Prediction method for remaining service life of lithium batteries using SSA-LSTM combination under variable mode decomposition

doi:10.19799/j.cnki.2095-4239.2024.0732

Abstract

Abstract:

The widespread application of lithium-ion batteries in electric vehicles, renewable energy, and other fields necessitates accurate prediction of their remaining useful life (RUL). Such predictions enable real-time monitoring of the battery's internal performance degradation, thereby reducing the risk associated with battery usage. We propose a combined prediction algorithm utilizing variational mode decomposition, sparrow search algorithm (SSA), and long short-term memory (LSTM) for predicting the remaining life of lithium-ion batteries. Initially, indirect health indicators for predicting RUL were extracted from the current, voltage, and temperature curves of the batteries. These indicators included isobaric charging time, isobaric charging energy, peak discharge temperature, and constant-current charging time. Subsequently, the VMD method was employed to decompose the capacity, aiming to avoid local fluctuations in capacity recovery and interference from test noise that could affect RUL prediction results. To address the susceptibility of traditional LSTM model hyperparameter settings toward experience and randomness, an SSA was proposed to optimize the parameters of the LSTM model, thereby enhancing the model's predictive capabilities. Ultimately, by utilizing NASA and CALCE datasets, a comparison was conducted between the proposed model and other models. Experimental results demonstrate that the proposed method achieves high predictive performance, with the root mean square error for RUL prediction of lithium-ion batteries consistently maintained within 2%.

Key words: lithium-ion batteries, remaining useful life, variational mode decomposition (VMD), sparrow search algorithm (SSA), long short-term memory (LSTM)

CLC Number:

TM 912

Jiabo LI, Zhixuan WANG, Di TIAN, Zhonglin SUN. Prediction method for remaining service life of lithium batteries using SSA-LSTM combination under variable mode decomposition[J]. Energy Storage Science and Technology, 2025, 14(2): 659-670.

Figures/Tables 27

Table 1

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Table 2

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Table 3

Table 4

Table 5

Table 6

Fig. 12

Fig. 13

Fig. 14

Fig. 15

Table 7

Table 8

Fig. 16

Table 9

Table 10

Table 11

References 18

1	GE M F, LIU Y B, JIANG X X, et al. A review on state of health estimations and remaining useful life prognostics of lithium-ion batteries[J]. Measurement, 2021, 174: 109057.
2	LIU C, WANG Y J, CHEN Z H. Degradation model and cycle life prediction for lithium-ion battery used in hybrid energy storage system[J]. Energy, 2019, 166: 796-806.
3	刘月峰, 赵光权, 彭喜元. 多核相关向量机优化模型的锂电池剩余寿命预测方法[J]. 电子学报, 2019, 47(6): 1285-1292. DOI: 10.3969/j.issn.0372-2112.2019.06.015.
	LIU Y F, ZHAO G Q, PENG X Y. A lithium-ion battery remaining using life prediction method based on multi-kernel relevance vector machine optimized model[J]. Acta Electronica Sinica, 2019, 47(6): 1285-1292. DOI: 10.3969/j.issn.0372-2112.2019.06.015.
4	KHODADADI SADABADI K, JIN X, RIZZONI G. Prediction of remaining useful life for a composite electrode lithium ion battery cell using an electrochemical model to estimate the state of health[J]. Journal of Power Sources, 2021, 481: 228861. DOI:10.1016/j.jpowsour.2020.228861.
5	EL MEJDOUBI A, CHAOUI H, GUALOUS H, et al. Lithium-ion batteries health prognosis considering aging conditions[J]. IEEE Transactions on Power Electronics, 2019, 34(7): 6834-6844.
6	YU J B. State of health prediction of lithium-ion batteries: Multiscale logic regression and Gaussian process regression ensemble[J]. Reliability Engineering & System Safety, 2018, 174: 82-95.
7	RAZAVI-FAR R, CHAKRABARTI S, SAIF M, et al. An integrated imputation-prediction scheme for prognostics of battery data with missing observations[J]. Expert Systems with Applications, 2019, 115: 709-723. DOI:10.1016/j.eswa.2018.08.033.
8	ALI M U, ZAFAR A, NENGROO S H, et al. Online remaining useful life prediction for lithium-ion batteries using partial discharge data features[J]. Energies, 2019, 12(22): 4366.
9	BAI G X, WANG P F, HU C. A self-cognizant dynamic system approach for prognostics and health management[J]. Journal of Power Sources, 2015, 278: 163-174.
10	TANG X P, YAO K, ZOU C F, et al. Predicting battery aging trajectory via a migrated aging model and Bayesian Monte Carlo method[J]. Energy Procedia, 2019, 158: 2456-2461.
11	WANG F K, HUANG C Y, MAMO T. Ensemble model based on stacked long short-term memory model for cycle life prediction of lithium-ion batteries[J]. Applied Sciences, 2020, 10(10): 3549.
12	ZHANG Y Z, XIONG R, HE H W, et al. Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries[J]. IEEE Transactions on Vehicular Technology, 2018, 67(7): 5695-5705. DOI:10.1109/TVT.2018.2805189.
13	魏腾飞, 潘庭龙. 基于改进PSO优化LSTM网络的短期电力负荷预测[J]. 系统仿真学报, 2021, 33(8): 1866-1874. DOI: 10.16182/j.issn1004731x.joss.20-0297.
	WEI T F, PAN T L. Short-term power load forecasting based on LSTM neural network optimized by improved PSO[J]. Journal of System Simulation, 2021, 33(8): 1866-1874.
14	LI S, FANG H J, SHI B. Remaining useful life estimation of Lithium-ion battery based on interacting multiple model particle filter and support vector regression[J]. Reliability Engineering & System Safety, 2021, 210: 107542. DOI:10.1016/j.ress.2021.107542.
15	常春, 王瑛琦, 姜久春, 等. 基于主动方波激励检测锂离子电池早期内短路[J]. 电池, 2024, 54(1): 24-28. DOI:10.19535/j.1001-1579. 2024.01.006.
	CHANG C, WANG Y Q, JIANG J C, et al. Detection of early internal short circuit of Li-ion battery based on active square wave excitation[J]. Dianchi(Battery Bimonthly), 2024, 54(1): 24-28. DOI:10.19535/j.1001-1579.2024.01.006.
16	MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67. DOI:10.1016/j.advengsoft.2016.01.008.
17	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. DOI:10.1162/neco.1997.9.8.1735.
18	SHI Y M, TIAN Y H, WANG Y W, et al. Learning long-term dependencies for action recognition with a biologically-inspired deep network[C]//2017 IEEE International Conference on Computer Vision (ICCV). October 22-29, 2017, Venice, Italy. IEEE, 2017: 716-725. DOI:10.1109/ICCV.2017.84.

电池型号	温度/℃	充电电流/A	放电电流/A	截止电压/V
B05	24	1.5	2	2.7
B06	24	1.5	2	2.7
B07	24	1.5	2	2.7
B18	24	1.5	2	2.7

电池	评价指标	LSTM	VMD-LSTM	VMD-SSA-LSTM	SSA-GPR	SSA-BP
B05	RMSE	0.030042	0.026647	0.01666	0.027592	0.029616
	MAE	0.027629	0.023644	0.015732	0.025463	0.026963
	MAPE	0.02042	0.017437	0.01675	0.018838	0.01992

电池	评价指标	LSTM	VMD-LSTM	VMD-SSA-LSTM	SSA-GPR	SSA-BP
B06	RMSE	0.042469	0.02555	0.016761	0.035789	0.037206
	MAE	0.035966	0.020792	0.014957	0.030624	0.031476
	MAPE	0.027604	0.0159	0.011712	0.023549	0.024178

电池	评价指标	LSTM	VMD-LSTM	VMD-SSA-LSTM	SSA-GPR	SSA-BP
B07	RMSE	0.027232	0.020322	0.019234	0.024218	0.026187
	MAE	0.022484	0.018142	0.017187	0.022117	0.022796
	MAPE	0.015269	0.012363	0.011718	0.015089	0.015513

电池	评价指标	LSTM	VMD-LSTM	VMD-SSA-LSTM	SSA-GPR	SSA-BP
B18	RMSE	0.022637	0.013673	0.010348	0.02948	0.02682
	MAE	0.018016	0.011538	0.0072894	0.02553	0.02385
	MAPE	0.01284	0.0082581	0.0053165	0.01824	0.01707