A hybrid approach for lithium-ion battery remaining useful life prediction using signal decomposition and machine learning

被引:0
作者
Fan, Yibiao [1 ]
Lin, Zhishan [2 ]
Wang, Fan [3 ]
Zhang, Jianpeng [3 ]
机构
[1] Longyan Univ, Sch Phys & Mech & Elect Engn, Longyan 361000, Peoples R China
[2] Fujian Antong Elect Co Ltd, Longyan 361000, Peoples R China
[3] Xiamen Univ, Sch Aerosp Engn, Xiamen 361102, Peoples R China
来源
SCIENTIFIC REPORTS | 2025年 / 15卷 / 01期
关键词
Li-ion batteries; Remaining useful life prediction; Long short-term memory; Support vector regression; CEEMDAN; Sparrow search algorithm; PARTICLE FILTER; MODEL; STATE; DIAGNOSIS;
D O I
10.1038/s41598-025-92262-8
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Lithium-ion batteries are widely used in many fields, and accurate prediction of their remaining useful life (RUL) was crucial for effective battery management and safety assurance. In order to solve the problem of reduced RUL prediction accuracy caused by the local capacity regeneration phenomenon during battery capacity degradation, this paper proposed a novel RUL prediction method, which combined complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique with an innovative hybrid prediction strategy that integrated the support vector regression (SVR) and the long short-term memory (LSTM) networks. First, CEEMDAN was used to decompose the battery capacity data into high-frequency and low-frequency components, thereby reducing the impact of capacity regeneration. Subsequently, the SVR model predicted the low-frequency component that characterized the main degradation trend, and the high-frequency component that contained capacity regeneration features was predicted using an LSTM network optimized by the sparrow search algorithm (SSA). Finally, the final RUL prediction was obtained by combining the predictions of the two models. Experimental results on NASA public datasets showed that the proposed hybrid method significantly outperformed existing methods: the RMSE of the methods proposed in this paper were all less than 0.0086 Ah, the MAE were all less than 0.0060 Ah, the R2 values were all higher than 0.96, and the RUL prediction errors were controlled within one cycle. This method gave full play to the complementary advantages of SVR and LSTM and provided an accurate and reliable solution for RUL prediction of lithium-ion batteries.
引用
收藏
页数:17
相关论文
共 41 条
  • [1] Financial time series forecasting model based on CEEMDAN and LSTM
    Cao, Jian
    Li, Zhi
    Li, Jian
    [J]. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2019, 519 : 127 - 139
  • [2] Chen C., 2021, J. Power Sources, V45, P589
  • [3] Remaining useful life and state of health prediction for lithium batteries based on empirical mode decomposition and a long and short memory neural network
    Cheng, Gong
    Wang, Xinzhi
    He, Yurong
    [J]. ENERGY, 2021, 232
  • [4] Remaining Useful Life Prediction of Aviation Lithium-ion Battery Based on SVR-MC
    Cui, Jianguo
    Zhao, Jie
    Cui, Xiao
    Liu, Dong
    Du, Wenyou
    Yu, Mingyue
    Jiang, Liying
    Wang, Jinglin
    [J]. 2022 34TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2022, : 505 - 510
  • [5] Empirical mode decomposition:: An analytical approach for sifting process
    Deléchelle, E
    Lemoine, J
    Niang, O
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2005, 12 (11) : 764 - 767
  • [6] Lithium-ion battery state of health monitoring and remaining useful life prediction based on support vector regression-particle filter
    Dong, Hancheng
    Jin, Xiaoning
    Lou, Yangbing
    Wang, Changhong
    [J]. JOURNAL OF POWER SOURCES, 2014, 271 : 114 - 123
  • [7] A data-driven prediction model for the remaining useful life prediction of lithium-ion batteries
    Feng, Juqiang
    Cai, Feng
    Li, Huachen
    Huang, Kaifeng
    Yin, Hao
    [J]. PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, 2023, 180 : 601 - 615
  • [8] Short-term wind power forecasting based on SSA-VMD-LSTM
    Gao, Xiaozhi
    Guo, Wang
    Mei, Chunxiao
    Sha, Jitong
    Guo, Yingjun
    Sun, Hexu
    [J]. ENERGY REPORTS, 2023, 9 : 335 - 344
  • [9] State-of-health estimation of lithium-ion batteries based on improved long short-term memory algorithm
    Gong, Yadong
    Zhang, Xiaoyong
    Gao, Dianzhu
    Li, Heng
    Yan, Lisen
    Peng, Jun
    Huang, Zhiwu
    [J]. JOURNAL OF ENERGY STORAGE, 2022, 53
  • [10] Development of a Data-Driven Method for Online Battery Remaining-Useful-Life Prediction
    Hell, Sebastian Matthias
    Kim, Chong Dae
    [J]. BATTERIES-BASEL, 2022, 8 (10):