电源学报

信号二次分解联合机器学习的锂电池剩余寿命预测

PDF下载

代佳骏中国电源学会学生会员 ¹ , 刘云冰 ¹ , 陈贵词 ² , 王文波 ²

电源学报 | 电池与储能 2025,23(8): 262-272

收起

电源学报 |电池与储能 2025 , 23 (8) : 262 -272

信号二次分解联合机器学习的锂电池剩余寿命预测

全屏

代佳骏中国电源学会学生会员¹, 刘云冰¹, 陈贵词², 王文波²

作者信息

^1.武汉科技大学理学院，武汉　430065

^2.冶金工业工程系统科学湖北省重点实验室，武汉　430065

通讯作者:

刘云冰（1972—　），男，通信作者，硕士，副教授。研究方向：大数据分析与处理，模式识别。E-mail：liuyunbing@wust.edu.cn。

作者简介:

代佳骏（2000—　），男，中国电源学会学生会员，硕士研究生。研究方向：锂电池剩余寿命预测。E-mail：daijiajun@wust.edu.cn。

陈贵词（1978—　），男，博士，教授。研究方向：神经网络，机器学习。E-mail：chenguici@wust.edu.cn。

王文波（1978—　），男，博士，教授。研究方向：多尺度分析和神经网络。E-mail：wangwenbo@wust.edu.cn。

Remaining Useful Life Prediction of Lithium Battery Based on Signal Secondary Decomposition Combined with Machine Learning

Jiajun DAI Student Member, CPSS¹, Yunbing LIU¹, Guici CHEN², Wenbo WANG²

Affiliations

^1.College of Science, Wuhan University of Science and Technology, Wuhan 430065, China

^2.Hubei Province Key Laboratory of Systems Science in Metallurgical Process, Wuhan 430065, China

出版时间: 2025-12-30 doi: 10.13234/j.issn.2095-2805.2025.8.262

文章导航

摘要

收起

剩余寿命能够监控锂电池使用能力与使用安全的瞬时状态。因此，掌控锂电池的剩余寿命情况对电池使用的安全性具有十分重要的意义。针对锂电池容量初次分解中高频振荡分量预测优度低的问题，提出1种基于高频信号二次分解联合机器学习预测模型的非线性非平稳信号处理办法。首先将原始信号由完全自适应噪声集合经验模态分解CEEMDAN（complete ensemble empirical mode decomposition with adaptive noise）算法分解，再将其中的高频随机扰动信号利用变分模态分解算法二次分解，然后由长短期记忆LSTM（long short-term memory）网络对分量预测。基于美国国家航天局NASA（National Aeronautics and Space Administration）的4个数据集实验验证，结果表明目标方法具有很高的预测精度。相对于一次分解预测模型CEEMDAN-LSTM，序列预测的拟合优度决定系数R²相对提高了1.25%；平均绝对误差MAE（mean absolute error）、均方根误差RMSE（root mean square error）与平均绝对百分比误差MAPE（mean absolute percentage error）分别相对降低了39.34%、49.43%和41.44%。通过马里兰大学高级生命周期工程中心CALCE（Center for Advanced Life Cycle Engineering）的2个数据集证明目标方法对高频信号的有效预测具有鲁棒性。

关键词

剩余寿命 / 二次分解 / 完全自适应噪声集合经验模态 / 变分模态分解 / 长短时期记忆网络

Abstract

收起

The remaining useful life can monitor the instantaneous state of the performance and safety of lithium battery. Therefore, controlling the remaining useful life of lithium battery is of significance for the safety of battery use. In response to the low predictability of high-frequency oscillation components in the initial decomposition of lithium battery capacity, a nonlinear and non-stationary signal processing method based on the secondary decomposition of high-frequency signals combined with machine learning prediction models is proposed. First, the original signal is decomposed by the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm. Then, the high-frequency random disturbance signals are further decomposed using the variational mode decomposition algorithm, followed by the prediction of components using the long short-term memory (LSTM) network. Experimental verification based on four NASA datasets shows that the proposed method has high prediction accuracy. Compared with those obtained by the CEEMDAN-LSTM model for single decomposition prediction, the value of R² of the sequence prediction is improved by 1.25%, while the values of MAE, RMSE and MAPE are reduced by 39.34%, 49.43% and 41.44%, respectively. The proposed method is robust for the effective prediction of high-frequency signals, as demonstrated by experiments on two CALCE datasets.

Key words

Remaining useful life / secondary decomposition / complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) / variational mode decomposition / long short-term memory (LSTM) network

引用本文

代佳骏中国电源学会学生会员, 刘云冰, 陈贵词, 王文波. 信号二次分解联合机器学习的锂电池剩余寿命预测. 电源学报, 2025 , 23 (8) : 262 -272 . DOI: 10.13234/j.issn.2095-2805.2025.8.262

Jiajun DAI, Yunbing LIU, Guici CHEN, Wenbo WANG. Remaining Useful Life Prediction of Lithium Battery Based on Signal Secondary Decomposition Combined with Machine Learning[J]. Journal of Power Supply, 2025 , 23 (8) : 262 -272 . DOI: 10.13234/j.issn.2095-2805.2025.8.262

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

Qu Wenyu, Chen Guici, Zhang Tingting. An adaptive noise reduction approach for remaining useful life prediction of lithium-ion batteries[J]. Energies, 2022, 15(19): 7422.

[2]

林娅, 陈则王. 锂离子电池剩余寿命预测研究综述[J]. 电子测量技术, 2018, 41(4): 29-35. Lin Ya, Chen Zewang. Review of remaining life pre-diction for lithium-ion batteries[J]. Electronic Measurement Technology, 2018, 41(4): 29-35. (in Chinese)

[3]

Hong J, Lee D, Jeong E R, et al. Towards the swift prediction of the remaining useful life of lithium-ion batteries with end-to-end deep learning[J]. Applied Energy, 2020, 278: 115646.

[4]

安昌祖, 张蕊萍, 张小周, 等. 基于模糊无迹卡尔曼滤波算法的锂电池SOC估计[J]. 电源技术, 2020, 44(3): 333-336, 356. An Changzu, Zhang Ruiping, Zhang Xiaozhou, et al. SOC estimation of lithium battery based on fuzzy unscented Kalman filter[J]. Chinese Journal of Power Sources, 2020, 44(3): 333-336, 356. (in Chinese)

[5]

叶林峰, 石元博, 黄越洋. 基于BiGRU网络的锂电池寿命预测[J]. 电源技术, 2021, 45(5): 598-601. Ye Linfeng, Shi Yuanbo, Huang Yueyang. Lithium battery life prediction based on BiGRU network[J]. Chinese Journal of Power Sources, 2021, 45(5): 598-601. (in Chinese)

[6]

Zhao Jiahui, Zhu Yong, Zhang Bin, et al. Method of predicting SOH and RUL of lithium-ion battery based on the combination of LSTM and GPR[J]. Sustainability, 2022, 14(19): 11865.

[7]

Li Hao, Fu Lijun, Zhang Yan. Lithium battery remaining useful life prediction based on multi-kernel support vector regression with hybrid optimization algorithm[J]. Journal of Electrochemical Energy Conversion and Storage, 2022, 19(3): 031006.

[8]

张朝龙, 何怡刚, 袁莉芬. 基于EEMD和MKRVM的锂电池剩余寿命预测方法[J]. 电力系统及其自动化学报, 2018, 30(7): 38-44. Zhang Chaolong, He Yigang, Yuan Lifen. Prediction approach for remaining useful life of lithium-ion battery based on EEMD and MKRVM[J]. Proceedings of the CSU-EPSA, 2018, 30(7): 38-44. (in Chinese)

[9]

Ouyang Mingsan, Shen Peicheng. Prediction of remaining useful life of lithium batteries based on WOA-VMD and LSTM[J]. Energies, 2022, 15(23): 8918.

[10]

Cai Yuxiang, Li Weimin, Zahid T, et al. Early prediction of remaining useful life for lithium-ion batteries based on CEEMDAN-transformer-DNN hybrid model[J]. Heliyon, 2023, 9(7): e17754.

[11]

Hu Liwen, Wang Wenbo, Ding Guorong. RUL prediction for lithium-ion batteries based on variational mode decomposition and hybrid network model[J]. Signal, Image and Video Processing, 2023, 17(6): 3109-3117.

[12]

宁雪峰, 石正禄, 许加柱. 基于健康因子和PSO-LSTM的锂离子电池健康状态估计[J/OL]. 电源学报, 2023: 1-13. (2023-11-24) [2024-02-13]. https://link.cnki.net/urlid/12.1420.TM.20231123.1426.002. Ning Xuefeng, Shi Zhenglu, Xu Jiazhu. State of health estimation of lithium-ion batteries based on health factors and PSO-LSTM[J/OL]. Journal of Power Supply, 2023: 1-13. (2023-11-24) [2024-02-13]. https://link.cnki.net/urlid/12.1420.TM.20231123.1426.002. (in Chinese)

[13]

Torres M E, Colominas M A, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic, 2011: 4144-4147.

[14]

Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.

[15]

陈红霞, 丁国荣, 陈贵词, 等. 联合变分模态分解和长短时记忆网络的锂离子电池健康状态估计[J]. 电源学报, 2024, 22(S1): 89-97. Chen Hongxia, Ding Guorong, Chen Guici, et al. State-of-health estimation of lithium-ion battery combining variational mode decomposition and long short-term memory network[J]. Journal of Power Supply, 2024, 22(S1): 89-97. (in Chinese)

[16]

Avci C, Tekinerdogan B, Catal C. Analyzing the performance of long short-term memory architectures for malware detection models[J]. Concurrency and Computation: Practice and Experience, 2023, 35(6): e7581.

[17]

任宏宇, 余瑶怡, 杜雄, 等. 基于优化长短期记忆神经网络的IGBT寿命预测模型[J]. 电工技术学报, 2024, 39(4): 1074-1086. Ren Hongyu, Yu Yaoyi, Du Xiong, et al. IGBT lifetime prediction model based on optimized long short-term memory neural network[J]. Transactions of China Electrotechnical Society, 2024, 39(4): 1074-1086. (in Chinese)

[18]

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. Yin Jie, Liu Bo, Sun guobing, 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. (in Chinese)

[19]

黄睿, 朱玲俐, 高峰, 等. 基于变分模态分解的卷积长短时记忆网络短期电力负荷预测方法[J]. 现代电力, 2024, 41(1): 97-105. Huang Rui, Zhu Lingli, Gao Feng, et al. Short-term power load forecasting method based on variational modal decomposition for convolutional long-short-term memory network[J]. Modern Electric Power, 2024, 41(1): 97-105. (in Chinese)

2025年第23卷第8期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2025.8.262

接收时间：2023-12-06
首发时间：2026-10-26
出版时间：2025-12-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-12-06
修回日期：2024-02-13
录用日期：2024-03-05

基金

作者信息

^1.武汉科技大学理学院，武汉　430065

^2.冶金工业工程系统科学湖北省重点实验室，武汉　430065

通讯作者:

刘云冰（1972—　），男，通信作者，硕士，副教授。研究方向：大数据分析与处理，模式识别。E-mail：liuyunbing@wust.edu.cn。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2025.8.262

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