Remaining useful life prediction of lithium-ion battery based on an ABC-LSTM model

doi:10.19799/j.cnki.2095-4239.2024.0675

Abstract

Abstract:

To ensure the safe and stable operation of energy storage systems, the accurate prediction of the remaining useful life (RUL) of lithium-ion batteries is crucial. This study presents an integrated forecasting model that combines the artificial bee colony (ABC) algorithm with a long short-term memory (LSTM) network enhanced by dropout techniques. This combination effectively improves the accuracy of RUL predictions for lithium-ion batteries. First, the dropout regularization method is utilized to effectively mitigate overfitting, thereby enhancing the generalization capability of the predictive model. Subsequently, an activation layer network structure is introduced to address capacity recovery and data noise issues, significantly enhancing the ability of the model to handle complex nonlinear data. Thereafter, the hyperparameters of the LSTM-based comprehensive forecasting model are optimized using the ABC algorithm to avoid local optima and improve the precision of RUL predictions. Finally, the predictive accuracy and robustness of the proposed model are verified using a public dataset from the NASA Research Center and the CALCE. The paper conducts an experimental analysis and verification of The predictive performance of various algorithms were experimentally analyzed and verified using training data at 40% and 60% levels. The performance of swarm optimization algorithms, such as the Sparrow Search Algorithm and the Humpback Whale Optimization Algorithm, were also compared. The experimental results demonstrate that the proposed ABC-LSTM integrated forecasting model can capture the global trends and local characteristics of the capacity degradation of the lithium-ion battery more accurately than the compared models. The root-mean-squared error of the RUL prediction results obtained with a 60% proportion of training data remained consistently within 1.02%; the mean absolute error remained consistently within 0.86%, and the fitting coefficient exceeded 97%.

Key words: lithium-ion battery, remaining useful life prediction, long short-term memory network, artificial bee colony algorithm, dropout technology

CLC Number:

TK 912

Yong LIU, Huaiwen YU, Dapeng LIU, Yong MU, Yingzhou WANG, Xiuyu ZHANG. Remaining useful life prediction of lithium-ion battery based on an ABC-LSTM model[J]. Energy Storage Science and Technology, 2025, 14(1): 331-345.

Figures/Tables 16

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Fig.6

Fig.7

Table 2

Fig.8

Fig.9

Table 3

Fig.10

Fig.11

Table 4

Table 5

References 24

1	万广伟, 廖微, 张强. 锂离子电池剩余使用寿命预测综述[J]. 汽车零部件, 2023(5): 92-95. DOI: 10.19466/j.cnki.1674-1986.2023. 05.018.
	WAN G W, LIAO W, ZHANG Q. Review on the prediction of the remaining useful life of lithium-ion batteries[J]. Automobile Parts, 2023(5): 92-95. DOI: 10.19466/j.cnki.1674-1986.2023.05.018.
2	KARIJADI I, CHOU S Y, DEWABHARATA A. Wind power forecasting based on hybrid CEEMDAN-EWT deep learning method[J]. Renewable Energy, 2023, 218: 119357. DOI: 10.1016/j.renene.2023.119357.
3	闫啸宇, 周思达, 卢宇, 等. 锂离子电池容量衰退机理与影响因素[J]. 北京航空航天大学学报, 2023, 49(6): 1402-1413. DOI: 10.13700/j.bh.1001-5965.2021.0458.
	YAN X Y, ZHOU S D, LU Y, et al. Degradation mechanism and influencing factors on lithium-ion batteries[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(6): 1402-1413. DOI: 10.13700/j.bh.1001-5965.2021.0458.
4	FENG L, JIANG L H, LIU J L, et al. Dynamic overcharge investigations of lithium ion batteries with different state of health[J]. Journal of Power Sources, 2021, 507: 230262. DOI: 10.1016/j.jpowsour.2021.230262.
5	康健强, 龚智超, 钱春虎, 等. 锂离子电池在高脉冲工况下老化机理的分析与研究[J]. 电工电能新技术, 2023, 42(10): 35-45. DOI: 10.3969/j.issn.1001-3849.2005.03.003.
	KANG J Q, GONG Z C, QIAN C H, et al. Analysis and research on aging mechanism of lithium-ion battery under high pulse current condition[J]. Advanced Technology of Electrical Engineering and Energy, 2023, 42(10): 35-45. DOI: 10.3969/j.issn.1001-3849.2005.03.003.
6	LI R, BAO L Y, CHEN L, et al. Accelerated aging of lithium-ion batteries: Bridging battery aging analysis and operational lifetime prediction[J]. Science Bulletin, 2023, 68(23): 3055-3079. DOI: 10.1016/j.scib.2023.10.029.
7	张若可, 郭永芳, 余湘媛, 等. 基于数据驱动的锂离子电池RUL预测综述[J]. 电源学报, 2023, 21(5): 182-190. DOI: 10.13234/j.issn.2095-2805.2023.5.182.
	ZHANG R K, GUO Y F, YU X Y, et al. Review of data-driven RUL prediction for lithium-ion batteries[J]. Journal of Power Supply, 2023, 21(5): 182-190. DOI: 10.13234/j.issn.2095-2805.2023.5.182.
8	吴祎, 王友仁. 基于变分模态分解和高斯过程回归的锂离子电池剩余寿命预测方法[J]. 计算机与现代化, 2020(2): 83-88. DOI: 10.3969/j.issn.1006-2475.2020.02.017.
	WU Y, WANG Y R. Remaining useful life prediction of lithium-ion batteries based on VMD and GPR algorithm[J]. Computer and Modernization, 2020(2): 83-88. DOI: 10.3969/j.issn.1006-2475.2020.02.017.
9	王志福, 罗崴, 闫愿, 等. 基于多方法融合的锂离子电池SOC-SOH联合估计[J]. 北京理工大学学报, 2023, 43(6): 575-584. DOI: 10.15918/j.tbit1001-0645.2022.148.
	WANG Z F, LUO W, YAN Y, et al. Joint SOC-SOH estimation for Li-ion batteries based on multi-method fusion[J]. Transactions of Beijing Institute of Technology, 2023, 43(6): 575-584. DOI: 10.15918/j.tbit1001-0645.2022.148.
10	PENG J K, LUO J Y, HE H W, et al. An improved state of charge estimation method based on cubature Kalman filter for lithium-ion batteries[J]. Applied Energy, 2019, 253: 113520. DOI: 10.1016/j.apenergy.2019.113520.
11	李银, 王建峰, 莫伟权, 等. 基于数据驱动的锂离子电池剩余寿命预测综述[J/OL]. 电源学报, 1-16[2024-06-21]. http://kns.cnki.net/kcms/detail/12.1420.TM.20230613.1715.002.html.
	LI Y, WANG J F, MO W Q, et al. A data-driven survey on the remaining useful life prediction of lithium-Ion batteries[J/OL]. Journal of Power Supply, 1-16[2024-06-21]. http://kns.cnki.net/kcms/detail/12.1420.TM.20230613.1715.002.html.
12	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. DOI: 10.19799/j.cnki.2095-4239.2022.0341.
	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. DOI: 10.19799/j.cnki.2095-4239.2022.0341.
13	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. DOI: 10.19912/j.0254-0096.tynxb.2022-0422.
	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. DOI: 10.19912/j.0254-0096.tynxb.2022-0422.
14	张洪生, 尚鑫磊. 基于DAE-BLS的锂离子电池剩余使用寿命预测方法[J/OL]. 计算机集成制造系统, 1-15[2024-06-21]. http://kns.cnki.net/kcms/detail/11.5946.TP.20230410.1518.022.html.
	ZHANG H S, SHANG X L. A remaining useful life prediction method for lithium-Ion batteries based on DAE-BLS[J/OL]. Computer Integrated Manufacturing Systems, 1-15[2024-06-21]. http://kns.cnki.net/kcms/detail/11.5946.TP.20230410.1518.022.html.
15	崔显, 陈自强, 卢地华, 等. 基于KCC-PF的锂离子电池剩余使用寿命预测[J]. 装备环境工程, 2022, 19(4): 86-94.
	CUI X, CHEN Z Q, LU D H, et al. Remaining useful life prediction of lithium-ion battery based on Kendall rank correlation coefficient particle filter[J]. Equipment Environmental Engineering, 2022, 19(4): 86-94.
16	邹红波, 柴延辉, 杨钦贺, 等. 基于混合ISSA-LSTM的锂离子电池剩余使用寿命预测[J]. 电力系统保护与控制, 2023, 51(19): 21-31. DOI: 10.19783/j.cnki.pspc.230297.
	ZOU H B, CHAI Y H, YANG Q H, et al. Remaining useful life prediction of lithium-ion batteries based on hybrid ISSA-LSTM[J]. Power System Protection and Control, 2023, 51(19): 21-31. DOI: 10.19783/j.cnki.pspc.230297.
17	莫易敏, 陈佳浩, 叶鹏, 等. 基于多健康因子LSTM的电池容量估计方法[J/OL]. 电源学报, 1-13[2024-06-21]. http://kns.cnki.net/kcms/detail/12.1420.TM.20231204.1025.002.html.
	MO Y M, CHEN J H, YE P, et al. Battery capacity estimation method based on multiple health factors LSTM[J/OL]. Journal of Power Supply, 1-13[2024-06-21]. http://kns.cnki.net/kcms/detail/12.1420.TM.20231204.1025.002.html.
18	尹杰, 刘博, 孙国兵, 等. 基于迁移学习和降噪自编码器-长短时间记忆的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(1): 289-302. DOI: 10.19595/j.cnki.1000-6753.tces.221890.
	YIN J, LIU B, SUN G B, et al. Transfer learning denoising autoencoder-long short term memory for remaining useful life prediction of Li-ion batteries[J]. Transactions of China Electrotechnical Society, 2024, 39(1): 289-302. DOI: 10.19595/j.cnki.1000-6753.tces.221890.
19	ANGELICA F, HYDRO R, SULISTIYA Z D, et al. DeepLyric: Predicting music emotions through LSTM-GRU hybrid models with regularization techniques[J]. Procedia Computer Science, 2023, 227: 973-980. DOI: 10.1016/j.procs.2023.10.606.
20	KAYA E, GORKEMLI B, AKAY B, et al. A review on the studies employing artificial bee colony algorithm to solve combinatorial optimization problems[J]. Engineering Applications of Artificial Intelligence, 2022, 115: 105311. DOI: 10.1016/j.engappai.2022. 105311.
21	朱子敬, 何利文. 基于ABC-LSTM-GRU的时间序列分解与预测模型[J]. 软件工程, 2024, 27(3): 58-62. DOI: 10. 19644/j.cnki.issn2096-1472.2024.003.012.
	ZHU Z J, HE L W. Time series decomposition and prediction model based on ABC-LSTM-GRU[J]. Software Engineering, 2024, 27(3): 58-62. DOI: 10.19644/j.cnki.issn2096-1472.2024.003.012.
22	GONG Y D, ZHANG X Y, GAO D Z, et al. State-of-health estimation of lithium-ion batteries based on improved long short-term memory algorithm[J]. Journal of Energy Storage, 2022, 53: 105046. DOI: 10.1016/j.est.2022.105046.
23	LIU Y W, SUN J, SHANG Y L, et al. A novel remaining useful life prediction method for lithium-ion battery based on long short-term memory network optimized by improved sparrow search algorithm[J]. Journal of Energy Storage, 2023, 61: 106645. DOI: 10.1016/j.est.2023.106645.
24	郝可青, 吕志刚, 邸若海, 等. 基于鲸鱼算法优化长短时记忆神经网络的锂电池剩余寿命预测[J]. 科学技术与工程, 2022, 22(29): 12900-12908. DOI: 10.3969/j.issn.1671-1815.2022.29.025.
	HAO K Q, LYU Z G, DI R H, et al. Remaining useful life prediction of lithium battery based on long short-term memory optimized by whale optimization algorithm[J]. Science Technology and Engineering, 2022, 22(29): 12900-12908. DOI: 10.3969/j.issn.1671-1815.2022.29.025.

序号	模型	MAE	RMSE	R²	E_r	PE_r
B05	SVR	0.0189	0.0233	0.9343	2	3.57%
	CNN	0.0227	0.0256	0.9028	8	14.29%
	LSTM	0.0144	0.0199	0.9522	7	12.5%
	ABC-LSTM	0.0085	0.0104	0.9850	1	1.79%

B06	SVR	0.0179	0.0263	0.9324	2	5%
	CNN	0.0223	0.0297	0.9264	4	10%
	LSTM	0.0202	0.0256	0.9232	5	12.5%
	ABC-LSTM	0.0117	0.0163	0.9672	2	5%

B07	SVR	0.0094	0.0150	0.9543	2	2.56%
	CNN	0.0307	0.0326	0.8315	15	19.23%
	LSTM	0.0170	0.0226	0.9189	4	5.13%
	ABC-LSTM	0.0088	0.0141	0.9681	2	2.56%

B18	SVR	0.0135	0.0219	0.8242	2	4.65%
	CNN	0.0362	0.0387	0.7624	10	23.25%
	LSTM	0.0297	0.0318	0.8417	7	16.28%
	ABC-LSTM	0.0075	0.0139	0.9316	2	4.65%

序号	模型	MAE	RMSE	R²	E_r	PE_r
CS2_35	SVR	0.0343	0.0409	0.9616	17	2.65%
	CNN	0.0229	0.0332	0.9747	12	1.87%
	LSTM	0.0148	0.0229	0.988	7	1.09%
	ABC-LSTM	0.0073	0.0139	0.9936	2	0.31%

CS2_36	SVR	0.0321	0.0408	0.9721	55	8.51%
	CNN	0.0352	0.0436	0.9681	57	8.82%
	LSTM	0.0193	0.0287	0.9863	10	1.55%
	ABC-LSTM	0.0101	0.0149	0.9920	4	0.62%

序号	模型	MAE	RMSE	R²	E_r	PE_r
B05	SVR	0.0121	0.0154	0.9183	0	0
	CNN	0.0123	0.0163	0.9211	5	21.74%
	LSTM	0.0128	0.0157	0.9364	2	8.7%
	ABC-LSTM	0.0058	0.0094	0.9696	0	0
B06	SVR	0.0076	0.0128	0.9538	2	28.57%
	CNN	0.0159	0.0202	0.9344	2	28.57%
	LSTM	0.0156	0.0194	0.9412	3	42.86%
	ABC-LSTM	0.0044	0.0095	0.9755	1	14.29%
B07	SVR	0.0092	0.0126	0.9430	6	13.33%
	CNN	0.0179	0.0211	0.8423	16	35.56%
	LSTM	0.0104	0.0141	0.9158	2	4.44%
	ABC-LSTM	0.0051	0.0084	0.9641	1	2.22%
B18	SVR	0.0149	0.0250	0.7148	1	5.88%
	CNN	0.0139	0.0247	0.7294	3	17.65%
	LSTM	0.0160	0.0278	0.4503	2	11.76%
	ABC-LSTM	0.0054	0.0125	0.9182	0	0

序号	模型	MAE	RMSE	R²	E_r	PE_r
CS2_35	SVR	0.0255	0.0313	0.9728	11	1.72%
	CNN	0.018	0.0258	0.9816	8	1.25%
	LSTM	0.0153	0.0237	0.9845	3	0.47%
	ABC-LSTM	0.0068	0.0109	0.9969	1	0.16%

CS2_36	SVR	0.0253	0.0282	0.9831	6	0.93%
	CNN	0.0209	0.0267	0.9849	5	0.77%
	LSTM	0.0165	0.022	0.9898	3	0.46%
	ABC-LSTM	0.0098	0.0115	0.9957	1	0.15%

模型	MAE	RMSE	R²
PSO-LSTM^[22]	0.0095	0.0162	0.9136
SSA-LSTM^[23]	0.0074	0.0134	0.9365
WOA-LSTM^[24]	0.0085	0.0104	0.9234
ABC-LSTM	0.0058	0.0094	0.9696