融合多项式特征扩展与CNN-Transformer模型的锂电池SOH估计

doi:10.19799/j.cnki.2095-4239.2024.0465

摘要/Abstract

摘要：

为了提高锂离子电池健康状态(state of health，SOH)估计的精确度，本研究结合卷积神经网络(convolutional neural networks，CNN)强大的局部特征提取能力和Transformer的序列处理能力，提出了基于多项式特征扩展的CNN-Transformer融合模型。该方法提取了与电池容量高度相关的增量容量(incremental capacity，IC)曲线峰值、IC曲线对应电压、面积及充电时间作为健康因子，然后将其进行多项式扩展，增加融合模型对输入特征的非线性处理能力。引入主成分分析法(principal component analysis，PCA)对特征空间进行降维，有利于捕获数据有效信息，减少模型训练时间。采用美国国家宇航局(National Aeronautics and Space Administration，NASA)数据集和马里兰大学数据集，通过加入多项式特征前后的CNN-Transformer模型对比、加入多项式特征的CNN-Transformer模型和单一模型算法对比，验证了加入多项式特征的CNN-Transformer融合算法的有效性和精确度，结果表明提出模型的SOH估计精度相较于未加入多项式特征的CNN-Transformer模型，对于B0005、B0006、B0007、B0018数据集分别提高了38.71%、50.28%、4.71%、17.58%。

关键词: 锂离子电池, 电池健康状态预测, 主成分分析法, CNN-Transformer, 增量容量分析, 多项式特征

Abstract:

To enhance the accuracy of state-of-health (SOH) estimation for lithium-ion batteries, this study proposes a convolutional neural network (CNN)-transformer fusion model based on polynomial feature expansion. The model leverages the powerful local feature extraction capability of CNNs and the sequence processing ability of transformers. Key health factors, highly correlated with battery capacity, such as peak values of incremental capacity curves, corresponding voltages, areas, and charging time, were extracted and expanded using polynomial features. This expansion enhances the model's ability to handle nonlinearities in the input features. Principal component analysis was employed to reduce the dimensionality of the feature space, which aided in capturing adequate data information and reduced training time. The effectiveness and accuracy of the proposed fusion algorithm were validated using open-source datasets from the National Aeronautics and Space Administration (NASA) and the University of Maryland. Comparative analyses of SOH estimation were conducted for the CNN-transformer model with and without polynomial features and for single-model algorithms. The results indicate that the SOH estimation accuracy of the proposed model, compared to the CNN-transformer model without polynomial features, improved by 38.71%, 50.28%, 4.71%, and 17.58% for datasets B0005, B0006, B0007, and B0018, respectively.

Key words: lithium-ion battery, battery state of health prediction, principal component analysis, CNN-Transformer, incremental capacity analysis, polynomial features

中图分类号:

TM 912

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.

Yuan CHEN, Siyuan ZHANG, Yujing CAI, Xiaohe HUANG, Yanzhong LIU. State-of-health estimation of lithium batteries based on polynomial feature extension of the CNN-transformer model[J]. Energy Storage Science and Technology, 2024, 13(9): 2995-3005.

图/表 11

图1

图2

图3

图4

图5

表1

图6

表2

图7

表3

表4

参考文献 34

1	TIAN X, GENG Y, SARKIS J, et al. Features of critical resource trade networks of lithium-ion batteries[J]. Resources Policy, 2021, 73: 102177. DOI: 10.1016/j.resourpol.2021.102177.
2	RAUF H, KHALID M, ARSHAD N. Machine learning in state of health and remaining useful life estimation: Theoretical and technological development in battery degradation modelling[J]. Renewable and Sustainable Energy Reviews, 2022, 156: 111903. DOI: 10.1016/j.rser.2021.111903.
3	JIANG K, LIU X L, LOU G F, et al. Parameter sensitivity analysis and cathode structure optimization of a non-aqueous Li-O₂ battery model[J]. Journal of Power Sources, 2020, 451: 227821. DOI: 10.1016/j.jpowsour.2020.227821.
4	JIANG S D, SONG Z X. A review on the state of health estimation methods of lead-acid batteries[J]. Journal of Power Sources, 2022, 517: 230710. DOI: 10.1016/j.jpowsour.2021.230710.
5	HOSSAIN LIPU M S, ANSARI S, MIAH M S, et al. Deep learning enabled state of charge, state of health and remaining useful life estimation for smart battery management system: Methods, implementations, issues and prospects[J]. Journal of Energy Storage, 2022, 55: 105752. DOI: 10.1016/j.est.2022.105752.
6	YANG S J, ZHANG C P, JIANG J C, et al. Review on state-of-health of lithium-ion batteries: Characterizations, estimations and applications[J]. Journal of Cleaner Production, 2021, 314: 128015. DOI: 10.1016/j.jclepro.2021.128015.
7	XIONG R, KIM J, SHEN W X, et al. Key technologies for electric vehicles[J]. Green Energy and Intelligent Transportation, 2022, 1(2): 100041. DOI: 10.1016/j.geits.2022.100041.
8	ZHAO J, ZHU Y, ZHANG B, et al. Review of state estimation and remaining useful life prediction methods for lithium–ion batteries[J]. Sustainability, 2023, 15(6): 5014.
9	TIAN H X, QIN P L, LI K, et al. A review of the state of health for lithium-ion batteries: Research status and suggestions[J]. Journal of Cleaner Production, 2020, 261: 120813. DOI: 10.1016/j.jclepro.2020.120813.
10	顾菊平, 蒋凌, 张新松, 等. 基于特征提取的锂离子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.
11	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. DOI: 10.1016/j.apenergy.2021.117346.
12	TRAN M K, MATHEW M, JANHUNEN S, et al. A comprehensive equivalent circuit model for lithium-ion batteries, incorporating the effects of state of health, state of charge, and temperature on model parameters[J]. Journal of Energy Storage, 2021, 43: 103252. DOI: 10.1016/j.est.2021.103252.
13	陈媛,段文献,何怡刚,等.带降噪自编码器的锂离子电池健康状态估计算法[J/OL].电工技术学报,1-17[2024-05-24].https://doi.org/10.19595/j.cnki.1000-6753.tces.231644.
	CHEN Y,DUAN W X,HE Y G, et al. Predicting the state of charge and health of batteries using data-driven machine learning[J/OL]. Nature Machine Intelligence,1-17[2024-05-24].https://doi.org/10.19595/j.cnki.1000-6753.tces.231644.
14	ZHANG M, YANG D F, DU J X, et al. A review of SOH prediction of Li-ion batteries based on data-driven algorithms[J]. Energies, 2023, 16(7): 3167. DOI: 10.3390/en16073167.
15	REN Z, DU C Q. A review of machine learning state-of-charge and state-of-health estimation algorithms for lithium-ion batteries[J]. Energy Reports, 2023, 9: 2993-3021. DOI: 10.1016/j.egyr.2023.01.108.
16	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.
17	VAN C N, QUANG D T. Estimation of SoH and internal resistances of lithium ion battery based on LSTM network[J]. International Journal of Electrochemical Science, 2023, 18(6): 100166. DOI: 10.1016/j.ijoes.2023.100166.
18	FAN Y X, XIAO F, LI C R, et al. A novel deep learning framework for state of health estimation of lithium-ion battery[J]. Journal of Energy Storage, 2020, 32: 101741. DOI: 10.1016/j.est. 2020.101741.
19	SUN S, LIN Q B, LI H S, et al. Simultaneous estimation of SOH and SOC of batteries based on SVM[C]//2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES). December 9-12, 2022, Beijing, China. IEEE, 2022: 1934-1938. DOI: 10.1109/SPIES55999.2022.10082477.
20	XIAO S, LIU P Y, CHEN K, et al. Battery state of health prediction based on voltage intervals, BP neural network and genetic algorithm[J]. International Journal of Green Energy, 2024, 21(8): 1743-1756. DOI: 10.1080/15435075.2023.2264959.
21	WEN L, BO N, YE X C, et al. A novel auto-LSTM-based state of health estimation method for lithium-ion batteries[J]. Journal of Electrochemical Energy Conversion and Storage, 2021, 18(3): 030902. DOI: 10.1115/1.4050100.
22	JIA C Y, TIAN Y K, SHI Y H, et al. State of health prediction of lithium-ion batteries based on bidirectional gated recurrent unit and transformer[J]. Energy, 2023, 285: 129401. DOI: 10.1016/j.energy.2023.129401.
23	ZHANG Q C, LI X, ZHOU C, et al. State-of-health estimation of batteries in an energy storage system based on the actual operating parameters[J]. Journal of Power Sources, 2021, 506: 230162. DOI: 10.1016/j.jpowsour.2021.230162.
24	BIAN X L, WEI Z B, LI W H, et al. State-of-health estimation of lithium-ion batteries by fusing an open circuit voltage model and incremental capacity analysis[J]. IEEE Transactions on Power Electronics, 2022, 37(2): 2226-2236. DOI: 10.1109/TPEL. 2021.3104723.
25	GISMERO A, NØRREGAARD K, JOHNSEN B, et al. Electric vehicle battery state of health estimation using Incremental Capacity Analysis[J]. Journal of Energy Storage, 2023, 64: 107110. DOI: 10.1016/j.est.2023.107110.
26	WANG Q S, WANG Z P, ZHANG L, et al. A battery capacity estimation framework combining hybrid deep neural network and regional capacity calculation based on real-world operating data[J]. IEEE Transactions on Industrial Electronics, 2023, 70(8): 8499-8508. DOI: 10.1109/TIE.2022.3229350.
27	JENU S, HENTUNEN A, HAAVISTO J, et al. State of health estimation of cycle aged large format lithium-ion cells based on partial charging[J]. Journal of Energy Storage, 2022, 46: 103855. DOI: 10.1016/j.est.2021.103855.
28	ZHANG Q C, LI X Z, DU Z C, et al. Aging performance characterization and state-of-health assessment of retired lithium-ion battery modules[J]. Journal of Energy Storage, 2021, 40: 102743. DOI: 10.1016/j.est.2021.102743.
29	CHEN K, LI J L, LIU K, et al. State of health estimation for lithium-ion battery based on particle swarm optimization algorithm and extreme learning machine[J]. Green Energy and Intelligent Transportation, 2024, 3(1): 100151. DOI: 10.1016/j.geits. 2024.100151.
30	SUN H L, SUN J R, ZHAO K, et al. Data-driven ICA-Bi-LSTM-combined lithium battery SOH estimation[J]. Mathematical Problems in Engineering, 2022, 2022: 9645892. DOI: 10.1155/2022/9645892.
31	SHE C Q, ZHANG L, WANG Z P, et al. Battery state-of-health estimation based on incremental capacity analysis method: Synthesizing from cell-level test to real-world application[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2023, 11(1): 214-223. DOI: 10.1109/JESTPE.2021.3112754.
32	TIAN J P, XIONG R, SHEN W X. State-of-health estimation based on differential temperature for lithium ion batteries[J]. IEEE Transactions on Power Electronics, 2020, 35(10): 10363-10373. DOI: 10.1109/TPEL.2020.2978493.
33	PARK S, LEE P, KIM D, et al. A SOH estimation method based on ICA peaks on temperature-robust and aging mechanism analysis under high temperature[C]//2021 IEEE Applied Power Electronics Conference and Exposition (APEC). June 14-17, 2021, Phoenix, AZ, USA. IEEE, 2021: 2646-2649. DOI: 10.1109/APEC42165.2021.9487032.
34	HOU X K, GUO X D, YUAN Y P, et al. The state of health prediction of Li-ion batteries based on an improved extreme learning machine[J]. Journal of Energy Storage, 2023, 70: 108044. DOI: 10.1016/j.est.2023.108044.

Method	B0005			B0006			B0007			B0018
Method	MAE	MAPE	RMSE	MAE	MAPE	RMSE	MAE	MAPE	RMSE	MAE	MAPE	RMSE
Poly-CNN-Transformer	0.00711	0.00535	0.00015	0.00796	0.00648	0.00011	0.0081	0.0056	0.0001	0.0075	0.0056	0.0001
CNN-Transformer	0.01160	0.00875	0.00021	0.01601	0.01294	0.00040	0.0085	0.0059	0.0001	0.0091	0.0068	0.0002

Method	B0005			B0006			B0007			B0018
Method	MAE	MAPE	RMSE	MAE	MAPE	RMSE	MAE	MAPE	RMSE	MAE	MAPE	RMSE
Poly-CNN-Transformer	0.0071	0.0053	0.0001	0.0079	0.0064	0.0001	0.0081	0.0056	0.0001	0.0075	0.0056	0.0001
Poly-Transformer	0.0072	0.0054	0.0001	0.0114	0.0093	0.0002	0.0136	0.0087	0.0005	0.0085	0.0064	0.0001
Poly-LSTM	0.0141	0.0160	0.0003	0.0100	0.0081	0.0001	0.0141	0.0093	0.0005	0.0090	0.0063	0.0001

Method	MAE	MAPE	RMSE
Poly-CNN-Transformer	0.01275	0.05605	0.00050
Poly-Transformer	0.01819	0.08535	0.00122
Poly-LSTM	0.01478	0.06916	0.00066
CNN-Transformer	0.01325	0.06539	0.00057

项目	CNN-Transformer	Transformer	LSTM
参数量/个	102	69	124
估算一次时间/ms	0.0276	0.0243	0.0124

[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]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[12]	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.
[13]	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.
[14]	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.
[15]	雷晶晶, 李泽皓, 陈斌斌, 黄登高. 基于电化学阻抗谱的电芯内部温度估计研究[J]. 储能科学与技术, 2024, 13(8): 2823-2834.