A New Hybrid Neural Network Method for State-of-Health Estimation of Lithium-Ion Battery

被引:29
作者
Bao, Zhengyi [1 ]
Jiang, Jiahao [1 ]
Zhu, Chunxiang [1 ,2 ]
Gao, Mingyu [1 ,3 ]
机构
[1] Hangzhou Dianzi Univ, Sch Elect & Informat, Hangzhou 310018, Peoples R China
[2] China Jiliang Univ, Engn Training Ctr, Hangzhou 310018, Peoples R China
[3] Zhejiang Prov Key Lab Equipment Elect, Hangzhou 310018, Peoples R China
关键词
lithium-ion battery; state-of-health; dilated convolutional neural networks; bidirectional gated recurrent units; hybrid network; SOH ESTIMATION; INCREMENTAL CAPACITY;
D O I
10.3390/en15124399
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 lithium-ion battery state-of-health (SOH) is important for the safe operation of electric vehicles; however, in practical applications, the accuracy of SOH estimation is affected by uncertainty factors, including human operation, working conditions, etc. To accurately estimate the battery SOH, a hybrid neural network based on the dilated convolutional neural network and the bidirectional gated recurrent unit, namely dilated CNN-BiGRU, is proposed in this paper. The proposed data-driven method uses the voltage distribution and capacity changes in the extracted battery discharge curve to learn the serial data time dependence and correlation. This method can obtain more accurate temporal and spatial features of the original battery data, resulting higher accuracy and robustness. The effectiveness of dilated CNN-BiGRU for SOH estimation is verified on two publicly lithium-ion battery datasets, the NASA Battery Aging Dataset and Oxford Battery Degradation Dataset. The experimental results reveal that the proposed model outperforms the compared data-driven methods, e.g., CNN-series and RNN-series. Furthermore, the mean absolute error (MAE) and root mean square error (RMSE) are limited to within 1.9% and 3.3%, respectively, on the NASA Battery Aging Dataset.
引用
收藏
页数:16
相关论文
共 36 条
[1]  
[王凡 Wang Fan], 2021, [储能科学与技术, Energy Storage Science and Technology], V10, P2326
[2]   Advanced mathematical methods of SOC and SOH estimation for lithium-ion batteries [J].
Andre, Dave ;
Appel, Christian ;
Soczka-Guth, Thomas ;
Sauer, Dirk Uwe .
JOURNAL OF POWER SOURCES, 2013, 224 :20-27
[3]  
Birkl C., 2017, OXFORD BATTERY DEGRA
[4]   State of health (SoH) estimation and degradation modes analysis of pouch NMC532/graphite Li-ion battery [J].
Chen, Xiaoxuan ;
Hu, Yonggang ;
Li, Sheng ;
Wang, Yuexing ;
Li, Dongjiang ;
Luo, Chuanjun ;
Xue, Xujin ;
Xu, Fei ;
Zhang, Zhongru ;
Gong, Zhengliang ;
Li, Yangxing ;
Yang, Yong .
JOURNAL OF POWER SOURCES, 2021, 498
[5]   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
[6]  
Chung J, 2014, ARXIV
[7]   Real-Time Estimation of PEMFC Parameters Using a Continuous-Discrete Extended Kalman Filter Derived from a Pseudo Two-Dimensional Model [J].
Diab, Yasser ;
Auger, Francois ;
Schaeffer, Emmanuel ;
Chevalier, Stephane ;
Allahham, Adib .
ENERGIES, 2022, 15 (07)
[8]   A novel deep learning framework for state of health estimation of lithium-ion battery [J].
Fan, Yaxiang ;
Xiao, Fei ;
Li, Chaoran ;
Yang, Guorun ;
Tang, Xin .
JOURNAL OF ENERGY STORAGE, 2020, 32
[9]   Deep Learning-Based Real-Time Building Occupancy Detection Using AMI Data [J].
Feng, Cong ;
Mehmani, Ali ;
Zhang, Jie .
IEEE TRANSACTIONS ON SMART GRID, 2020, 11 (05) :4490-4501
[10]   Online State-of-Health Estimation for Li-Ion Battery Using Partial Charging Segment Based on Support Vector Machine [J].
Feng, Xuning ;
Weng, Caihao ;
He, Xiangming ;
Han, Xuebing ;
Lu, Languang ;
Ren, Dongsheng ;
Ouyang, Minggao .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2019, 68 (09) :8583-8592