI:10.3389/fenrg.2022.1013800.

李英顺, 阚宏达, 郭占男, 等. 基于数据预处理和VMD-LSTM-GPR的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(10): 3244-3258. DOI:10.19595/j.cnki.1000-6753.tces.230210.

LI Y S, KAN H D, GUO Z N, et al. Prediction of remaining useful life of lithium-ion battery based on data preprocessing and VMD-LSTM-GPR[J]. Transactions of China Electrotechnical Society, 2024, 39(10): 3244-3258. DOI:10.19595/j.cnki.1000-6753.tces.230210.

JIN H Y, CUI N M, CAI L, et al. State-of-health estimation for lithium-ion batteries with hierarchical feature construction and auto-configurable Gaussian process regression[J]. Energy, 2023, 262: 125503. DOI:10.1016/j.energy.2022.125503.

YANG Y L, CHEN S Y, CHEN T, et al. State of health assessment of lithium-ion batteries based on deep Gaussian process regression considering heterogeneous features[J]. Journal of Energy Storage, 2023, 61: 106797. DOI:10.1016/j.est.2023.106797.

GONG D L, GAO Y, KOU Y L, et al. State of health estimation for lithium-ion battery based on energy features[J]. Energy, 2022, 257: 124812. DOI:10.1016/j.energy.2022.124812.

JIANG Y Y, CHEN Y, YANG F F, et al. State of health estimation of lithium-ion battery with automatic feature extraction and self-attention learning mechanism[J]. Journal of Power Sources, 2023, 556: 232466. DOI:10.1016/j.jpowsour.2022.232466.

李超然, 肖飞, 樊亚翔, 等. 基于卷积神经网络的锂离子电池SOH估算[J]. 电工技术学报, 2020, 35(19): 4106-4119.

LI C R, XIAO F, FAN Y X, et al. An approach to lithium-ion battery SOH estimation based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020, 35(19): 4106-4119.

DENG Z W, HU X S, XIE Y, et al. Battery health evaluation using a short random segment of constant current charging[J]. iScience, 2022, 25(5): 104260. DOI:10.1016/j.isci.2022.104260.

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, 14(4): 1585-1595.

SHEN J W, SHE Y X, SHU X, 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, 14(4): 1585-1595.

江银锋, 宋文祥, 施语. 基于随机充放电片段和稀疏高斯过程回归的电池健康状态估计[J]. 电工技术学报, 2025, 40(19): 6359-6377. DOI:10.19595/j.cnki.1000-6753.tces.241763.

JIANG Y F, SONG W X, SHI Y. Battery state of health estimation using sparse Gaussian process regression based on random partial charge and discharge data[J]. Transactions of China Electrotechnical Society, 2025, 40(19): 6359-6377. DOI:10.19595/j.cnki.1000-6753.tces.241763.

TIAN Y, LIN C, MENG X F, et al. Accelerated commercial battery electrode-level degradation diagnosis via only 11-point charging segments[J ] . eScience, 2025, 5(1): 100325. DOI:10.1016/j.esci.2024.100325.

SAHA B, GOEBEL K. Battery data set[DB]. NASA AMES prognostics data repository, 2007.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于多参数耦合模型的锂电池健康管理策略在智能物流仓储中的应用

盐包水电解质浓度对固液界面影响规律

圆柱形锂离子电池在针刺条件下的安全性研究

模糊综合评价法的储能系统性能评估

2025年中国储能技术研究进展