Remaining useful life prediction of lithium-ion batteries based on the DESSA-DESN model and the NCA algorithm

doi:10.19799/j.cnki.2095-4239.2023.0398

Abstract

Abstract:

The remaining useful life (RUL) of lithium-ion batteries is crucial in managing and using energy storage devices. To improve the prediction accuracy, this study proposes a RUL prediction method based on improved deep echo state network (DESN) and neighborhood component analysis (NCA), in which the DESN is optimized by a hybrid differential evolution (DE)-sparrow search algorithm (SSA). First, various health indicators (HIs) are selected to describe the battery aging mechanism by analyzing the capacity decay characteristics of lithium-ion batteries. The NCA is used to reduce the HI dimensionality. Four high-correlation health factors are then obtained as the model input. Next, the DE algorithm (DE) and the SSA are combined to construct the DESSA algorithm, which is used to optimize the DESN network parameters. As a result, the DESSA-DESN prediction model is established. Finally, the validity and the generalization performance of the proposed model are verified using datasets from the National Aeronautics and Space Administration and the Center for Advanced Life Cycle Engineering. The results show that, compared with existing methods (e.g., SSA-DESN and ground penetrating radar), the proposed method more accurately tracks the degradation state of lithium-ion batteries with smaller prediction errors. The root-mean-squared error of the prediction results remains within 1.5%, while the mean absolute error remains within 1%.

Key words: lithium ion batteries, remaining useful life, domain component analysis, deep echo state network, hybrid differential evolution-sparrow search algorithm

CLC Number:

TM 912

Lianbing LI, Le ZHU, Ruixiong JING, Lanchao WANG, Qiqi HAN. Remaining useful life prediction of lithium-ion batteries based on the DESSA-DESN model and the NCA algorithm[J]. Energy Storage Science and Technology, 2023, 12(10): 3191-3202.

Figures/Tables 16

Table 1

Fig. 1

Fig. 2

Fig. 3

Table 2

Table 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Table 4

Fig. 8

Table 5

Fig. 9

Table 6

Table 7

References 35

1	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.
2	LI A, WEST A C, PREINDL M. Towards unified machine learning characterization of lithium-ion battery degradation across multiple levels: A critical review[J]. Applied Energy, 2022, 316: 119030.
3	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.
4	崔树辉, 周贺, 黄振兴, 等. 动力电池梯次利用关键技术与应用综述[J]. 广东电力, 2023, 36(1): 9-19.
	CUI S H, ZHOU H, HUANG Z X, et al. Review of key technologies and applications of echelon utilization of power batteries[J]. Guangdong Electric Power, 2023, 36(1): 9-19.
5	金鑫, 王凯. 平滑新能源波动的混合储能优化配置[J]. 广东电力, 2021, 34(8): 80-85.
	JIN X, WANG K. Optimal allocation of hybrid energy storage to smooth fluctuation of new energy[J]. Guangdong Electric Power, 2021, 34(8): 80-85.
6	XU P H, HU X Y, LIU B L, et al. Hierarchical estimation model of state-of-charge and state-of-health for power batteries considering current rate[J]. IEEE Transactions on Industrial Informatics, 2022, 18(9): 6150-6159.
7	YANG K, CHEN Z W, HE Z J, et al. Online estimation of state of health for the airborne Li-ion battery using adaptive DEKF-based fuzzy inference system[J]. Soft Computing, 2020, 24(24): 18661-18670.
8	ZHANG J S, JIANG Y C, LI X, et al. Remaining useful life prediction of lithium-ion battery with adaptive noise estimation and capacity regeneration detection[J]. IEEE/ASME Transactions on Mechatronics, 2023, 28(2): 632-643.
9	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.
10	MA Y, YAO M H, LIU H C, et al. State of Health estimation and remaining useful life prediction for lithium-ion batteries by improved particle swarm optimization-back propagation neural network[J]. Journal of Energy Storage, 2022, 52: 104750.
11	李强龙, 孙建瑞, 赵坤, 等. 基于IALO-SVR的锂电池健康状态预测[J]. 电子测量与仪器学报, 2022, 36(1): 204-211.
	LI Q L, SUN J R, ZHAO K, et al. Prediction for the state of health of lithium-ion batteries based on IALO-SVR[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(1): 204-211.
12	LI P H, ZHANG Z J, GROSU R, et al. An end-to-end neural network framework for state-of-health estimation and remaining useful life prediction of electric vehicle lithium batteries[J]. Renewable and Sustainable Energy Reviews, 2022, 156: 111843.
13	LIN M Q, ZENG X P, WU J. State of health estimation of lithium-ion battery based on an adaptive tunable hybrid radial basis function network[J]. Journal of Power Sources, 2021, 504: 230063.
14	WU C L, FU J C, HUANG X R, et al. Lithium-ion battery health state prediction based on VMD and DBO-SVR[J]. Energies, 2023, 16(10): 3993.
15	CATELANI M, CIANI L, FANTACCI R, et al. Remaining useful life estimation for prognostics of lithium-ion batteries based on recurrent neural network[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-11.
16	CHE Y H, HU X S, LIN X K, et al. Health prognostics for lithium-ion batteries: Mechanisms, methods, and prospects[J]. Energy & Environmental Science, 2023, 16(2): 338-371.
17	LI W H, SENGUPTA N, DECHENT P, et al. Online capacity estimation of lithium-ion batteries with deep long short-term memory networks[J]. Journal of Power Sources, 2021, 482: 228863.
18	FENG H L, SONG D D. A health indicator extraction based on surface temperature for lithium-ion batteries remaining useful life prediction[J]. Journal of Energy Storage, 2021, 34: 102118.
19	FAN Y C, QIU J S, WANG S L, et al. Incremental capacity curve health-indicator extraction based on Gaussian filter and improved relevance vector machine for lithium-ion battery remaining useful life estimation[J]. Metals, 2022, 12(8): 1331.
20	XIA F, WANG K G, CHEN J J. State of health and remaining useful life prediction of lithium-ion batteries based on a disturbance-free incremental capacity and differential voltage analysis method[J]. Journal of Energy Storage, 2023, 64: 107161.
21	HU X S, XU L, LIN X K, et al. Battery lifetime prognostics[J]. Joule, 2020, 4(2): 310-346.
22	李建林, 李雅欣, 陈光, 等. 退役动力电池健康状态特征提取及评估方法综述[J]. 中国电机工程学报, 2022, 42(4): 1332-1347.
	LI J L, LI Y X, CHEN G, et al. Research on feature extraction and SOH evaluation methods for retired power battery[J]. Proceedings of the CSEE, 2022, 42(4): 1332-1347.
23	XIONG R, SUN Y, WANG C X, et al. A data-driven method for extracting aging features to accurately predict the battery health[J]. Energy Storage Materials, 2023, 57: 460-470.
24	KIM M, KIM I, KIM J, et al. Lifetime prediction of lithium ion batteries by using the heterogeneity of graphite anodes[J]. ACS Energy Letters, 2023, 8(7): 2946-2953.
25	李练兵, 李思佳, 李洁, 等. 基于差分电压和Elman神经网络的锂离子电池RUL预测方法[J]. 储能科学与技术, 2021, 10(6): 2373-2384.
	LI L B, LI S J, LI J, et al. RUL prediction of lithium-ion battery based on differential voltage and Elman neural network[J]. Energy Storage Science and Technology, 2021, 10(6): 2373-2384.
26	JAEGER H, HAAS H. Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication[J]. Science, 2004, 304(5667): 78-80.
27	刘鹏, 叶润, 闫斌, 等. 一种深度回声状态网络的输入尺度自适应算法[J]. 计算机工程, 2022, 48(2): 92-98, 105.
	LIU P, YE R, YAN B, et al. An adaptive algorithm of input scale for deep echo state networks[J]. Computer Engineering, 2022, 48(2): 92-98, 105.
28	STORN R, PRICE K. Differential evolution-A simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359.
29	张子恒, 吴定会, 杨朝辉, 等. 基于改进差分进化算法的微网容量优化配置[J]. 控制工程, 2023, 30(1): 90-97.
	ZHANG Z H, WU D H, YANG Z H, et al. Optimal allocation of microgrid capacity based on improved differential evolution algorithm[J]. Control Engineering of China, 2023, 30(1): 90-97.
30	XUE J K, SHEN B. A novel swarm intelligence optimization approach: Sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
31	冯增喜, 何鑫, 崔巍, 等. 混合随机反向学习和高斯变异的混沌松鼠搜索算法[J]. 计算机集成制造系统, 2023, 29(2): 604-615.
	FENG Z X, HE X, CUI W, et al. Chaos squirrel search algorithm based on random inverse learning and Gaussian mutation[J]. Computer Integrated Manufacturing Systems, 2023, 29(2): 604-615.
32	WANG J W, DENG Z W, YU T, et al. State of health estimation based on modified Gaussian process regression for lithium-ion batteries[J]. Journal of Energy Storage, 2022, 51: 104512.
33	FENG H L, YAN H M. State of health estimation of large-cycle lithium-ion batteries based on error compensation of autoregressive model[J]. Journal of Energy Storage, 2022, 52: 104869.
34	MA Y, SHAN C, GAO J W, et al. A novel method for state of health estimation of lithium-ion batteries based on improved LSTM and health indicators extraction[J]. Energy, 2022, 251: 123973.
35	JI Y F, CHEN Z W, SHEN Y, et al. An RUL prediction approach for lithium-ion battery based on SADE-MESN[J]. Applied Soft Computing, 2021, 104: 107195.

数据集	NASA	CALCE
电池类型	圆柱形全电池	长方体全电池
电池尺寸/mm	18×65	5.4×33.6×50.6
阳极材料	石墨	石墨
阴极材料	镍钴锰酸锂(NMC)	钴酸锂(LCO)
标称容量/Ah	2	1.1
额定电压/V	3.7	3.7
实验温度/°C	24	25

特征	特征类型	B5	B6	B7	CS2-35	CS2-36	CS2-37
Tcc	电流曲线相关	0.9924	0.9467	0.9805	0.9976	0.9982	0.9982
Tcv	电流曲线相关	-0.9012	-0.9126	-0.8872	-0.9012	-0.8756	-0.8994
Acc	电流曲线相关	0.9965	0.9945	0.9938	0.9983	0.9968	0.9976
Acv	电压曲线相关	-0.9323	-0.9042	-0.9352	-0.9428	-0.9532	-0.9656
Tdcc	电压曲线相关	-0.9343	-0.8954	-0.9015	-0.9265	-0.8662	-0.8897
Rcc	电压曲线相关	0.9938	0.9544	0.9813	0.9947	0.9926	0.9942
ICP	IC曲线相关	0.9912	0.9567	0.9675	0.9588	0.9481	0.9432
ICPL	IC曲线相关	-0.9024	-0.9349	-0.9107	-0.9718	-0.9723	-0.9705
DVPL	DV曲线相关	0.9593	0.9636	0.9415	0.9628	0.9543	0.9386
DVPLD	DV曲线相关	-0.9223	-0.9434	-0.9118	-0.9212	-0.9145	-0.9078

特征	B5	B6	B7	CS2-35	CS2-36	CS2-37
HI1	0.9882	0.9896	0.9912	0.9885	0.9851	0.9774
HI2	0.9935	0.9845	0.9981	0.9871	0.9886	0.9659
HI3	0.9891	0.9904	0.9895	0.9956	0.9969	0.9894
HI4	0.9965	0.9856	0.9962	0.9972	0.9989	0.9980

电池型号	模型	RMSE/%	MAE/%	AE/周期
B5	DESN	3.691	2.988	5
	DE-DESN	2.541	1.931	3
	SSA-DESN DESSA-DESN	1.983 0.914	1.542 0.783	1 0
B6	DESN	4.471	3.664	3
	DE-DESN	3.565	2.731	3
	SSA-DESN DESSA-DESN	2.535 1.466	1.999 0.689	1 1
B7	DESN	3.071	2.613	—
	DE-DESN	2.159	1.683	3
	SSA-DESN DESSA-DESN	1.954 1.269	1.332 0.728	— 1

电池型号	预测模型	RMSE/%	MAE/%	AE/周期
CS35	DESN	3.402	2.692	2
	DE-DESN	2.299	1.680	2
	SSA-DESN DESSA-DESN	1.968 1.253	1.442 0.923	1 0
CS36	DESN	3.048	2.319	2
	DE-DESN	2.819	2.112	1
	SSA-DESN DESSA-DESN	1.998 1.284	1.492 0.797	1 0
CS37	DESN	3.376	2.686	3
	DE-DESN	2.251	1.565	2
	SSA-DESN DESSA-DESN	1.767 1.075	1.134 0.793	1 1