电源学报

基于容量序列分解与重构的LSTM锂电池剩余寿命预测算法

PDF下载

冯杰中国电源学会学生会员 ¹ , 吕志刚 ¹ , 邸若海 ¹ , 王鹏 ² , 王储 ¹

电源学报 | 人工智能与电力电子 2026,24(3): 230-241

收起

电源学报 |人工智能与电力电子 2026 , 24 (3) : 230 -241

基于容量序列分解与重构的LSTM锂电池剩余寿命预测算法

全屏

冯杰中国电源学会学生会员¹, 吕志刚¹, 邸若海¹, 王鹏², 王储¹

作者信息

^1.西安工业大学电子信息工程学院，西安　710021

^2.西安工业大学发展规划处，西安　710021

通讯作者:

吕志刚（1978—　），男，通信作者，硕士，副教授。研究方向：嵌入式技术，图像处理，故障诊断与健康管理。E-mail：lvzhigang@xatu.edu.cn。

作者简介:

冯杰（2000—　），男，中国电源学会学生会员，硕士研究生。研究方向：神经网络建模与电池健康状态研究。E-mail：fengjie@st.xatu.edu.cn。

邸若海（1986—　），男，博士，副教授。研究方向：不确定建模理论与方法，复杂系统健康状态评估与故障预测，作战系统仿真与分析。E-mail：diruohai@xatu.edu.cn。

王鹏（1978—　），男，博士，教授。研究方向：模式识别与智能系统，军民用装备健康管理与预测等方向研究。E-mail：wang_peng@xatu.edu.cn。

王储（1988—　），男，博士，讲师。研究方向：复杂系统故障预测与健康管理。E-mail：wangchu@xatu.edu.cn。

Remaining Useful Life Prediction Algorithm for Lithium-ion Batteries Based on LSTM of Capacity Sequence Decomposition and Reconstruction

Jie FENG Student Member, CPSS¹, Zhigang LÜ¹, Ruohai DI¹, Peng WANG², Chu WANG¹

Affiliations

^1.School of Electronic Information Engineering, Xi’an Technological University, Xi’an 710021, China

^2.Development and Planning Department, Xi’an Technological University, Xi’an 710021, China

出版时间: 2026-03-30 doi: 10.13234/j.issn.2095-2805.2026.3.230

文章导航

摘要

收起

锂电池未来容量的准确预测是锂电池健康管理系统的关键。针对锂电池容量序列受容量再生等影响，设计了1种基于容量序列分解与重构的长短期记忆LSTM（long short-term memory）神经网络锂电池剩余寿命预测模型。首先，使用自适应噪声完备集合经验模态分解CEEMDAN（complete ensemble empirical mode decomposition with adaptive noise）技术将原始序列分解为多个固有模态分量，可以消除容量回升现象；其次，采用Hurst技术将各分量重组成多个规律性强的子序列，可以降低测试阶段的时耗；然后，分别对多个子序列利用鲸鱼优化算法WOA（whale optimization algorithm）对LSTM的参数进行优化并将多组预测结果进行叠加，从而获得最终的预测结果；最后，在2组具有不同退化特征的锂电池失效数据集上验证了设计模型的有效性。实验结果表明，所提方法在平均绝对误差和均方根误差方面均能保持在一定范围内。

关键词

锂离子电池 / 经验模态分解 / 赫斯特 / 鲸鱼优化算法 / 长短期记忆神经网络

Abstract

收起

The accurate prediction of the futural capacity of lithium batteries is crucial for their health management systems. Aimed at the impact of capacity regeneration on the capacity sequences of lithium-ion batteries, a long short-term memory (LSTM) neural network-based remaining useful life prediction model is proposed, which is based on capacity sequence decomposition and reconstruction. First, the CEEMDAN technology is used to decompose the original sequence into various intrinsic mode components, so as to eliminate the phenomenon of capacity rebound. Second, the Hurst technique is utilized to reassemble each component into multiple systematically strong sub-sequences, which can reduce the time consumption during the testing phase. Third, the whale optimization algorithm is applied to multiple sub-sequences to optimize the parameters of LSTM, and the outcomes from various sets of predictions are further aggregated to derive the ultimate prediction results. Finally, the effectiveness of the proposed model is verified on two sets of lithium-ion battery failure datasets with different degradation characteristics. Experimental results show that the proposed method can maintain both the mean absolute error and root mean square error in certain ranges.

Key words

Lithium-ion battery / empirical mode decomposition / Hurst / whale optimization algorithm / long short-term memory (LSTM) neural network

引用本文

冯杰中国电源学会学生会员, 吕志刚, 邸若海, 王鹏, 王储. 基于容量序列分解与重构的LSTM锂电池剩余寿命预测算法. 电源学报, 2026 , 24 (3) : 230 -241 . DOI: 10.13234/j.issn.2095-2805.2026.3.230

Jie FENG, Zhigang LÜ, Ruohai DI, Peng WANG, Chu WANG. Remaining Useful Life Prediction Algorithm for Lithium-ion Batteries Based on LSTM of Capacity Sequence Decomposition and Reconstruction[J]. Journal of Power Supply, 2026 , 24 (3) : 230 -241 . DOI: 10.13234/j.issn.2095-2805.2026.3.230

基金

收起

国家自然科学基金资助项目(62171360)
陕西省科技厅重点研发计划资助项目(2023-LL-QY-25)
国家重点研发计划资助项目(2022YFF0604900)
2022年度陕西高校青年创新团队资助项目
山东省智慧交通重点实验室（筹）资助项目
2023年陕西省高校工程研究中心资助项目

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

成燕, 郑林弘, 刘江. 基于模态分解和时间序列的锂电池健康状态估计[J]. 电源学报, 2025, 23(5): 241-250. Cheng Yan, Zheng Linhong, Liu Jiang. Estimation of state-of-health of lithium-ion batteries based on modal decomposition and time series[J]. Journal of Power Supply, 2025, 23(5): 241-250. (in Chinese)

[2]

罗伟林, 张立强, 吕超, 等. 锂离子电池寿命预测国外研究现状综述[J]. 电源学报, 2013, 11(1): 140-144. Luo Weilin, Zhang Liqiang, Lü Chao, et al. Review on foreign status of life prediction of lithium-ion batteries[J]. Journal of Power Supply, 2013, 11(1): 140-144. (in Chinese)

[3]

Khodadadi Sadabadi K, Jin Xin, Rizzoni G. Prediction of remaining useful life for a composite electrode lithium ion battery cell using an electrochemical model to estimate the state of health[J]. Journal of Power Sources, 2021, 481: 228861.

[4]

Goebel K, Saha B, Saxena A, et al. Prognostics in battery health management[J]. IEEE Instrumentation & Measurement Magazine, 2008, 11(4): 33-40.

[5]

Xu Jun, Mei Xuesong, Wang Xiao, et al. Wavelet based relative state of health estimation for lithium-ion batteries[J]. Energy Procedia, 2019, 158: 3101-3106.

[6]

Rawat W, Wang Zenghui. Deep convolutional neural networks for image classification: A comprehensive review[J]. Neural Computation, 2017, 29(9): 2352-2449.

[7]

Wang Jianguo, Zhang Shude, Li Chenyu, et al. A data-driven method with mode decomposition mechanism for remaining useful life prediction of lithium-ion batteries[J]. IEEE Transactions on Power Electronics, 2022, 37(11): 13684-13695.

[8]

Zhang Yongzhi, Xiong Rui, He Hongwen, et al. Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries[J]. IEEE Transactions on Vehicular Technology, 2018, 67(7): 5695-5705.

[9]

姜琳. 锂离子电池荷电状态估计与寿命预测技术研究[D]. 成都: 电子科技大学, 2013. Jiang Lin. Research on state of charge estimation and life prediction of lithium-ion batteries[D]. Chengdu: University of Electronic Science and Technology of China, 2013. (in Chinese)

[10]

谢滟馨, 王顺利, 史卫豪, 等. 一种用于高保真锂电池SOC估计的无迹粒子滤波新方法[J]. 储能科学与技术, 2021, 10(2): 722-731. Xie Yanxin, Wang Shunli, Shi Weihao, et al. A new method of unscented particle filter for high-fidelity lithium-ion battery SOC estimation[J]. Energy Storage Science and Technology, 2021, 10(2): 722-731. (in Chinese)

[11]

王钟毅, 姬晓, 左思. 基于BP神经网络的锂电池剩余寿命预测[J]. 汽车实用技术, 2021, 46(1): 8-9. Wang Zhongyi, Ji Xiao, Zuo Si. Prediction of residual life of lithium battery based on BP neural network[J]. Automobile Technology, 2021, 46(1): 8-9. (in Chinese)

[12]

Greff K, Srivastava R K, Koutník J, et al. LSTM: A search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2222-2232.

[13]

丁恒, 黄凯, 田海建. 基于VMD和ISSA-ELM的锂离子电池剩余使用寿命预测[J]. 电源学报, 2024, 22(6): 188-198. Ding Heng, Huang Kai, Tian Haijian. Prediction of remaining useful life of lithium-ion battery based on VMD and ISSA-ELM[J]. Journal of Power Supply, 2024, 22(6): 188-198. (in Chinese)

[14]

刘伟霞, 田勋, 肖家勇, 等. 基于混合模型及LSTM的锂电池SOH与剩余寿命预测[J]. 储能科学与技术, 2021, 10(2): 689-694. Liu Weixia, Tian Xun, Xiao Jiayong, et al. Estimation of SOH and remaining life of lithium batteries based on a combination model and long short-term memory[J]. Energy Storage Science and Technology, 2021, 10(2): 689-694. (in Chinese)

[15]

史永胜, 施梦琢, 丁恩松, 等. 基于多退化特征的锂离子电池剩余寿命预测[J]. 电源技术, 2020, 44(6): 836-840. Shi Yongsheng, Shi Mengzhuo, Ding Ensong, et al. Remaining useful life prediction of lithium ion battery based on multiple degradation characteristics[J]. Chinese Journal of Power Sources, 2020, 44(6): 836-840. (in Chinese)

[16]

毕贵红, 谢旭, 蔡子龙, 等. 动态条件下基于深度学习的锂电池容量估计[J]. 汽车工程, 2022, 44(6): 868-877, 885. Bi Guihong, Xie Xu, Cai Zilong, et al. Capacity estimation of lithium-ion battery based on deep learning under dynamic conditions[J]. Automotive Engineering, 2022, 44(6): 868-877, 885. (in Chinese)

[17]

董云龙, 张兆祥, 刘宁波, 等. 海杂波多普勒谱Hurst指数特性分析及目标检测[J]. 雷达科学与技术, 2023, 21(4): 355-363, 374. Dong Yunlong, Zhang Zhaoxiang, Liu Ningbo, et al. Characteristic analysis on Hurst index of sea clutter Doppler spectrum and target detection[J]. Radar Science and Technology, 2023, 21(4): 355-363, 374. (in Chinese)

[18]

曹梦茜, 郑东健. 基于FCM-WOA-LSTM的大坝变形预测模型及其应用[J]. 水电能源科学, 2023, 41(5): 71-75. Cao Mengxi, Zheng Dongjian. Dam deformation predicttion model and its application based on FCM-WOA-LSTM[J]. Water Resources and Power, 2023, 41(5): 71-75. (in Chinese)

2026年第24卷第3期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2026.3.230

接收时间：2023-10-21
首发时间：2026-10-29
出版时间：2026-03-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-10-21
修回日期：2023-12-09
录用日期：2023-12-25

基金

National Natural Science Foundation of China(62171360)

国家自然科学基金资助项目(62171360)

Shaanxi Science and Technology Department(2023-LL-QY-25)

陕西省科技厅重点研发计划资助项目(2023-LL-QY-25)

National Key Research and Development Program(2022YFF0604900)

国家重点研发计划资助项目(2022YFF0604900)

2022 Shaanxi University Youth Innovation Team Project

2022年度陕西高校青年创新团队资助项目

Shandong Key Laboratory of Smart Transportation (Preparation)

山东省智慧交通重点实验室（筹）资助项目

2023 Shaanxi University Engineering Research Center

2023年陕西省高校工程研究中心资助项目

作者信息

^1.西安工业大学电子信息工程学院，西安　710021

^2.西安工业大学发展规划处，西安　710021

通讯作者:

吕志刚（1978—　），男，通信作者，硕士，副教授。研究方向：嵌入式技术，图像处理，故障诊断与健康管理。E-mail：lvzhigang@xatu.edu.cn。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2026.3.230

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT