基于AED-CEEMD-Transformer的锂离子电池健康状态估计

doi:10.19799/j.cnki.2095-4239.2023.0440

摘要/Abstract

摘要：

锂电池健康状态(state of health，SOH)的精确预测评估对电池设备安全稳定运行极为重要，通过对SOH的快速准确预测，可以提高电池设备的安全性并降低出现故障的风险。针对难以精确预测锂离子电池SOH的问题，本文采用电池容量作为SOH的指标，提出一种利用平均欧几里得距离(average euclidean distance，AED)和互补集合经验模态分解(complementary ensemble empirical mode decomposition，CEEMD)方法建立基于Transformer网络结构的锂离子电池健康状态估计算法。首先，我们利用AED评估电池数据库中的电池与待预测电池初期循环容量之间的相似度，并选出具有相似容量退化趋势的电池作为训练集以提高模型的训练速度，然后利用CEEMD方法将电池容量曲线分解为容量再生部分以及退化趋势部分，将各个分量分别使用Transformer网络来建立锂电池退化模型，进而得到锂离子电池的SOH预测结果。本文使用分别来自斯坦福大学与马里兰大学的两个具有不同充放电策略与不同测试环境下的锂离子电池数据集来验证了所提出的电池预测算法的准确性。本文所提模型的均方根误差均能控制在4%以内，具有较好的精确性，并通过与基于LSTM、RNN、GRU的常用锂离子电池健康状态估计算法结果的比较，验证了所提出估计方法的优越性。

关键词: 锂离子电池, Transformer网络, 电池健康状态, 平均欧几里得距离, 联合互补集合经验模态分解

Abstract:

The accurate prediction and assessment of the state of health (SOH) of lithium-ion batteries are extremely important for the safe and stable operation of the battery equipment. Quickly and accurately predicting the SOH can enhance the safety of battery devices and reduce the failure risk. This study proposes an algorithm for estimating the health status of lithium-ion batteries based on the transformer network structure to address the challenge of accurately predicting their SOH. This algorithm utilizes the battery capacity as the SOH indicator, incorporating the average Euclidean distance (AED) and complementary ensemble empirical mode decomposition (CEEMD) methods. First, the AED is used to assess the similarity between the initial cycle capacities of the batteries in the battery database and the battery to be predicted. The batteries in the battery database with similar capacity degradation trends are selected as the training set for improving the model's training speed. The CEEMD method is then employed to decompose the battery capacity curve into the capacity regeneration and degradation trend parts. The degradation models for the lithium-ion batteries are separately established using the transformer network for each component. As a result, the predictions for the SOH of lithium-ion batteries are obtained. This study validates the accuracy of the proposed battery prediction algorithm using two lithium-ion battery datasets from Stanford University and the University of Maryland. These datasets comprise batteries tested under different charge-discharge strategies and testing environments. The root mean square error of the proposed model can be controlled within 4%, demonstrating its high accuracy level. The superiority of the proposed estimation method is validated by comparing it with the commonly used lithium-ion battery health estimation algorithms based on the long short-term memory, recurrent neural network, and gated recurrent unit.

Key words: lithium-ion battery, transformer network, state of health, average euclidean distance, complementary ensemble empirical mode decomposition

中图分类号:

TM 911

陈锐, 丁凯, 祖连兴, 许青松, 王宗标, 罗大思, 苏敬江, 胡圣, 毛冀龙. 基于AED-CEEMD-Transformer的锂离子电池健康状态估计[J]. 储能科学与技术, 2023, 12(10): 3242-3253.

Rui CHEN, Kai DING, Lianxing ZU, Qingsong XU, Zongbiao WANG, Dasi LUO, Jingjiang SU, Sheng HU, Jilong MAO. Prediction of state of health of lithium-ion batteries based on the AED-CEEMD-Transformer network[J]. Energy Storage Science and Technology, 2023, 12(10): 3242-3253.

图/表 8

图 1

图 2

图3

图4

图5

表1

图6

表2

参考文献 25

1	LU J H, XIONG R, TIAN J P, et al. Battery degradation prediction against uncertain future conditions with recurrent neural network enabled deep learning[J]. Energy Storage Materials, 2022, 50: 139-151.
2	胡振恺, 雷博, 李勇琦, 等. 储能用锂离子电池安全性测试与评估方法比较[J]. 储能科学与技术, 2022, 11(5): 1650-1656.
	HU Z K, LEI B, LI Y Q, et al. Comparative study on safety test and evaluation methods of lithium-ion batteries for energy storage[J]. Energy Storage Science and Technology, 2022, 11(5): 1650-1656.
3	戴俊彦, 夏明超, 陈奇芳. 基于双重注意力机制的电池SOH估计和RUL预测编解码模型[J]. 电力系统自动化, 2023, 47(6): 168-177.
	DAI J Y, XIA M C, CHEN Q F. Encoding and decoding model of state of health estimation and remaining useful life prediction for batteries based on dual-stage attention mechanism[J]. Automation of Electric Power Systems, 2023, 47(6): 168-177.
4	SHEN S Q, LIU B C, ZHANG K, et al. Toward fast and accurate SOH prediction for lithium-ion batteries[J]. IEEE Transactions on Energy Conversion, 2021, 36(3): 2036-2046.
5	徐乐, 邓忠伟, 谢翌, 等. 锂离子电池高精度机理建模、参数辨识与寿命预测研究进展[J]. 机械工程学报, 2022, 58(22): 19-36.
	XU L, DENG Z W, XIE Y, et al. Review on research progress in high-fidelity modeling, parameter identification and lifetime prognostics of lithium-ion battery[J]. Journal of Mechanical Engineering, 2022, 58(22): 19-36.
6	王瑞洁, 惠周利, 杨明. 基于间接健康指标的高斯过程回归对锂电池SOH预测[J]. 储能科学与技术, 2023, 12(2): 560-569.
	WANG R J, HUI Z L, YANG M. Gaussian process regression based on indirect health indicators for SOH estimation of lithium battery[J]. Energy Storage Science and Technology, 2023, 12(2): 560-569.
7	MA G J, XU S P, YANG T, et al. A transfer learning-based method for personalized state of health estimation of lithium-ion batteries[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, PP(99): 1-11.
8	舒星, 刘永刚, 申江卫, 等. 基于改进最小二乘支持向量机与Box-Cox变换的锂离子电池容量预测[J]. 机械工程学报, 2021, 57(14): 118-128.
	SHU X, LIU Y G, SHEN J W, et al. Capacity prediction for lithium-ion batteries based on improved least squares support vector machine and box-cox transformation[J]. Journal of Mechanical Engineering, 2021, 57(14): 118-128.
9	何冰琛, 杨薛明, 王劲松, 等. 基于PCA-GPR的锂离子电池剩余使用寿命预测[J]. 太阳能学报, 2022, 43(5): 484-491.
	HE B C, YANG X M, WANG J S, et al. Prediction of remaining useful life of lithium-ion batteries based on pca-gpr[J]. Acta Energiae Solaris Sinica, 2022, 43(5): 484-491.
10	郑伟彦, 吴靖, 许杰, 等. 基于RVM-PF融合算法的锂离子电池剩余使用寿命预测[J]. 浙江电力, 2021, 40(4): 54-64.
	ZHENG W Y, WU J, XU J, et al. Prediction of remaining useful life of lithium-ion battery based on RVM-PF algorithm[J]. Zhejiang Electric Power, 2021, 40(4): 54-64.
11	TIAN J P, XIONG R, SHEN W X, et al. Deep neural network battery charging curve prediction using 30 points collected in 10 Min[J]. Joule, 2021, 5(6): 1521-1534.
12	梁海峰, 袁芃, 高亚静. 基于CNN-Bi-LSTM网络的锂离子电池剩余使用寿命预测[J]. 电力自动化设备, 2021, 41(10): 213-219.
	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.
13	PHAM T, LE T, DANG D, et al. ARNS: A data-driven approach for SoH estimation of lithium-ion battery using nested sequence models with considering relaxation effect[J]. IEEE Access, 2022, 10: 117067-117083.
14	王朋凯, 张新燕, 张光昊. 基于ResNet-Bi-LSTM-Attention的锂离子电池剩余使用寿命预测[J]. 储能科学与技术, 2023, 12(4): 1215-1222.
	WANG P K, ZHANG X Y, ZHANG G H. Remaining useful life prediction of lithium-ion batteries based on ResNet-Bi-LSTM-Attention model[J]. Energy Storage Science and Technology, 2023, 12(4): 1215-1222.
15	VASWANI A, SHAZEER N, PARMAR N, et al. Attention Is All You Need[M]. arXiv, 2017.
16	刘芊彤, 邢远秀. 基于VMD-PSO-GRU模型的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2023, 12(1): 236-246.
	LIU Q T, XING Y X. Remaining life prediction of lithium-ion battery based on VMD-PSO-GRU model[J]. Energy Storage Science and Technology, 2023, 12(1): 236-246.
17	肖浩逸, 何晓霞, 梁佳佳, 等. 一种基于模态分解和机器学习的锂电池寿命预测方法[J]. 储能科学与技术, 2022, 11(12): 3999-4009.
	XIAO H Y, HE X X, LIANG J J, et al. A lithium battery life-prediction method based on mode decomposition and machine learning[J]. Energy Storage Science and Technology, 2022, 11(12): 3999-4009.
18	郑雪莹, 邓晓刚, 曹玉苹. 基于能量加权高斯过程回归的锂离子电池健康状态预测[J]. 电子测量与仪器学报, 2020, 34(6): 63-69.
	ZHENG X Y, DENG X G, CAO Y P. State of health prediction of lithium-ion batteries based on energy-weighted Gaussian process regression[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(6): 63-69.
19	陈彦余, 夏向阳, 周文钊, 等. 基于EMD-ARMA的锂离子电池剩余寿命预测[J]. 电力学报, 2021, 36(1): 43-50, 59.
	CHEN Y Y, XIA X Y, ZHOU W Z, et al. Prediction of the lithium-ion battery remaining useful life based on EMD-ARMA[J]. Journal of Electric Power, 2021, 36(1): 43-50, 59.
20	欧阳名三, 屈琪. 基于SAE-EEMD-GRU的锂离子电池剩余使用寿命预测[J]. 佳木斯大学学报(自然科学版), 2022, 40(2): 43-49.
	MINGSAN O Y, QI Q. Remaining useful life prediction of lithium-ion batteries based on SAE-EEMD-GRU[J]. Journal of Jiamusi University (Natural Science Edition), 2022, 40(2): 43-49.
21	HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995.
22	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). May 22-27, 2011, Prague, Czech Republic. IEEE, 2011: 4144-4147.
23	CONG X W, ZHANG C P, JIANG J C, et al. A hybrid method for the prediction of the remaining useful life of lithium-ion batteries with accelerated capacity degradation[J]. IEEE Transactions on Vehicular Technology, 2020, 69(11): 12775-12785.
24	SEVERSON K A, ATTIA P M, JIN N, et al. Data-driven prediction of battery cycle life before capacity degradation[J]. Nature Energy, 2019, 4(5): 383-391.
25	黄凯, 丁恒, 郭永芳, 等. 基于数据预处理和长短期记忆神经网络的锂离子电池寿命预测[J]. 电工技术学报, 2022, 37(15): 3753-3766.
	HUANG K, DING H, GUO Y F, et al. Prediction of remaining useful life of lithium-ion battery based on adaptive data preprocessing and long short-term memory network[J]. Transactions of China Electrotechnical Society, 2022, 37(15): 3753-3766.

电池	误差	前30%训练集				前50%训练集				前70%训练集
电池	误差	OURS	LSTM	RNN	GRU	OURS	LSTM	RNN	GRU	OURS	LSTM	RNN	GRU
A0	RMSE	0.04599	0.04981	0.05130	0.05337	0.04753	0.05160	0.05322	0.05334	0.04857	0.05027	0.05059	0.05109
A0	MAPE	0.03332	0.03533	0.03715	0.03857	0.03457	0.03798	0.03993	0.04000	0.03842	0.04049	0.04076	0.04106
A1	RMSE	0.05217	0.05672	0.06219	0.06051	0.05467	0.05906	0.06120	0.06363	0.04996	0.05406	0.05551	0.05541
A1	MAPE	0.03859	0.04137	0.04570	0.04429	0.04155	0.04562	0.04742	0.04928	0.04073	0.04444	0.04561	0.04542
B0	RMSE	0.04896	0.05504	0.05836	0.05666	0.04810	0.05150	0.05475	0.05305	0.04934	0.05091	0.05258	0.05206
B0	MAPE	0.03738	0.04130	0.04390	0.04240	0.03744	0.04056	0.04292	0.04162	0.04006	0.04188	0.04319	0.04277
B1	RMSE	0.04890	0.05444	0.05632	0.05516	0.05159	0.05661	0.05782	0.05914	0.04536	0.04943	0.05149	0.05171
B1	MAPE	0.03676	0.03983	0.04254	0.04176	0.04010	0.04385	0.04506	0.04612	0.03828	0.04139	0.04273	0.04293
C1	RMSE	0.03968	0.04459	0.04657	0.04710	0.04254	0.04748	0.04901	0.04779	0.04229	0.04742	0.04841	0.04808
C1	MAPE	0.02872	0.03214	0.03331	0.03356	0.03111	0.03482	0.03605	0.03495	0.03308	0.03749	0.03813	0.03783
C2	RMSE	0.04011	0.04501	0.04707	0.04869	0.04270	0.04785	0.05026	0.04898	0.04509	0.04823	0.04889	0.04996
C2	MAPE	0.02793	0.03223	0.03306	0.03414	0.03043	0.03385	0.03680	0.03554	0.03572	0.03804	0.03870	0.03963

电池	误差	前30%训练集				前50%训练集				前70%训练集
电池	误差	OURS	LSTM	RNN	GRU	OURS	LSTM	RNN	GRU	OURS	LSTM	RNN	GRU
CS1	RMSE	0.03637	0.03937	0.03988	0.03986	0.03687	0.03802	0.03882	0.03882	0.03280	0.03324	0.03313	0.03335
CS1	MAPE	0.08005	0.08188	0.08320	0.08314	0.08857	0.09069	0.09296	0.09296	0.09761	0.09977	0.09950	0.10023
CS2	RMSE	0.01584	0.01811	0.01829	0.01863	0.01451	0.01635	0.01653	0.01657	0.01060	0.01127	0.01154	0.01175
CS2	MAPE	0.01573	0.01740	0.01763	0.01789	0.01495	0.01672	0.01691	0.01695	0.01184	0.01260	0.01288	0.01307
CS3	RMSE	0.02656	0.02884	0.02905	0.02925	0.02614	0.02770	0.02819	0.02824	0.02146	0.02175	0.02189	0.02190
CS3	MAPE	0.03453	0.03639	0.03655	0.03673	0.03829	0.03861	0.03915	0.03923	0.03468	0.03540	0.03558	0.03562
CS4	RMSE	0.03259	0.03470	0.03536	0.03528	0.03030	0.03184	0.03234	0.03231	0.02546	0.02592	0.02613	0.02598
CS4	MAPE	0.05495	0.05670	0.05776	0.05766	0.05607	0.05884	0.05978	0.05966	0.05538	0.05671	0.05760	0.05709
CS5	RMSE	0.02647	0.02843	0.02885	0.02835	0.02637	0.02775	0.02794	0.02787	0.02377	0.02405	0.02422	0.02423
CS5	MAPE	0.03604	0.03743	0.03779	0.03736	0.04016	0.04059	0.04079	0.04066	0.04107	0.04120	0.04143	0.04144
CS 6	RMSE	0.02543	0.02787	0.02837	0.02833	0.02609	0.02752	0.02768	0.02772	0.02339	0.02353	0.02369	0.02366
CS 6	MAPE	0.03324	0.03491	0.03530	0.03525	0.03779	0.03802	0.03815	0.03819	0.03744	0.03762	0.03784	0.03777

[1]	李悦, 王博, 吴楠. 石墨烯/Si/SiO _x 纳米复合材料的制备及储锂性能研究[J]. 储能科学与技术, 2023, 12(9): 2752-2759.
[2]	曾少鸿, 吴伟雄, 刘吉臻, 汪双凤, 叶石丰, 冯振宇. 锂离子电池浸没式冷却技术研究综述[J]. 储能科学与技术, 2023, 12(9): 2888-2903.
[3]	李纪伟, 刘睿涵, 吕桃林, 潘隆, 马常军, 李清波, 赵芝芸, 杨文, 解晶莹. 基于局部离群点检测和标准差方法的锂离子电池组早期故障诊断[J]. 储能科学与技术, 2023, 12(9): 2917-2926.
[4]	黄晓伟, 李少鹏, 张校刚. 负极补锂锂化裕度对电芯性能的影响及机理研究[J]. 储能科学与技术, 2023, 12(9): 2727-2734.
[5]	陈欣, 李云伍, 梁新成, 李法霖, 张志冬. 基于模态分解的Transformer-GRU联合电池健康状态估计[J]. 储能科学与技术, 2023, 12(9): 2927-2936.
[6]	江婉薇, 梁呈景, 钱历, 刘梅城, 朱孟想, 马骏. 锡基三维石墨烯泡沫调控及其锂电池负极性能[J]. 储能科学与技术, 2023, 12(9): 2746-2751.
[7]	高欣, 王若谷, 高文菁, 邓泽军, 梁睿祺, 杨騉. 基于运行数据的储能电站电池组一致性评估方法[J]. 储能科学与技术, 2023, 12(9): 2937-2945.
[8]	周向阳, 胡颖杰, 梁家浩, 周其杰, 文康, 陈松, 杨娟, 唐晶晶. 天然鳞片石墨球化尾料的高性能负极材料制备及储锂特性研究[J]. 储能科学与技术, 2023, 12(9): 2767-2777.
[9]	官亦标, 沈进冉, 刘家亮, 渠展展, 高飞, 刘施阳, 郭翠静, 周淑琴, 付珊珊. 以安全高质量应用为导向的储能锂离子电池综合性能评价标准[J]. 储能科学与技术, 2023, 12(9): 2946-2953.
[10]	左安昊, 方儒卿, 李哲. 锂离子电池单颗粒动力学表征方法综述[J]. 储能科学与技术, 2023, 12(8): 2457-2481.
[11]	陈满, 程志翔, 赵春朋, 彭鹏, 雷旗开, 金凯强, 王青松. 锂离子电池储能集装箱爆炸危害数值模拟[J]. 储能科学与技术, 2023, 12(8): 2594-2605.
[12]	黄永浩, 臧国景, 朱霨亚, 廖友好, 李伟善. LiF添加剂改善含锂陶瓷隔膜与4.35 V LiNi_0.8Co_0.1Mn_0.1O₂ 正极的界面稳定性[J]. 储能科学与技术, 2023, 12(8): 2361-2369.
[13]	杨佳兴, 张恒运, 徐屹东. 基于电化学-热耦合模型的锂离子电池组件产热分析[J]. 储能科学与技术, 2023, 12(8): 2615-2625.
[14]	张吉禄, 董育辰, 宋强, 袁思鸣, 郭孝东. 多晶及单晶高镍三元材料LiNi_0.9Co_0.05Mn_0.05O₂ 的可控制备及其电化学储锂特性[J]. 储能科学与技术, 2023, 12(8): 2382-2389.
[15]	郭煜, 王亦伟, 钟隽, 杜进桥, 田杰, 李艳, 蒋方明. 基于增量容量曲线的锂离子电池微内短路故障诊断方法[J]. 储能科学与技术, 2023, 12(8): 2536-2546.