Remaining useful life prediction of a lithium-ion battery based on a cheetah optimization-extreme learning machine with improved Sine chaotic mapping

doi:10.19799/j.cnki.2095-4239.2024.0990

Abstract

Abstract:

To address the challenges of unstable predictions and accuracy when using extreme learning machines (ELMs) to predict the remaining useful life of lithium-ion batteries, this study proposes a cheetah optimization (CO) algorithm to optimize the ELM model performance. The equal voltage drop discharge time, extracted from the lithium-ion battery dataset, is employed as an indirect health factor. Furthermore, the CO algorithm is introduced to optimize the ELM parameters. This initial population of the CO algorithm is improved using sine chaotic mapping. The effectiveness and accuracy of the proposed model are verified using the battery dataset provided by the NASA Center for Excellence Prediction and the Oxford Battery Degradation Dataset from Oxford University. The optimal amount of training data and the ideal number of neurons are obtained through multiple experiments with the original ELM model. The residual service life of batteries is predicted using the proposed SCO-ELM model. Compared with the original ELM and the genetic algorithm-optimized ELM model, the proposed SCO-ELM model achieves a root mean square error below 0.004 and significantly faster prediction times. The prediction accuracy improves by 40% on average and the prediction speed is improved by more than 78%. Using the training results of battery B0005 to predict the performance of similar battery packs, the prediction accuracy improves by 25% on average, and the prediction speed increases by more than 75%. Thus, the experimental results confirm that the proposed method offers high prediction accuracy, fast computation speed, low operation complexity, and a stable model.

Key words: lithium-ion battery, remaining useful life, extreme learning machine, cheetah optimization, chaotic mapping

CLC Number:

TM 912

Peng WANG, Jun ZHOU, Xing WU, Tao LIU. Remaining useful life prediction of a lithium-ion battery based on a cheetah optimization-extreme learning machine with improved Sine chaotic mapping[J]. Energy Storage Science and Technology, 2025, 14(4): 1603-1616.

Figures/Tables 28

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Table 1

Fig. 5

Table 2

Fig. 6

Table 3

Fig. 7

Table 4

Fig. 8

Table 5

Fig. 9

Table 6

Table 7

Fig. 10

Fig. 11

Fig. 12

Table 8

Fig. 13

Fig. 14

Fig. 15

Table 9

Fig. 16

Fig. 17

Fig. 18

Table 10

References 21

1	卢婷, 杨文强. 锂离子电池全生命周期内评估参数及评估方法综述[J]. 储能科学与技术, 2020, 9(3): 657-669. DOI: 10.19799/j.cnki. 2095-4239.2019.0263.
	LU T, YANG W Q. Review of evaluation parameters and methods of lithium batteries throughout its life cycle[J]. Energy Storage Science and Technology, 2020, 9(3): 657-669. DOI: 10.19799/j.cnki.2095-4239.2019.0263.
2	KIM I S. A technique for estimating the state of health of lithium batteries through a dual-sliding-mode observer[J]. IEEE Transactions on Power Electronics, 2010, 25(4): 1013-1022. DOI: 10.1109/TPEL.2009.2034966.
3	HE W, WILLIARD N, OSTERMAN M, et al. Prognostics of lithium-ion batteries based on Dempster-Shafer theory and the Bayesian Monte Carlo method[J]. Journal of Power Sources, 2011, 196(23): 10314-10321. DOI: 10.1016/j.jpowsour.2011. 08.040.
4	AN D, CHOI J H, KIM N H. Prognostics 101: A tutorial for particle filter-based prognostics algorithm using Matlab[J]. Reliability Engineering & System Safety, 2013, 115: 161-169. DOI: 10.1016/j.ress.2013.02.019.
5	SU X H, WANG S, PECHT M, et al. Prognostics of lithium-ion batteries based on different dimensional state equations in the particle filtering method[J]. Transactions of the Institute of Measurement and Control, 2017, 39(10): 1537-1546.
6	MIAO Q, XIE L, CUI H J, et al. Remaining useful life prediction of lithium-ion battery with unscented particle filter technique[J]. Microelectronics Reliability, 2013, 53(6): 805-810. DOI: 10.1016/j.microrel.2012.12.004.
7	HE W, WILLIARD N, CHEN C C, et al. State of charge estimation for electric vehicle batteries under an adaptive filtering framework[C]//Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing). May 23-25, 2012, Beijing, China. IEEE, 2012: 1-5. DOI: 10.1109/PHM. 2012.6228849.
8	WANG S L, FERNANDEZ C, CAO W, et al. An adaptive working state iterative calculation method of the power battery by using the improved Kalman filtering algorithm and considering the relaxation effect[J]. Journal of Power Sources, 2019, 428: 67-75. DOI: 10.1016/j.jpowsour.2019.04.089.
9	ZHAO Y, LIU P, WANG Z P, et al. Fault and defect diagnosis of battery for electric vehicles based on big data analysis methods[J]. Applied Energy, 2017, 207: 354-362. DOI: 10.1016/j.apenergy.2017.05.139.
10	EDDAHECH A, BRIAT O, BERTRAND N, et al. Behavior and state-of-health monitoring of Li-ion batteries using impedance spectroscopy and recurrent neural networks[J]. International Journal of Electrical Power & Energy Systems, 2012, 42(1): 487-494. DOI: 10.1016/j.ijepes.2012.04.050.
11	XIONG R, TIAN J P, SHEN W X, et al. Semi-supervised estimation of capacity degradation for lithium ion batteries with electrochemical impedance spectroscopy[J]. Journal of Energy Chemistry, 2023, 76: 404-413. DOI: 10.1016/j.jechem. 2022. 09.045.
12	PATIL M A, TAGADE P, HARIHARAN K S, et al. A novel multistage Support Vector Machine based approach for Li ion battery remaining useful life estimation[J]. Applied Energy, 2015, 159: 285-297. DOI: 10.1016/j.apenergy.2015.08.119.
13	LONG B, XIAN W M, JIANG L, et al. An improved autoregressive model by particle swarm optimization for prognostics of lithium-ion batteries[J]. Microelectronics Reliability, 2013, 53(6): 821-831. DOI: 10.1016/j.microrel.2013.01.006.
14	姜媛媛, 刘柱, 罗慧, 等. 锂电池剩余寿命的ELM间接预测方法[J]. 电子测量与仪器学报, 2016, 30(2): 179-185. DOI: 10.13382/j.jemi. 2016.02.002.
	JIANG Y Y, LIU Z, LUO H, et al. ELM indirect prediction method for the remaining life of lithium-ion battery[J]. Journal of Electronic Measurement and Instrumentation, 2016, 30(2): 179-185. DOI: 10.13382/j.jemi.2016.02.002.
15	陈则王, 李福胜, 林娅, 等. 基于GA-ELM的锂离子电池RUL间接预测方法[J]. 计量学报, 2020, 41(6): 735-742. DOI: 10.3969/j.issn. 1000-1158.2020.06.17.
	CHEN Z W, LI F S, LIN Y, et al. Indirect prediction method of RUL for lithium-ion battery based on GA-ELM[J]. Acta Metrologica Sinica, 2020, 41(6): 735-742. DOI: 10.3969/j.issn.1000-1158. 2020.06.17.
16	刘柱, 姜媛媛, 罗慧, 等. 基于最优权阈值ELM算法的锂离子电池RUL预测[J]. 电源学报, 2018, 16(4): 168-173. DOI: 10.13234/j.issn.2095-2805.2018.4.168.
	LIU Z, JIANG Y Y, LUO H, et al. Prediction of lithium-ion battery RUL based on optimal weight and threshold using ELM algorithm[J]. Journal of Power Supply, 2018, 16(4): 168-173. DOI: 10. 13234/j.issn.2095-2805.2018.4.168.
17	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501. DOI: 10.1016/j.neucom.2005.12.126.
18	AKBARI M A, ZARE M, AZIZIPANAH-ABARGHOOEE R, et al. The cheetah optimizer: A nature-inspired metaheuristic algorithm for large-scale optimization problems[J]. Scientific Reports, 2022, 12(1): 10953. DOI: 10.1038/s41598-022-14338-z.
19	单梁, 强浩, 李军, 等. 基于Tent映射的混沌优化算法[J]. 控制与决策, 2005, 20(2): 179-182. DOI: 10.13195/j.cd.2005.02.60.shanl.013.
	SHAN L, QIANG H, LI J, et al. Chaotic optimization algorithm based on tent map[J]. Control and Decision, 2005, 20(2): 179-182. DOI: 10.13195/j.cd.2005.02.60.shanl.013.
20	刘磊, 姜博文, 周恒扬, 等. 融合改进Sine混沌映射的新型粒子群优化算法[J]. 西安交通大学学报, 2023, 57(8): 182-193. DOI: 10. 7652/xjtuxb202308018.
	LIU L, JIANG B W, ZHOU H Y, et al. A novel particle swarm optimization algorithm incorporating improved Sine chaos mapping[J]. Journal of Xi'an Jiaotong University, 2023, 57(8): 182-193. DOI: 10.7652/xjtuxb202308018.
21	BIRKL C. Diagnosis and prognosis of degradation in lithium-ion batteries[D]. Oxford, South East England, UK: University of Oxford, 2017.

电池数据集	相关性	偏相关性
B0005	0.998271	0.931276
B0006	0.994482	0.931649
B0007	0.998413	0.947518
B0018	0.997773	0.962799

训练数据量	RMSE	r²
70	0.005686	0.996488
80	0.003693	0.995305
90	0.003714	0.997775
100	0.003937	0.996634

神经元数量	RMSE	r²
1	0.165125	0.995686
2	0.003755	0.994720
3	0.003666	0.995497
4	0.003582	0.995422

训练模型	RMSE	r²	训练时间 /s	ELM模型预测精度提升/%	ELM模型预测速度提升/%
ELM	0.010503	0.995182	0.000483	—	—
LSTM	0.017830	0.963152	2.241374	41.0937	99.9784
Transformer	0.029974	0.890339	9.276232	64.9596	99.9948

训练模型	RMSE	r²	训练时间/s
ELM	0.014614	0.993549	0.000358
GA-ELM	0.007035	0.995531	0.253348
SCO-ELM	0.003783	0.995071	0.058393