基于递归图多尺度特征的储能锂离子电池剩余寿命预测方法

doi:10.19799/j.cnki.2095-4239.2024.0398

储能科学与技术 ›› 2024, Vol. 13 ›› Issue (10): 3630-3641.doi: 10.19799/j.cnki.2095-4239.2024.0398

• 储能测试与评价 • 上一篇

基于递归图多尺度特征的储能锂离子电池剩余寿命预测方法

谢毓广¹(), 李金中¹, 邹文豪²(), 毛磊²()

^1.国网安徽省电力有限公司电力科学研究院，安徽合肥 230601
^2.中国科学技术大学工程科学学院，安徽合肥 230026

收稿日期:2024-05-06 修回日期:2024-06-06 出版日期:2024-10-28 发布日期:2024-10-30
通讯作者: 邹文豪,毛磊 E-mail:95662479@qq.com;wenhaozou@mail.ustc.edu.cn;leimao82@ustc.edu.cn
作者简介:谢毓广（1979—），男，博士，正高级工程师，研究方向为电力系统优化运行、新能源并网及储能技术，E-mail：95662479@qq.com；
基金资助:
国家电网有限公司科技项目(SGAHDK00DJJS2200281);安徽省自然科学基金能源互联网联合基金(2208085UD03)

Prediction of remaining useful life for lithium-ion battery using recurrence plot analysis

Yuguang XIE¹(), Jinzhong LI¹, Wenhao ZOU²(), Lei MAO²()

^1.State Grid Anhui Electric Power Research Institute, Hefei 230601, Anhui, China
^2.School of Engineering Science, University of Science and Technology of China, Hefei 230026, Anhui, China

Received:2024-05-06 Revised:2024-06-06 Online:2024-10-28 Published:2024-10-30
Contact: Wenhao ZOU, Lei MAO E-mail:95662479@qq.com;wenhaozou@mail.ustc.edu.cn;leimao82@ustc.edu.cn

摘要/Abstract

摘要：

锂离子电池在长期循环使用过程中不可避免地会出现性能退化，这直接影响储能锂离子电池系统的稳定运行。为此，本工作提出基于递归图多尺度特征的锂离子电池剩余寿命预测方法，用于解决从一维状态信号中提取关键退化特征的局限性。鉴于递归图像内蕴含丰富的时空退化特征，首先，构建深度学习多尺度特征提取架构，通过可变大小的感受野，识别同一电压区域在多个周期内的时间维度变化以及相邻电压区域之间空间维度的递归图像时空演变，进而提取深层多尺度特征，用于实现从多尺度特征到RUL的映射建模。再次，通过开展综合评估实验，对所提出方法的预测效果进行系统验证。研究结果表明，该方法使用有限数量的充电过程递归图作为输入，能实现模型快速收敛和准确预测。此外，在跨倍率预测场景中，相较于浅层指标，可实现在2C倍率下将绝对误差和均方根误差的指标性能提升约7倍和5.7倍。最后，通过开展与一维序列输入的对比实验，进一步验证基于递归图多尺度特征进行锂离子电池剩余寿命预测的有效性，实现了各评价指标约50%和43%的性能提升，同时成像所需时序电压采样点数据量相对较小。

关键词: 锂离子电池, 剩余寿命预测, 递归图, 多尺度特征提取

Abstract:

During the long-term cycling of lithium-ion batteries (LIBs), performance degradation is inevitable, which directly impacts the stable operation of the battery system. To address this, this paper proposes a novel for predicting the remaining useful life of LIBs based on multi-scale features derived from recurrence plots. This approach aims to overcome the limitations of extracting key degradation features from one-dimensional (1D) signals, such as voltage data. By leveraging the rich spatiotemporal degradation features captured in recurrence plots, we first develop a deep learning architecture for effective multi-scale feature extraction. This architecture detects temporal variations within the same voltage region across multiple cycles and examines the spatial evolution of recurrence plots between adjacent voltage regions using variable-sized receptive fields. This approach enables the extraction of deep multi-scale features, which are then mapped to RUL modeling. Comprehensive evaluation experiments were performed to systematically validate the predictive effectiveness of the proposed method. The results suggest that by using a limited number of charge process recurrence plots as input, the model achieves rapid convergence and accurate predictions. Additionally, in cross-rate prediction scenarios, the proposed method improves performance metrics, with absolute error (MAE) and root mean squared error (RMSE) reduced by approximately 7-fold and 5.7-fold, respectively, at a 2C rate compared to shallow indicators. Finally, comparative experiments with 1D sequence inputs further validate the effectiveness of predicting the RUL of LIBs using multiscale features of recurrence plots. This approach achieves performance improvements of approximately 50% and 43% in various evaluation metrics, while requiring relatively minimal time-series voltage sampling data for imaging.

Key words: lithium-ion batteries, remaining useful life prediction, recurrence plot, multi-scale feature extraction

中图分类号:

TM 912

谢毓广, 李金中, 邹文豪, 毛磊. 基于递归图多尺度特征的储能锂离子电池剩余寿命预测方法[J]. 储能科学与技术, 2024, 13(10): 3630-3641.

Yuguang XIE, Jinzhong LI, Wenhao ZOU, Lei MAO. Prediction of remaining useful life for lithium-ion battery using recurrence plot analysis[J]. Energy Storage Science and Technology, 2024, 13(10): 3630-3641.

图/表 16

图 1

图2

表1

图3

表2

图4

图5

表3

图6

图7

图 8

图9

表4

图10

表5

图 11

参考文献 27

1	朱晓庆, 王震坡, WANG Hsin, 等. 锂离子动力电池热失控与安全管理研究综述[J]. 机械工程学报, 2020, 56(14): 91-118. DOI: 10.3901/JME.2020.14.091.
	ZHU X Q, WANG Z P, WANG Hsin, et al. Review of thermal runaway and safety management for lithium-ion traction batteries in electric vehicles[J]. Journal of Mechanical Engineering, 2020, 56(14): 91-118. DOI: 10.3901/JME.2020.14.091.
2	CHEN K, LIAO Q, LIU K, et al. Capacity degradation prediction of lithium-ion battery based on artificial bee colony and multi-kernel support vector regression[J]. Journal of Energy Storage, 2023, 72: 108160. DOI: 10.1016/j.est.2023.108160.
3	于志雨. 基于多维特征提取的电池剩余使用寿命预测[D]. 哈尔滨: 哈尔滨工业大学, 2022. DOI: 10.27061/d.cnki.ghgdu.2022.000702.
	YU Z Y. Prediction of battery remaining service life based on multi-dimensional feature extraction[D]. Harbin: Harbin Institute of Technology, 2022. DOI: 10.27061/d.cnki.ghgdu.2022.000702.
4	朱洪涛. 基于模型与数据驱动融合的锂电池寿命预测算法研究[D]. 成都: 电子科技大学, 2022. DOI: 10.27005/d.cnki.gdzku.2022. 001795.
	ZHU H T. Research on lithium battery life prediction algorithm based on model and data-driven fusion[D]. Chengdu: University of Electronic Science and Technology of China, 2022. DOI: 10.27005/d.cnki.gdzku.2022.001795.
5	李晋, 王青松, 孔得朋, 等. 锂电池储能安全评价研究进展[J]. 储能科学与技术, 2023, 12(7): 2282-2301. DOI: 10.19799/j.cnki. 2095-4239.2023.0252.
	LI J, WANG Q S, KONG D P, et al. Research progress on the safety assessment of lithium-ion battery energy storage[J]. Energy Storage Science and Technology, 2023, 12(7): 2282-2301. DOI: 10.19799/j.cnki.2095-4239.2023.0252.
6	刘泓成. 基于改进神经网络的锂电池剩余使用寿命预测研究[D]. 长春: 吉林大学, 2021. DOI: 10.27162/d.cnki.gjlin.2021.004960.
	LIU H C. Research on prediction of residual service life of lithium battery based on improved neural network[D]. Changchun: Jilin University, 2021. DOI: 10.27162/d.cnki.gjlin.2021.004960.
7	HE W, WILLIARD N, OSTERMAN M, et al. Prognostics of lithium-ion batteries based on Dempster-Shafer theory and the Bayesian Monte Carlo method[J]. Journal of Power Sources, 2011, 196(23): 10314-10321. DOI: 10.1016/j.jpowsour.2011.08.040.
8	刘若桐, 李建林, 吕喆, 等. 退役动力电池应用潜力分析[J]. 电气技术, 2021, 22(8): 1-9. DOI: 10.3969/j.issn.1673-3800.2021.08.001.
	LIU R T, LI J L, LYU Z, et al. Application potential analysis of decommissioned power batteries[J]. Electrical Engineering, 2021, 22(8): 1-9. DOI: 10.3969/j.issn.1673-3800.2021.08.001.
9	姜久春, 高洋, 张彩萍, 等. 电动汽车锂离子动力电池健康状态在线诊断方法[J]. 机械工程学报, 2019, 55(20): 60-72, 84. DOI: 10.3901/JME.2019.20.060.
	JIANG J C, GAO Y, ZHANG C P, et al. Online diagnostic method for health status of lithium-ion battery in electric vehicle[J]. Journal of Mechanical Engineering, 2019, 55(20): 60-72, 84. DOI: 10.3901/JME.2019.20.060.
10	段文献. 锂电池状态估计与剩余使用寿命预测的研究[D]. 长春: 吉林大学, 2023. DOI: 10.27162/d.cnki.gjlin.2023.007572.
	DUAN W X. Research on state estimation and residual life prediction of lithium-ion battery[D]. Changchun: Jilin University, 2023. DOI: 10.27162/d.cnki.gjlin.2023.007572.
11	卢婷, 杨文强. 锂电池全生命周期内评估参数及评估方法综述[J]. 储能科学与技术, 2020, 9(3): 657-669. DOI: 10.19799/j.cnki.2095-4239.2019.0263.
	LU T, YANG W Q. Review of evaluation parameters and methods of lithium batteries throughout its life cycle[J]. Energy Storage Science and Technology, 2020, 9(3): 657-669. DOI: 10.19799/j.cnki.2095-4239.2019.0263.
12	杨杰, 王婷, 杜春雨, 等. 锂电池模型研究综述[J]. 储能科学与技术, 2019, 8(1): 58-64. DOI: 10.12028/j.issn.2095-4239.2018.0143.
	YANG J, WANG T, DU C Y, et al. Overview of the modeling of lithium-ion batteries[J]. Energy Storage Science and Technology, 2019, 8(1): 58-64. DOI: 10.12028/j.issn.2095-4239.2018.0143.
13	钱广俊, 韩雪冰, 卢兰光, 等. 锂电池系统均衡策略研究进展[J]. 机械工程学报, 2022, 58(24): 145-162. DOI: 10.3901/JME.2022. 24.145.
	QIAN G J, HAN X B, LU L G, et al. Advances in lithium-ion battery system equalization strategy research[J]. Journal of Mechanical Engineering, 2022, 58(24): 145-162. DOI: 10.3901/JME.2022.24.145.
14	顾菊平, 蒋凌, 张新松, 等. 基于特征提取的锂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.
15	梁海峰, 袁芃, 高亚静. 基于CNN-Bi-LSTM网络的锂电池剩余使用寿命预测[J]. 电力自动化设备, 2021, 41(10): 213-219. DOI: 10.16081/j.epae.202110030.
	LIANG H F, YUAN P, GAO Y J. Remaining useful life prediction of lithium-ion battery based on CNN-Bi-LSTM network[J]. Electric Power Automation Equipment, 2021, 41(10): 213-219. DOI: 10.16081/j.epae.202110030.
16	薛瑾. 锂电池健康状态估计及剩余使用寿命预测研究[D]. 长沙: 湖南大学, 2022. DOI: 10.27135/d.cnki.ghudu.2022.001885.
	XUE J. Research on health state estimation and remaining service life prediction of lithium battery[D]. Changsha: Hunan University, 2022. DOI: 10.27135/d.cnki.ghudu.2022.001885.
17	WU J, ZHANG C B, CHEN Z H. An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks[J]. Applied Energy, 2016, 173: 134-140. DOI: 10.1016/j.apenergy.2016.04.057.
18	MA G J, ZHANG Y, CHENG C, et al. Remaining useful life prediction of lithium-ion batteries based on false nearest neighbors and a hybrid neural network[J]. Applied Energy, 2019, 253: 113626. DOI: 10.1016/j.apenergy.2019.113626.
19	ZHANG W, LI X, LI X. Deep learning-based prognostic approach for lithium-ion batteries with adaptive time-series prediction and on-line validation[J]. Measurement, 2020, 164: 108052. DOI: 10.1016/j.measurement.2020.108052.
20	ECKMANN J P, KAMPHORST S O, RUELLE D. Recurrence plots of dynamical systems[M]// World Scientific Series on Nonlinear Science Series A: World Scientific, 1995: 441-445. DOI: 10.1142/9789812833709_0030.
21	MARWAN N, CARMEN ROMANO M, THIEL M, et al. Recurrence plots for the analysis of complex systems[J]. Physics Reports, 2007, 438(5/6): 237-329. DOI: 10.1016/j.physrep.2006.11.001.
22	ZAHANGIR ALOM M, TAHA T M, YAKOPCIC C, et al. The history began from AlexNet: A comprehensive survey on deep learning approaches[J]. ArXiv e-Prints, 2018: arXiv: 1803.01164. DOI: 10.48550/arXiv.1803.01164.
23	ZOU W H, LU Z Q, HU Z Y, et al. Remaining useful life estimation of bearing using deep multiscale window-based transformer[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3514211. DOI: 10.1109/TIM.2023.3268453.
24	LU Z Q, LIANG L Y, ZHU J, et al. Rotating machinery fault diagnosis under multiple working conditions via a time-series transformer enhanced by convolutional neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3533611. DOI: 10.1109/TIM.2023.3318707.
25	CHRISTOPH B. Diagnosis and prognosis of degradation in lithium-ion batteries[D]. Oxford, South East England, UK: University of Oxford, 2017
26	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Advances in neural information processing systems, 2017: 5998-6008.
27	YAO D C, LI B Y, LIU H C, et al. Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit[J]. Measurement, 2021, 175: 109166. DOI: 10.1016/j.measurement.2021.109166.

层名称	具体参数及输出尺寸
输入层	(time_steps, 224, 224)
卷积层1	卷积核-11×11，通道-48，输出-(48, 55, 55)
最大池化层1	卷积核-3×3，步长-2，输出-(48, 27, 27)
卷积层2	卷积核-5×5，通道-128，输出-(128, 27, 27)
最大池化层2	卷积核-3×3，步长-2，输出-(128, 13, 13)
卷积层3	卷积核-3×3，通道-192，输出-(192, 13, 13)
卷积层4	卷积核-3×3，通道-192，输出-(192, 13, 13)
卷积层5	卷积核-3×3，通道-128，输出-(128, 13, 13)
最大池化层3	卷积核-3×3，步长-2，输出-(128, 6, 6)
全连接层	(128×6×6, 1024)
全连接层	(1024, 1024)
全连接层	(1024, 1)

超参数项目	参数设置情况
输入图像尺寸	(batch_counts, time_steps, 224, 224)
学习率	10^-4
丢弃率	0.3
批量大小	48
优化器	AdamW
最大训练次数	200

名称	循环数
	1		2		3		4
	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
Cell-2-1	5.43	6.88	5.83	8.29	5.40	10.67	6.44	10.90
Cell-2-2	5.59	7.48	4.13	5.34	4.72	5.64	4.39	5.56
Cell-2-3	3.89	5.36	3.62	4.94	3.94	4.83	4.73	5.80
Cell-2-4	4.08	5.16	5.38	5.82	3.45	4.45	5.15	6.19
Cell-2-5	9.36	11.56	6.23	7.94	5.45	6.95	8.10	9.32
Cell-2-6	4.70	6.11	4.48	5.68	4.73	6.41	5.39	7.93
Cell-2-7	8.78	11.21	10.13	13.14	9.39	11.90	10.29	12.10
Cell-2-8	8.39	11.44	7.58	10.21	6.99	9.31	8.92	10.62

平均值	6.28	8.15	5.92	7.67	5.51	7.52	6.68	8.55

工况	深层多尺度特征		浅层特征
工况	MAE	RMSE	MAE	RMSE
1.5C	6.28	8.62	22.51	24.28
2C	7.27	9.19	72.15	77.75
平均值	6.78	8.91	47.33	51.02

名称	所提方法		DWM-Trans		1D-MSCNN
名称	MAE	RMSE	MAE	RMSE	MAE	RMSE
Cell-2-1	5.40	10.67	6.90	9.67	12.02	15.40
Cell-2-2	4.72	5.64	5.59	6.51	9.39	11.50
Cell-2-3	3.94	4.83	3.85	4.71	6.54	7.83
Cell-2-4	3.45	4.45	3.39	4.54	6.15	7.34
Cell-2-5	5.45	6.95	4.12	4.80	10.90	12.36
Cell-2-6	4.73	6.41	4.21	5.35	6.96	8.16
Cell-2-7	9.39	11.90	13.17	16.13	20.39	25.04
Cell-2-8	6.99	9.31	12.58	15.16	15.16	18.56

平均值	5.51	7.52	6.73	8.36	10.94	13.27

基于递归图多尺度特征的储能锂离子电池剩余寿命预测方法

Prediction of remaining useful life for lithium-ion battery using recurrence plot analysis

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 27

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孙中麟, 李嘉波, 田迪, 王志璇, 邢晓静. 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.
[2]	陆继忠, 彭思敏, 李晓宇. 基于多特征量分析和LSTM-XGBoost模型的锂离子电池SOH估计方法[J]. 储能科学与技术, 2024, 13(9): 2972-2982.
[3]	胡雪峰, 常先雷, 刘肖肖, 徐威, 张文彬. 适用于宽温度范围的锂离子电池SOC估计方法[J]. 储能科学与技术, 2024, 13(9): 2983-2994.
[4]	沈思远, 刘亚坤, 罗栋煌, 李雨珺, 郝伟. 储能锂离子电池模组暂态过电压防护设计与电路研发[J]. 储能科学与技术, 2024, 13(9): 3277-3286.
[5]	陈媛, 章思源, 蔡宇晶, 黄小贺, 刘炎忠. 融合多项式特征扩展与CNN-Transformer模型的锂电池SOH估计[J]. 储能科学与技术, 2024, 13(9): 2995-3005.
[6]	邢瑞鹤, 翁素婷, 李叶晶, 张佳怡, 张浩, 王雪锋. AI辅助电池材料表征与数据分析[J]. 储能科学与技术, 2024, 13(9): 2839-2863.
[7]	何宁, 杨芳芳. 考虑能量和温度特征的锂离子电池早期寿命预测[J]. 储能科学与技术, 2024, 13(9): 3016-3029.
[8]	管鸿盛, 钱诚, 孙博, 任羿. 贫数据条件下锂离子电池容量退化轨迹预测方法[J]. 储能科学与技术, 2024, 13(9): 3084-3093.
[9]	柯学, 洪华伟, 郑鹏, 李智诚, 范培潇, 杨军, 郭宇铮, 蒯春光. 基于多时间尺度建模自动特征提取和通道注意力机制的锂离子电池健康状态估计[J]. 储能科学与技术, 2024, 13(9): 3059-3071.
[10]	田成文, 孙丙香, 赵鑫泽, 付智城, 马仕昌, 赵博, 张旭博. 基于数据驱动的锂离子电池快速寿命预测[J]. 储能科学与技术, 2024, 13(9): 3103-3111.
[11]	李清波, 张懋慧, 罗英, 吕桃林, 解晶莹. 基于等效电路模型融合电化学原理的锂离子电池荷电状态估计[J]. 储能科学与技术, 2024, 13(9): 3072-3083.
[12]	何智峰, 陶远哲, 胡泳钢, 王其聪, 杨勇. 机器学习强化的电化学阻抗谱技术及其在锂离子电池研究中的应用[J]. 储能科学与技术, 2024, 13(9): 2933-2951.
[13]	孙丙香, 杨鑫, 周兴振, 马仕昌, 王志豪, 张维戈. 基于简化阻抗模型和比较元启发式算法的锂离子电池参数辨识方法[J]. 储能科学与技术, 2024, 13(9): 2952-2962.
[14]	黄煜峰, 梁焕超, 许磊. 基于卡尔曼滤波算法优化Transformer模型的锂离子电池健康状态预测方法[J]. 储能科学与技术, 2024, 13(8): 2791-2802.
[15]	王志勇, 蔡君瑶, 佘英奇, 钟树林, 潘康华. 氮杂环导电高分子改性锂离子电池石墨负极材料[J]. 储能科学与技术, 2024, 13(8): 2511-2518.