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

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...

Full description

Saved in:
Bibliographic Details
Published inEnergies (Basel) Vol. 15; no. 12; p. 4399
Main Authors Bao, Zhengyi, Jiang, Jiahao, Zhu, Chunxiang, Gao, Mingyu
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.06.2022
Subjects
Accuracy
Aging
bidirectional gated recurrent units
Datasets
dilated convolutional neural networks
Electric vehicles
hybrid network
Kalman filters
Lithium
Lithium cells
Lithium-ion batteries
lithium-ion battery
Machine learning
Methods
Neural networks
Partial differential equations
Root-mean-square errors
Service life (Engineering)
state-of-health
Temperature effects
Working conditions
China
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:1996-1073
1996-1073
DOI:10.3390/en15124399