多特征融合的MVMD-VSN_GRU锂离子电池健康状态预测方法研究

吴康佳; 姬钰培; 冀鹏宇; 袁泽宇; 崔方舒; 乔钢柱

doi:10.19799/j.cnki.2095-4239.2026.0198

您当前的位置：

首页 >

文章列表页 >

多特征融合的MVMD-VSN_GRU锂离子电池健康状态预测方法研究

储能测试与评价 | 更新时间：2026-07-28

- 多特征融合的MVMD-VSN_GRU锂离子电池健康状态预测方法研究
- Research on state of health prediction method of lithium-ion batteries based on multi-feature fusion MVMD-VSN_GRU
- 储能科学与技术 2026年15卷第7期页码：2802-2816
- 作者机构：
  
  1.中北大学计算机科学与技术学院，山西太原 030051
  2.中北大学极限环境光电动态测试技术与仪器全国重点实验室，山西太原 030051
- 作者简介：
  
  吴康佳（2001—），女，硕士研究生，研究方向为储能电池健康管理，E-mail：kjia0215@163.com；
  乔钢柱，教授，研究方向为物联网技术及应用、大数据处理技术等，E-mail：qiaogz@nuc.edu.cn。
- 基金信息：
  
  山西省基础研究计划(202303021222084);山西省基础研究计划(202303021222120)
- DOI：10.19799/j.cnki.2095-4239.2026.0198
  中图分类号： TM 912
- 收稿：2026-03-10，
  
  修回：2026-04-29，
  
  网络首发：2026-07-28，
  
  纸质出版：2026-07-28
- 稿件说明：
移动端阅览
吴康佳, 姬钰培, 冀鹏宇, 等. 多特征融合的MVMD-VSN_GRU锂离子电池健康状态预测方法研究[J]. 储能科学与技术, 2026, 15(7): 2802-2816.

WU Kangjia, JI Yupei, JI Pengyu, et al. Research on state of health prediction method of lithium-ion batteries based on multi-feature fusion MVMD-VSN_GRU[J]. Energy Storage Science and Technology, 2026, 15(7): 2802-2816.
吴康佳, 姬钰培, 冀鹏宇, 等. 多特征融合的MVMD-VSN_GRU锂离子电池健康状态预测方法研究[J]. 储能科学与技术, 2026, 15(7): 2802-2816. DOI： 10.19799/j.cnki.2095-4239.2026.0198.

WU Kangjia, JI Yupei, JI Pengyu, et al. Research on state of health prediction method of lithium-ion batteries based on multi-feature fusion MVMD-VSN_GRU[J]. Energy Storage Science and Technology, 2026, 15(7): 2802-2816. DOI： 10.19799/j.cnki.2095-4239.2026.0198.

摘要

在新能源汽车、大规模储能电站等领域快速发展的背景下，精准预测锂离子电池健康状态（state of health，SOH）对于保障电池系统安全稳定运行以及延长服役寿命具有重要意义。针对锂离子电池健康状态直接性能参数获取困难，以及传统时序预测模型中单一变量预测精度偏低、多变量权重固定导致SOH预测精度受限的问题，本研究提出一种基于变量选择网络（variable selection network，VSN）与门控循环单元（gated recurrent unit，GRU）的多特征融合的锂离子电池SOH预测模型。该方法从电池充放电循环数据中提取与SOH高度相关的健康因子（health indicator，HI）构成多元特征序列，采用多元变分模态分解对此多特征序列进行协同自适应分解，以充分提取并保留变量间的耦合时频特征。在每个分解得到的多元子序列上，构建基于袋獾优化算法超参数寻优的VSN_GRU模型，实现对关键健康因子的动态感知与建模预测。最后，将各分解分量的预测结果叠加求和得到最终SOH预测值。在NASA电池数据集与WZU随机电池退化数据上的实验结果表明，相较于消融实验中的对比模型，本模型可有效提升锂离子电池SOH的预测精度。

Abstract

Against the backdrop of the rapid development of new energy vehicles and large-scale energy storage systems

accurate prediction of the state of health (SOH) of lithium-ion batteries is of great importance for ensuring the safe and stable operation of battery systems and extending their service life. To address the challenges associated with the direct acquisition of lithium-ion battery health parameters

as well as the limited SOH prediction accuracy of traditional time-series forecasting models caused by low single-variable prediction precision and multivariable weighting schemes

this study proposes a multi-feature fusion SOH prediction model based on a variable selection network (VSN) and gated recurrent unit (GRU). First

health indicators (HIs) with high correlations to SOH are extracted from battery charge-discharge cycle data to construct a multivariate feature sequence. Subsequently

the sequence is adaptively and collaboratively decomposed using multivariate variational mode decomposition to fully extract and preserve the coupled time-frequency characteristics among variables. For each decomposed multivariate subsequence

a VSN_GRU model optimized using the Tasmanian Devil Optimization algorithm is developed to achieve dynamic perception

modeling

and prediction of key HIs. Finally

the overall SOH prediction is obtained by aggregating the prediction results of all decomposed components. Experimental results based on the NASA battery dataset and the WZU random battery degradation dataset demonstrate that

compared with benchmark models used in the ablation experiments

the proposed model substantially improves the prediction accuracy of lithium-ion battery SOH.

关键词

Keywords

references

TIAN H X, QIN P L, LI K, et al. A review of the state of health for lithium-ion batteries: Research status and suggestions[J]. Journal of Cleaner Production, 2020, 261: 120813. DOI:10.1016/j.jclepro. 2020.120813.

张吴哲, 蔡志端, 吴成傲, 等. 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.

ZHANG W Z, CAI Z D, WU C A, et al. 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.

晋殿卫, 顾则宇, 张志宏. 锂电池健康度和剩余寿命预测算法研究[J]. 电力系统保护与控制, 2023, 51(1): 122-130. DOI:10.19783/j.cnki.pspc.211447.

JIN D W, GU Z Y, ZHANG Z H. Lithium battery health degree and residual life prediction algorithm[J]. Power System Protection and Control, 2023, 51(1): 122-130. DOI:10.19783/j.cnki.pspc.211447.

张朝龙, 陈阳, 刘梦玲, 等. 一种基于ICA-T特征和CNN-LA-BiLSTM的锂离子电池健康状态估计方法[J]. 储能科学与技术, 2025(3): 1258-1269.

ZHANG C L, CHEN Y, LIU M L, et al. A state of health estimation method for lithium-ion batteries using ICA-T features and CNN-LA-BiLSTM[J]. Energy Storage Science and Technology, 2025(3): 1258-1269.

LIU Y W, SUN J, SHANG Y L, et al. A novel remaining useful life prediction method for lithium-ion battery based on long short-term memory network optimized by improved sparrow search algorithm[J]. Journal of Energy Storage, 2023, 61: 106645. DOI:10.1016/j.est.2023.106645.

ZHU R, DUAN B, ZHANG J M, et al. Co-estimation of model parameters and state-of-charge for lithium-ion batteries with recursive restricted total least squares and unscented Kalman filter[J]. Applied Energy, 2020, 277: 115494. DOI:10.1016/j.apenergy.2020.115494.

樊欣欣, 丁晖, 陈秀国, 等. 基于模糊逻辑的变电站蓄电池在线健康状态评估[J]. 电子器件, 2021, 44(1): 136-140. DOI:10.3969/j.issn.1005-9490.2021.01.026.

FAN X X, DING H, CHEN X G, et al. On-line health assessment of substation battery based on fuzzy logic[J]. Chinese Journal of Electron Devices, 2021, 44(1): 136-140. DOI:10.3969/j.issn.1005-9490.2021.01.026.

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.

娄岚浩, 杨立鹏, 杨晓光. 锂离子电池电化学机理模型参数辨识研究综述[J]. 化工学报, 2025, 76(9): 4369-4382.

LOU L H, YANG L P, YANG X G. Review of parameter identification for physics-based lithium-ion battery models[J]. CIESC Journal, 2025, 76(9): 4369-4382.

CHEN D Q, ZHOU X Z. AttMoE: Attention with mixture of experts for remaining useful life prediction of lithium-ion batteries[J]. Journal of Energy Storage, 2024, 84: 110780. DOI:10.1016/j.est. 2024.110780.

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. DOI:10.19799/j.cnki.2095-4239.2024.1253.

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. DOI:10.19799/j.cnki.2095-4239.2024. 1253.

董作林, 宋金岩, 孟子迪. 基于模态分解和深度学习的锂离子电池寿命预测[J]. 储能科学与技术, 2025, 14(4): 1645-1653. DOI:10.19799/j.cnki.2095-4239.2024.0983.

DONG Z L, SONG J Y, MENG Z D. Lithium-ion battery life prediction based on mode decomposition and deep learning[J]. Energy Storage Science and Technology, 2025, 14(4): 1645-1653. DOI:10.19799/j.cnki.2095-4239.2024.0983.

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.

LI J B, WANG Z X, TIAN D, et al. Prediction method for remaining service life of lithium batteries using SSA-LSTM combination under variable mode decomposition[J]. Energy Storage Science and Technology, 2025, 14(2): 659-670.

STREB M, OHRELIUS M, SIDDIQUI A, et al. Diagnosis and prognosis of battery degradation through re-evaluation and Gaussian process regression of electrochemical model parameters[J]. Journal of Power Sources, 2023, 588: 233686. DOI:10.1016/j.jpowsour.2023.233686.

ZHANG X G, WANG Z, GONG Q S, et al. State of health estimation of lithium-ion batteries based on hybrid neural networks with residual connections[J]. Journal of the Electrochemical Society, 2025, 172(2): 020503. DOI:10.1149/1945-7111/adada3.

尹杰, 刘博, 孙国兵, 等. 基于迁移学习和降噪自编码器-长短时间记忆的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(1): 289-302. DOI:10.19595/j.cnki.1000-6753.tces.221890.

YIN J, LIU B, SUN G B, et al. Transfer learning denoising autoencoder-long short term memory for remaining useful life prediction of Li-ion batteries[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 289-302. DOI:10.19595/j.cnki.1000-6753.tces.221890.

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.

WANG J L, ZHANG F D, ZHANG J C, et al. A flexible RUL prediction method based on poly-cell LSTM with applications to lithium battery data[J]. Reliability Engineering & System Safety, 2023, 231: 108976. DOI:10.1016/j.ress.2022.108976.

时洪雷, 刘喜军, 高竟译, 等. 基于超参数优化和混合神经网络的锂硫电池健康状态估计[J]. 储能科学与技术, 2025, 14(12): 4721-4731.

SHI H L, LIU X J, GAO J Y, et al. State of health estimation of lithium-sulfur batteries based on hyperparameter optimization and hybrid neural networks[J]. Energy Storage Science and Technology, 2025, 14(12): 4721-4731.

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.

张安安, 谢琳惺, 杨威. 基于CNN-GRU组合神经网络的锂电池寿命预测模型研究[J]. 电测与仪表, 2025, 62(7): 77-84.

ZHANG A A, XIE L X, YANG W. Research on Lithium battery life prediction model based on CNN-GRU combined neural network[J]. Electrical Measurement & Instrumentation, 2025, 62(7): 77-84.

WANG X H, DAI K, HU M, et al. Lithium-ion battery health state and remaining useful life prediction based on hybrid model MFE-GRU-TCA[J]. Journal of Energy Storage, 2024, 95: 112442. DOI:10.1016/j.est.2024.112442.

莫易敏, 余自豪, 叶鹏, 等. 基于迁移学习与GRU神经网络结合的锂电池SOH估计[J]. 太阳能学报, 2024, 45(3): 233-239. DOI:10.19912/j.0254-0096.tynxb.2022-1771.

MO Y M, YU Z H, YE P, et al. Lithium battery SOH estimation method based on combination of transfer learning and GRU neural network[J]. Acta Energiae Solaris Sinica, 2024, 45(3): 233-239. DOI:10.19912/j.0254-0096.tynxb.2022-1771.

LIM B, ARIK S Ö, LOEFF N, et al. Temporal Fusion Transformers for interpretable multi-horizon time series forecasting[J]. International Journal of Forecasting, 2021, 37(4): 1748-1764. DOI:10.1016/j.ijforecast.2021.03.012.

郭鑫喆, 王业琴, 王超, 等. 基于多目标模态分解与NAHL神经网络的电动汽车充电负荷预测方法[J]. 电测与仪表, 2025, 62(3): 20-29.

GUO X Z, WANG Y Q, WANG C, et al. Electric vehicle charging load prediction method based on multi-objective modal decomposition and NAHL neural network[J]. Electrical Measurement & Instrumentation, 2025, 62(3): 20-29.

REHMAN N U, AFTAB H. Multivariate variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2019, 67(23): 6039-6052. DOI:10.1109/TSP.2019.2951223.

DEHGHANI M, HUBÁLOVSKÝ Š, TROJOVSKÝ P. Tasmanian devil optimization: A new bio-inspired optimization algorithm for solving optimization algorithm[J]. IEEE Access, 2022, 10: 19599-19620. DOI:10.1109/ACCESS.2022.3151641.

李泽龙, 乔钢柱, 崔方舒, 等. 应用VMD-HPO-NBEATS模型的锂离子电池SOH预测[J]. 中国测试, 2024, 50(9): 65-73. DOI:10.11857/j.issn.1674-5124.2024070058.

LI Z L, QIAO G Z, CUI F S, et al. State of health prediction of lithium-ion batteries based on VMD-HPO-NBEATS model[J]. China Measurement & Testing Technology, 2024, 50(9): 65-73. DOI:10.11857/j.issn.1674-5124.2024070058.

LYU D Z, ZHANG B, ZIO E, et al. Battery cumulative lifetime prognostics to bridge laboratory and real-life scenarios[J]. Cell Reports Physical Science, 2024, 5(9): 102164. DOI:10.1016/j.xcrp.2024.102164.

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

基于集成学习和分位数回归的锂离子电池寿命预测方法

基于EEMD-GRU-NN锂离子电池表面温度预测方法研究

基于模态分解的Transformer-GRU联合电池健康状态估计

塔式重力储能系统关键技术与集成应用研究现状及进展

高利用率锌金属负极：关键挑战与研究进展