基于健康特征参数的CNN-LSTM&GRU组合锂电池SOH估计

doi:10.19799/j.cnki.2095-4239.2021.0623

摘要/Abstract

摘要：

锂电池健康状态(state of health，SOH)是表征电池实际寿命的关键性参数。SOH不可直接测量，为进一步提升锂电池SOH估计的精度，提出一种基于健康特征参数的CNN-LSTM与GRU组合SOH估计方法。首先，从锂电池充电曲线中初步选取健康特征参数，并通过Spearman相关系数提取健康特征，具体包括恒定电流充电时长、恒定电压充电时长、恒定电流充电时长与恒定电压充电时长的比值以及恒定电流充电阶段温度曲线在时间上的积分与恒定电压充电阶段温度曲线在时间上的积分。其次，采用卷积神经网络(convolutional neural network，CNN)提取健康特征的局部特征，长短期神经网络(long short-term memory，LSTM)挖掘数据时间序列特征，构造CNN-LSTM融合神经网络。然后，将CNN-LSTM网络与门口循环单元(gated recurrent unit，GRU)通过自适应权重因子构成组合SOH估计模型。最后，以NASA锂电池数据集5号、6号、7号、18号电池参数为依据进行验证。实验结果表明，所提组合模型相比于CNN-LSTM、LSTM和GRU此类单一模型，平均绝对误差分别降低了71.8.%、62.4%、22.6%，均方根分别降低了84.1%、79.8%、44.3%。

关键词: 锂离子电池, 健康状态, 健康特征, CNN-LSTM, GRU

Abstract:

The State of Health (SOH) of lithium batteries is a key parameter to characterize the actual useful life. SOH is not directly measurable, and a combined CNN-LSTM and GRU estimation method based on health feature parameters is proposed to further improve the accuracy of SOH estimation. Firstly, the health feature parameters are initially selected from the Li-ion battery charging curve, and the health features are extracted by Spearman correlation coefficient. Secondly, Convolutional Neural Network (CNN) is used to extract local features of health features and Long Short-Term Memory (LSTM) to mine data time series features to construct a CNN-LSTM fusion neural network. Subsequently, the CNN-LSTM and the Gated Recurrent Unit (GRU) are combined to form a combined SOH estimation model by adaptive weighting factors. Finally, the validation is based on the NASA lithium battery dataset 5, 6, 7, and 18 battery parameters. The experimental results show that the estimation accuracy of the proposed combined model is better than that of the single model, and the estimation error is further reduced.

Key words: lithium-ion battery, state of health, health feature, CNN-LSTM, GRU

中图分类号:

TM 911

戴彦文, 于艾清. 基于健康特征参数的CNN-LSTM&GRU组合锂电池SOH估计[J]. 储能科学与技术, 2022, 11(5): 1641-1649.

Yanwen DAI, Aiqing YU. Combined CNN-LSTM and GRU based health feature parameters for lithium-ion batteries SOH estimation[J]. Energy Storage Science and Technology, 2022, 11(5): 1641-1649.

图/表 12

图1

图2

表1

图3

图4

图5

图6

图7

图8

图9

表2

四种方法的SOH估计结果"

型号	预测起点	SOH	CNN-LSTM&GRU			CNN-LSTM			LSTM			GRU
型号	预测起点	SOH	E_SOH	E_rr	$E E r r$ /%	E_SOH	E_rr	$E E r r$ /%	E_SOH	E_rr	$E E r r$ /%	E_SOH	E_rr	$E E r r$ /%
B5	80	31	31	0	0	28	3	9.7	26	5	16.1	26	5	16.1
B6	80	19	18	1	5.2	16	3	15.7	14	5	26.3	15	4	21.1
B7	80	66	67	1	1.5	64	2	3.0	62	4	6.1	62	4	6.1
B18	80	32	33	1	3.1	29	3	9.4	24	8	25.0	27	5	15.6

表2

表3

参考文献 25

1	CAMPI T, CRUCIANI S, MARADEI F, et al. Magnetic field mitigation by multicoil active shielding in electric vehicles equipped with wireless power charging system[J]. IEEE Transactions on Electromagnetic Compatibility, 2020, 62(4): 1398-1405.
2	FAN S, LIU J, WU Q, et al. Optimal coordination of virtual power plant with photovoltaics and electric vehicles: A temporally coupled distributed online algorithm[J]. Applied Energy, 2020, 277: 115583.
3	ZHANG L, FAN W T, WANG Z P, et al. Battery heating for lithium-ion batteries based on multi-stage alternative currents[J]. Journal of Energy Storage, 2020, 32: 101885.
4	张振宇, 汪光森, 聂世雄, 等. 脉冲大倍率放电条件下磷酸铁锂电池荷电状态估计[J]. 电工技术学报, 2019, 34(8): 1769-1779.
	ZHANG Z Y, WANG G S, NIE S X, et al. State of charge estimation of LiFePO₄ battery under the condition of high rate pulsed discharge[J]. Transactions of China Electrotechnical Society, 2019, 34(8): 1769-1779.
5	SUI X, HE S, VILSEN S B, et al. A review of non-probabilistic machine learning-based state of health estimation techniques for Lithium-ion battery[J]. Applied Energy, 2021, 300: 117346.
6	LIPU M S H, HANNAN M A, HUSSAIN A, et al. A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations[J]. Journal of Cleaner Production, 2018, 205: 115-133.
7	LIN C P, CABRERA J, YANG F F, et al. Battery state of health modeling and remaining useful life prediction through time series model[J]. Applied Energy, 2020, 275: 115338.
8	任璞, 王顺利, 何明芳, 等. 基于内阻增加和容量衰减双重标定的锂电池健康状态评估[J]. 储能科学与技术, 2021, 10(2): 738-743.
	REN P, WANG S L, HE M F, et al. State of health estimation of Li-ion battery based on dual calibration of internal resistance increasing and capacity fading[J]. Energy Storage Science and Technology, 2021, 10(2): 738-743.
9	ZHANG C, ALLAFI W, DINH Q, et al. Online estimation of battery equivalent circuit model parameters and state of charge using decoupled least squares technique[J]. Energy, 2018, 142: 678-688.
10	严干贵, 李洪波, 段双明, 等. 基于模型参数辨识的储能电池状态估算[J]. 中国电机工程学报, 2020, 40(24): 8145-8154, 8251.
	YAN G G, LI H B, DUAN S M, et al. Energy storage battery state estimation based on model parameter identification[J]. Proceedings of the CSEE, 2020, 40(24): 8145-8154, 8251.
11	王英楷, 张红, 王星辉. 基于1DCNN-LSTM的锂离子电池SOH预测[J]. 储能科学与技术, 2022, 11(1): 240-245.
	WANG Y K, ZHANG H, WANG X H. Hybrid 1DCNN-LSTM model for predicting lithium ion battery state of health[J]. Energy Storage Science and Technology, 2022, 11(1): 240-245.
12	徐超, 李立伟, 杨玉新, 等. 基于改进粒子滤波的锂电池SOH预测[J]. 储能科学与技术, 2020, 9(6): 1954-1960.
	XU C, LI L W, YANG Y X, et al. Lithium-ion battery SOH estimation based on improved particle filter[J]. Energy Storage Science and Technology, 2020, 9(6): 1954-1960.
13	杨胜杰, 罗冰洋, 王菁, 等. 基于容量增量曲线峰值区间特征参数的锂离子电池健康状态估算[J]. 电工技术学报, 2021, 36(11): 2277-2287.
	YANG S J, LUO B Y, WANG J, et al. State of health estimation for lithium-ion batteries based on peak region feature parameters of incremental capacity curve[J]. Transactions of China Electrotechnical Society, 2021, 36(11): 2277-2287.
14	National Aeronautics and Space Administration Prognostics Center of Excellence. PCoE Datasets[EB/OL]. https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/#battery.
15	YANG J F, XIA B, HUANG W X, et al. Online state-of-health estimation for lithium-ion batteries using constant-voltage charging current analysis[J]. Applied Energy, 2018, 212: 1589-1600.
16	WANG Z K, ZENG S K, GUO J B, et al. State of health estimation of lithium-ion batteries based on the constant voltage charging curve[J]. Energy, 2019, 167: 661-669.
17	YE Y H, SHI Y X, CAI N S, et al. Electro-thermal modeling and experimental validation for lithium ion battery[J]. Journal of Power Sources, 2012, 199: 227-238.
18	张小利, 李雄飞, 李军. 融合图像质量评价指标的相关性分析及性能评估[J]. 自动化学报, 2014, 40(2): 306-315.
	ZHANG X L, LI X F, LI J. Validation and correlation analysis of metrics for evaluating performance of image fusion[J]. Acta Automatica Sinica, 2014, 40(2): 306-315.
19	殷浩然, 苗世洪, 韩佶, 等. 基于三维卷积神经网络的配电物联网异常辨识方法[J]. 电力系统自动化, 2022, 46(1): 42-50.
	YIN H R, MIAO S H, HAN J, et al. Anomaly identification method for distribution Internet of Things based on three-dimensional convolutional neural network[J]. Automation of Electric Power Systems, 2022, 46(1): 42-50.
20	孙黎霞, 白景涛, 周照宇, 等. 基于双向长短期记忆网络的电力系统暂态稳定评估[J]. 电力系统自动化, 2020, 44(13): 64-72.
	SUN L X, BAI J T, ZHOU Z Y, et al. Transient stability assessment of power system based on Bi-directional long-short-term memory network[J]. Automation of Electric Power Systems, 2020, 44(13): 64-72.
21	孟安波, 陈顺, 王陈恩, 等. 基于混沌CSO优化时序注意力GRU模型的超短期风电功率预测[J]. 电网技术, 2021, 45(12): 4692-4700.
	MENG A B, CHEN S, WANG C N, et al. Ultra-short-term wind power prediction based on chaotic CSO optimized temporal attention GRU model[J]. Power System Technology, 2021, 45(12): 4692-4700.
22	顾国庆, 李晓辉. 基于箱线图异常检测的指数加权平滑预测模型[J]. 计算机与现代化, 2021(1): 28-33.
	GU G Q, LI X H. Exponential weighted smoothing prediction model based on abnormal detection of box-plot[J]. Computer and Modernization, 2021(1): 28-33.
23	REHMAN A U, BELHAOUARI S B, IJAZ M, et al. Multi-classifier tree with transient features for drift compensation in electronic nose[J]. IEEE Sensors Journal, 2020, 21(5): 6564-6574.
24	王英楷, 张红, 王星辉. 基于1DCNN-LSTM的锂离子电池SOH预测[J]. 储能科学与技术, 2022, 11(1): 240-245.
	WANG Y K, ZHANG H, WANG X H. Hybrid 1DCNN-LSTM model for predicting lithium ion battery state of health[J]. Energy Storage Science and Technology, 2022, 11(1): 240-245.
25	张吉昂, 王萍, 程泽. 基于充电电压片段和融合方法的锂离子电池SOC-SOH-RUL联合估计‍[J/OL]. 电网技术: 1-12[2021-10-31]. https://doi.org/10.13335/j.1000-3673.pst.2021.0888.
	ZHANG Ji'ang, WANG Ping, CHENG Ze. A Joint estimation framework of SOC-SOH-RUL for lithium batteries based on charging voltage segment and hybrid method[J/OL]. Power System Technology1-12[2021-10-31]. https://doi.‍org/10.‍13335/j.1000-3673.pst.2021.0888.

型号	预测起点	RUL	CNN-LSTM&GRU		CNN-LSTM		LSTM		GRU
型号	预测起点	RUL	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
B5	80	31	0.0096	0.0152	0.0124	0.0273	0.0341	0.0957	0.0255	0.0755
B6	80	19	0.0332	0.0390	0.0418	0.0624	0.0502	0.0566	0.0752	0.1038
B7	80	66	0.0162	0.0212	0.0426	0.0468	0.0681	0.0850	0.0470	0.0569
B18	80	32	0.0260	0.0322	0.0387	0.0742	0.1038	0.1122	0.0753	0.0900

[1]	李海涛, 孔令丽, 张欣, 余传军, 王纪威, 徐琳. N/P设计对高镍NCM/Gr电芯性能的影响[J]. 储能科学与技术, 2022, 11(7): 2040-2045.
[2]	陈龙, 夏权, 任羿, 曹高萍, 邱景义, 张浩. 多物理场耦合下锂离子电池组可靠性研究现状与展望[J]. 储能科学与技术, 2022, 11(7): 2316-2323.
[3]	易顺民, 谢林柏, 彭力. 基于VF-DW-DFN的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2022, 11(7): 2305-2315.
[4]	祝庆伟, 俞小莉, 吴启超, 徐一丹, 陈芬放, 黄瑞. 高能量密度锂离子电池老化半经验模型[J]. 储能科学与技术, 2022, 11(7): 2324-2331.
[5]	王宇作, 王瑨, 卢颖莉, 阮殿波. 孔结构对软碳负极储锂性能的影响[J]. 储能科学与技术, 2022, 11(7): 2023-2029.
[6]	孔为, 金劲涛, 陆西坡, 孙洋. 对称蛇形流道锂离子电池冷却性能[J]. 储能科学与技术, 2022, 11(7): 2258-2265.
[7]	霍思达, 薛文东, 李新丽, 李勇. 基于CiteSpace知识图谱的锂电池复合电解质可视化分析[J]. 储能科学与技术, 2022, 11(7): 2103-2113.
[8]	邓健想, 赵金良, 黄成德. 高能量锂离子电池硅基负极黏结剂研究进展[J]. 储能科学与技术, 2022, 11(7): 2092-2102.
[9]	刘显茜, 孙安梁, 田川. 基于仿生翅脉流道冷板的锂离子电池组液冷散热[J]. 储能科学与技术, 2022, 11(7): 2266-2273.
[10]	于春辉, 何姿颖, 张晨曦, 林贤清, 肖哲熙, 魏飞. 硅基负极与电解液化学反应的分析与抑制策略[J]. 储能科学与技术, 2022, 11(6): 1749-1759.
[11]	丁奕, 杨艳, 陈锴, 曾涛, 黄云辉. 锂离子电池智能消防及其研究方法[J]. 储能科学与技术, 2022, 11(6): 1822-1833.
[12]	张言, 王海, 刘朝孟, 张德柳, 王佳东, 李建中, 高宣雯, 骆文彬. 锂离子电池富镍三元正极材料NCM的研究进展[J]. 储能科学与技术, 2022, 11(6): 1693-1705.
[13]	欧宇, 侯文会, 刘凯. 锂离子电池中的智能安全电解液研究进展[J]. 储能科学与技术, 2022, 11(6): 1772-1787.
[14]	韩俊伟, 肖菁, 陶莹, 孔德斌, 吕伟, 杨全红. 致密储能：基于石墨烯的方法学和应用实例[J]. 储能科学与技术, 2022, 11(6): 1865-1873.
[15]	辛耀达, 李娜, 杨乐, 宋维力, 孙磊, 陈浩森, 方岱宁. 锂离子电池植入传感技术[J]. 储能科学与技术, 2022, 11(6): 1834-1846.