一种基于不一致性特征融合的电池组健康状态估计方法

齐洪峰; 吴祖正; 张珺玮; 任坤华; 张言茹

doi:10.19799/j.cnki.2095-4239.2026.0281

您当前的位置：

首页 >

文章列表页 >

一种基于不一致性特征融合的电池组健康状态估计方法

储能测试与评价 | 更新时间：2026-08-26

- 一种基于不一致性特征融合的电池组健康状态估计方法
- A state of health estimation method for battery packs based on cell inconsistency feature fusion
- 储能科学与技术 2026年15卷第8期页码：3280-3293
- 作者机构：
  
  1.中车工业研究院有限公司，北京 100160
  2.北京交通大学，北京 100044
  3.中移能源科技（北京）有限公司，北京 100044
- 作者简介：
  
  齐洪峰（1973—），男，硕士，正高级工程师，研究方向为轨道交通装备产品平台技术，E-mail：qihongfeng@crrcgc.cc；
  张言茹，博士，实验师，研究方向为动力电池技术，E-mail：yr_zhang@bjtu.edu.cn。
- 基金信息：
- DOI：10.19799/j.cnki.2095-4239.2026.0281
  中图分类号： TM 911
- 收稿：2026-04-02，
  
  修回：2026-05-28，
  
  网络首发：2026-08-26，
  
  纸质出版：2026-08-28
- 稿件说明：
移动端阅览
齐洪峰, 吴祖正, 张珺玮, 等. 一种基于不一致性特征融合的电池组健康状态估计方法[J]. 储能科学与技术, 2026, 15(8): 3280-3293.

QI Hongfeng, WU Zuzheng, ZHANG Junwei, et al. A state of health estimation method for battery packs based on cell inconsistency feature fusion[J]. Energy Storage Science and Technology, 2026, 15(8): 3280-3293.
齐洪峰, 吴祖正, 张珺玮, 等. 一种基于不一致性特征融合的电池组健康状态估计方法[J]. 储能科学与技术, 2026, 15(8): 3280-3293. DOI： 10.19799/j.cnki.2095-4239.2026.0281.

QI Hongfeng, WU Zuzheng, ZHANG Junwei, et al. A state of health estimation method for battery packs based on cell inconsistency feature fusion[J]. Energy Storage Science and Technology, 2026, 15(8): 3280-3293. DOI： 10.19799/j.cnki.2095-4239.2026.0281.

摘要

锂离子电池组健康状态（state of health，SOH）的准确估计对于保障电池安全可靠运行至关重要，本研究提出一种考虑复杂不一致性影响的电池组健康状态估计方法。该方法从电池原始充电时序数据与容量增量曲线中挖掘反映电池组单体不一致性演变规律的表征信息，结合相关性分析完成冗余特征剔除，筛选出核心不一致性特征，构建融合片段充电时序特征与单体不一致性标量特征的电池组健康表征体系。提出了一种Transformer编码器与多层感知机相结合的双分支SOH估计模型，实现时序特征与标量特征的有效融合。依托经过实测数据校验、精度可靠的电池组数字孪生仿真平台，构建了覆盖完整健康区间的仿真样本数据集完成模型训练与初步测试。结果表明，所提模型在测试集上表现出较高的SOH估计精度，均方根误差小于1%。进一步在两组不同不一致性、不同健康状态的实测电池组数据上开展了模型迁移验证，SOH估计绝对误差小于2%。通过特征消融研究进一步验证了不一致性特征的引入与特征融合策略能够显著提升模型的SOH估计精度与可靠性。

Abstract

Accurate state of health (SOH) estimation for lithium-ion battery packs plays an essential role in ensuring safe and reliable operation

particularly under complex inconsistency conditions. This study proposes an SOH estimation method that extracts time-series and statistical features reflecting cell inconsistency from charging time-series data and capacity increment curves. Redundant features are removed through correlation analysis while retaining the core inconsistency features. A dual-branch model based on a Transformer encoder and a multilayer perceptron is then developed to fuse dynamic temporal information with global inconsistency descriptors. To support the training and preliminary testing of the model

a large-scale simulation dataset covering the full battery health range is generated on a battery-pack digital twin and verified against measured data. The proposed method achieves a high SOH estimation accuracy (root mean square error <1%) on the test set. Transfer validation on two measured battery packs with different inconsistency and health states shows absolute SOH estimation errors below 2%. Ablation results further demonstrate that the inconsistency features and fusion strategy significantly improve the SOH estimation accuracy and robustness.

关键词

Keywords

references

董明, 李晓枫, 熊锦晨, 等. 基于自放电阻抗变化的锂电池存储容量衰减评估技术[J]. 中国电机工程学报, 2025, 45(3): 1052-1062. DOI: 10.13334/j.0258-8013.pcsee.231788.

DONG M, LI X F, XIONG J C, et al. Evaluation of lithium battery storage capacity degradation based on self-discharge impedance change[J]. Proceedings of the CSEE, 2025, 45(3): 1052-1062. DOI: 10.13334/j.0258-8013.pcsee.231788.

王德顺, 薛金花, 魏海坤, 等. 磷酸铁锂电池模组老化行为[J]. 科学技术与工程, 2022, 22(19): 8562-8567. DOI: 10.3969/j.issn.1671-1815.2022.19.053.

WANG D S, XUE J H, WEI H K, et al. Aging behavior of lithium iron phosphate battery modules[J]. Science Technology and Engineering, 2022, 22(19): 8562-8567. DOI: 10.3969/j.issn.1671-1815.2022.19.053.

袁梓菡, 严晓, 杨涛. 老化锂电池模组关键电池性能参数的量化分析[J]. 储能科学与技术, 2022, 11(1): 221-227.

YUAN Z H, YAN X, YANG T. Quantitative analysis of key battery performance parameters of aging lithium battery module[J]. Energy Storage Science and Technology, 2022, 11(1): 221-227.

刘璐, 牛萌, 郑伟杰, 等. 考虑内部参数不一致性的储能系统用锂电池组建模[J]. 电力系统自动化, 2021, 45(19): 15-23. DOI: 10.7500/AEPS20210322002.

LIU L, NIU M, ZHENG W J, et al. Modeling of lithium-ion battery packs for energy storage system considering inconsistency of internal battery parameters[J]. Automation of Electric Power Systems, 2021, 45(19): 15-23. DOI: 10.7500/AEPS20210322002.

吴凤和, 柴海宁, 章正柱, 等. 基于自适应LTTB与DTW-DBA-means的动力电池组不一致性评估方法[J]. 计量学报, 2024, 45(6): 890-898.

WU F H, CHAI H N, ZHANG Z Z, et al. An inconsistency assessment method for power battery pack based on adaptive LTTB and DTW-DBA-means[J]. Acta Metrologica Sinica, 2024, 45(6): 890-898.

张腾, 常国峰. 基于单体特征参数差异的电池组热特性和热一致性研究[J]. 储能科学与技术, 2025, 14(8): 3194-3206. DOI: 10.19799/j.cnki.2095-4239.2025.0127.

ZHANG T, CHANG G F. Thermal characterization and thermal consistency study of battery packs based on differences in monomer characteristic parameters[J]. Energy Storage Science and Technology, 2025, 14(8): 3194-3206. DOI: 10.19799/j.cnki. 2095-4239.2025.0127.

杨思嘉. 电动汽车动力电池组健康状态评估及梯次利用分选应用研究[D]. 北京: 北京交通大学, 2024.YANG S J. Research on state of health evaluation and echelon utilization sorting application of power battery packs for electric vehicles[D]. Beijing: Beijing Jiaotong University, 2024.

李卓昊, 石琼林, 王康丽, 等. 锂离子电池健康状态估计方法研究现状与展望[J]. 电力系统自动化, 2024, 48(20): 109-129. DOI: 10.7500/AEPS20231221006.

LI Z H, SHI Q L, WANG K L, et al. Research status and prospects of state of health estimation methods for lithium-ion batteries[J]. Automation of Electric Power Systems, 2024, 48(20): 109-129. DOI: 10.7500/AEPS20231221006.

汪宇航, 黄海宏, 王海欣, 等. 基于荷电状态差异的退役电池健康状态快速估计研究[J]. 仪器仪表学报, 2023, 44(12): 55-68. DOI: 10.19650/j.cnki.cjsi.J2311641.

WANG Y H, HUANG H H, WANG H X, et al. Research on fast estimation of the state of health of retired batteries based on the state of charge differences[J]. Chinese Journal of Scientific Instrument, 2023, 44(12): 55-68. DOI: 10.19650/j.cnki.cjsi.J231 1641.

霍德鑫, 范国栋, 张希, 等. 基于电化学模型的全固态电池健康状态估计[J]. 电源技术, 2025, 49(5): 1006-1012. DOI: 10.3969/j.issn.1002-087X.2025.05.016.

HUO D X, FAN G D, ZHANG X, et al. State of health estimation of all-solid-state batteries based on electrochemical model[J]. Chinese Journal of Power Sources, 2025, 49(5): 1006-1012. DOI: 10.3969/j.issn.1002-087X.2025.05.016.

金帅, 董静. 基于数据驱动的锂离子电池健康状态估计研究进展综述[J]. 仪器仪表学报, 2024, 45(3): 45-59.

JIN S, DONG J. A review of research progress on data-driven state of health estimation for lithium-ion batteries[J]. Chinese Journal of Scientific Instrument, 2024, 45(3): 45-59.

顾菊平, 蒋凌, 张新松, 等. 基于特征提取的锂离子电池健康状态评估及影响因素分析[J]. 电工技术学报, 2023, 38(19): 5330-5342. DOI: 10.19595/j.cnki.1000-6753.tces.231085.

GU J P, JIANG L, ZHANG X S, et al. Estimation and influencing factor analysis of lithium-ion batteries state of health based on features extraction[J]. Transactions of China Electrotechnical Society, 2023, 38(19): 5330-5342. DOI: 10.19595/j.cnki.1000-6753.tces.231085.

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.

张瑛, 康永哲, 段彬, 等. 基于数据-模型双驱动的电池组容量在线估计[J]. 机械工程学报, 2025, 61(2): 210-221.

ZHANG Y, KANG Y Z, DUAN B, et al. Online estimation of battery pack capacity based on dual driven method of data and model[J]. Journal of Mechanical Engineering, 2025, 61(2): 210-221.

SUN G, LIU Y, LIU X. A method for estimating lithium-ion battery state of health based on physics-informed machine learning[J]. Journal of Power Sources, 2025, 627: DOI: 10.1016/j.jpowsour. 2024.235767.

WANG J Y, ZHANG C P, ZHANG L J, et al. A novel aging characteristics-based feature engineering for battery state of health estimation[J]. Energy, 2023, 273: 127169. DOI: 10.1016/j.energy.2023.127169.

范鑫源. 考虑不一致性的电池组建模方法及应用研究[D]. 北京: 北京交通大学, 2023.FAN X Y. Research on modeling method and application of battery pack considering inconsistency[D]. Beijing: Beijing Jiaotong University, 2023.

许万里, 洪小波, 王东阳, 等. 基于一致性检验的锂离子电池组健康状态预测[J]. 电源技术, 2025(4): 772-781.

XU W L, HONG X B, WANG D Y, et al. Prediction of lithium-ion battery pack SOH based on consistency check[J]. Chinese Journal of Power Sources, 2025(4): 772-781.

DU Y H, SONG Y C, LIU D T. Degradation modeling of serial space lithium-ion battery pack based on online inconsistency representation parameters[J]. Journal of Power Sources, 2024, 624: 235608. DOI: 10.1016/j.jpowsour.2024.235608.

ZHOU Z K, DUAN B, KANG Y Z, et al. Online state of health estimation for series-connected LiFePO 4 battery pack based on differential voltage and inconsistency analysis[J ] . IEEE Transactions on Transportation Electrification, 2024, 10(1): 989-998. DOI: 10.1109/TTE.2023.3274819.

MU A X, ZHANG B J, LI C G, et al. Estimating SOC and SOH of energy storage battery pack based on voltage inconsistency using reference-difference model and dual extended Kalman filter[J]. Journal of Energy Storage, 2024, 81: 110221. DOI: 10.1016/j.est.2023.110221.

DIAO W P, JIANG J C, ZHANG C P, et al. Energy state of health estimation for battery packs based on the degradation and inconsistency[J]. Energy Procedia, 2017, 142: 3578-3583. DOI: 10.1016/j.egypro.2017.12.248.

ZHANG X, WANG Y J, LIU C, et al. A novel approach of battery pack state of health estimation using artificial intelligence optimization algorithm[J]. Journal of Power Sources, 2018, 376: 191-199. DOI: 10.1016/j.jpowsour.2017.11.068.

王子鹏, 黄凯, 孙恺, 等. 基于源域电池迭代模块和LSTM神经网络的锂离子电池寿命预测[J]. 电源学报, 2025, 23(7): 294-303.

WANG Z P, HUANG K, SUN K, et al. Prediction of remaining useful life of lithium-ion battery based on source-domain battery iterations module and LSTM neural network[J]. Journal of Power Supply, 2025, 23(7): 294-303.

赵沁峰, 蔡艳平, 王新军. 锂离子电池全生命周期剩余使用寿命预测[J]. 电源学报, 2024, 22(2): 197-204.

ZHAO Q F, CAI Y P, WANG X J. Remaining useful life prediction for full life cycle of lithium-ion battery[J]. Journal of Power Supply, 2024, 22(2): 197-204.

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

融合REMD-NHITS与KDE的锂离子电池健康状态退化预测

融合特征多尺度池化的锂电池健康状态评估算法

基于超参数自适应优化的Transformer锂离子电池SOH预测算法

基于自适应变分模态分解与重构的全钒液流电池健康状态预测

混合储能的孤岛直流微电网运行协调控制策略