Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm

被引:12
作者
Wu, Jingjin [1 ]
Cheng, Xukun [1 ]
Huang, Heng [1 ]
Fang, Chao [1 ]
Zhang, Ling [1 ]
Zhao, Xiaokang [2 ]
Zhang, Lina [3 ]
Xing, Jiejie [1 ]
机构
[1] Hainan Univ, Mech & Elect Engn Coll, Haikou, Hainan, Peoples R China
[2] Hainan Curium Technol Co Ltd, Haikou, Peoples R China
[3] China Agr Univ, Engn Coll, Beijing, Peoples R China
关键词
lithium-ion batteries; RUL; RF; PSO; machine learning; HEALTH ESTIMATION; RANDOM FOREST; MODEL; STATE; PROGNOSTICS; OPTIMIZATION; NETWORK;
D O I
10.3389/fenrg.2022.937035
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is the key to the battery health management system. However, problems of unstable model output and extensive calculation limit the prediction accuracy. This article proposes a Particle Swarm Optimization Random Forest (PSO-RF) prediction method to improve the RUL prediction accuracy. First, the battery capacity extracted from the lithium-ion battery data set of the National Aeronautics and Space Administration (NASA) and the University of Maryland Center for Advanced Life Cycle Engineering (CALCE) is set as the battery life health factor. Then, a PSO-RF prediction model is established based on the optimal parameters for the number of trees and the number of random features to split by the PSO algorithm. Finally, the experiment is verified on the NASA and CALCE data sets. The experiment results indicate that the method predicts RUL with Mean Absolute Error (MAE) less than 2%, Root Mean Square Error (RMSE) less than 3%, and goodness of fit greater than 94%. This method solves the problem of parameter selection in the RF algorithm.
引用
收藏
页数:20
相关论文
共 34 条
[1]   Gated recurrent unit least-squares generative adversarial network for battery cycle life prediction [J].
Ardeshiri, Reza Rouhi ;
Razavi-Far, Roozbeh ;
Li, Tao ;
Wang, Xu ;
Ma, Chengbin ;
Liu, Ming .
MEASUREMENT, 2022, 196
[2]   A generic model-free approach for lithium-ion battery health management [J].
Bai, Guangxing ;
Wang, Pingfeng ;
Hu, Chao ;
Pecht, Michael .
APPLIED ENERGY, 2014, 135 :247-260
[3]   Spatial prediction of soil surface texture in a semiarid region using random forest and multiple linear regressions [J].
Chagas, Cesar da Silva ;
de Carvalho Junior, Waldir ;
Bhering, Silvio Barge ;
Calderano Filho, Braz .
CATENA, 2016, 139 :232-240
[4]   Polynomial approximation pseudo-two-dimensional battery model for online application in embedded battery management system [J].
Deng, Zhongwei ;
Yang, Lin ;
Deng, Hao ;
Cai, Yishan ;
Li, Dongdong .
ENERGY, 2018, 142 :838-850
[5]   Remaining useful life prediction of lithium-ion battery based on extended Kalman particle filter [J].
Duan, Bin ;
Zhang, Qi ;
Geng, Fei ;
Zhang, Chenghui .
INTERNATIONAL JOURNAL OF ENERGY RESEARCH, 2020, 44 (03) :1724-1734
[6]   An RUL prediction approach for lithium-ion battery based on SADE-MESN [J].
Ji, Yufan ;
Chen, Zewang ;
Shen, Yong ;
Yang, Ke ;
Wang, Youren ;
Cui, Jiang .
APPLIED SOFT COMPUTING, 2021, 104
[7]   A new neural network model for the state-of-charge estimation in the battery degradation process [J].
Kang, LiuWang ;
Zhao, Xuan ;
Ma, Jian .
APPLIED ENERGY, 2014, 121 :20-27
[8]   DETERMINING EMBEDDING DIMENSION FOR PHASE-SPACE RECONSTRUCTION USING A GEOMETRICAL CONSTRUCTION [J].
KENNEL, MB ;
BROWN, R ;
ABARBANEL, HDI .
PHYSICAL REVIEW A, 1992, 45 (06) :3403-3411
[9]   A support vector machine-based state-of-health estimation method for lithium-ion batteries under electric vehicle operation [J].
Klass, Verena ;
Behm, Marten ;
Lindbergh, Goran .
JOURNAL OF POWER SOURCES, 2014, 270 :262-272
[10]   Hour-ahead wind power forecast based on random forests [J].
Lahouar, A. ;
Slama, J. Ben Hadj .
RENEWABLE ENERGY, 2017, 109 :529-541