State-of-health estimation of lithium-ion batteries using a novel dual-stage attention mechanism based recurrent neural network

被引:26
作者
Hong, Jiangnan [1 ,2 ]
Chen, Yucheng [3 ]
Chai, Qinqin [1 ,2 ]
Lin, Qiongbin [1 ]
Wang, Wu [1 ]
机构
[1] Fuzhou Univ, Coll Elect Engn & Automat, Fuzhou 350000, Peoples R China
[2] Wuhan Univ Sci & Technol, Minist Educ, Engn Res Ctr Met Automat & Measurement Technol, Wuhan 430081, Peoples R China
[3] Zhangzhou Inst Technol, Sch Informat Engn, Zhangzhou 363000, Peoples R China
关键词
State of health; Lithium-ion battery; Dual -stage attention -based recurrent neural; network; MODEL;
D O I
10.1016/j.est.2023.109297
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
Accurate estimation of the state of health (SOH) of lithium-ion batteries is an important guarantee to ensure safe and reliable operation of lithium-ion battery systems. However, the complex aging mechanism inside the battery makes it difficult to measure the battery SOH directly. In this paper, a SOH estimation method based on a novel dual-stage attention-based recurrent neural network (DARNN) and health feature (HF) extraction from time varying charging process is proposed. Firstly, the constant current charging time, the maximum temperature time, the isochronous voltage difference, and the isochronous current were extracted as lithium-ion battery HFs, and their correlations with SOH are verified by spearman correlation coefficient. Secondly, the DARNN is proposed to capture the time-dependent and temporal features of the input sequence and to accurately predict SOH. Finally, the proposed estimation method is validated on the NASA battery dataset. The results show that the method can accurately estimate SOH for lithium-ion batteries. The mean square error and the mean absolute percentage error of the method are <0.5 %.
引用
收藏
页数:10
相关论文
共 30 条
[1]   An estimation model for state of health of lithium-ion batteries using energy-based features [J].
Cai, Li ;
Lin, Jingdong ;
Liao, Xiaoyong .
JOURNAL OF ENERGY STORAGE, 2022, 46
[2]  
Chen Wan, 2022, Proceedings of 2021 Chinese Intelligent Automation Conference. Lecture Notes in Electrical Engineering (801), P47, DOI 10.1007/978-981-16-6372-7_6
[3]   Lithium-ion batteries remaining useful life prediction based on BLS-RVM [J].
Chen, Zewang ;
Shi, Na ;
Ji, Yufan ;
Niu, Mu ;
Wang, Youren .
ENERGY, 2021, 234
[4]   Remaining useful life and state of health prediction for lithium batteries based on empirical mode decomposition and a long and short memory neural network [J].
Cheng, Gong ;
Wang, Xinzhi ;
He, Yurong .
ENERGY, 2021, 232
[5]   Estimation of the state of health (SOH) of batteries using discrete curvature feature extraction [J].
Goh, Hui Hwang ;
Lan, Zhentao ;
Zhang, Dongdong ;
Dai, Wei ;
Kurniawan, Tonni Agustiono ;
Goh, Kai Chen .
JOURNAL OF ENERGY STORAGE, 2022, 50
[6]   A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction [J].
Guo, Peiyao ;
Cheng, Ze ;
Yang, Lei .
JOURNAL OF POWER SOURCES, 2019, 412 :442-450
[7]  
Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[8]   Improved State-of-health prediction based on auto-regressive integrated moving average with exogenous variables model in overcoming battery degradation-dependent internal parameter variation [J].
Kim, Seongwoo ;
Lee, Pyeong-Yeon ;
Lee, Miyoung ;
Kim, Jonghoon ;
Na, Woonki .
JOURNAL OF ENERGY STORAGE, 2022, 46
[9]   Electrochemical Model Based Observer Design for a Lithium-Ion Battery [J].
Klein, Reinhardt ;
Chaturvedi, Nalin A. ;
Christensen, Jake ;
Ahmed, Jasim ;
Findeisen, Rolf ;
Kojic, Aleksandar .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2013, 21 (02) :289-301
[10]   State-of-health estimation and remaining useful life prediction for the lithium-ion battery based on a variant long short term memory neural network [J].
Li, Penghua ;
Zhang, Zijian ;
Xiong, Qingyu ;
Ding, Baocang ;
Hou, Jie ;
Luo, Dechao ;
Rong, Yujun ;
Li, Shuaiyong .
JOURNAL OF POWER SOURCES, 2020, 459