State-of-health estimation of Lithium-ion battery based on back-propagation neural network with adaptive hidden layer

The reliability and safety of lithium-ion batteries (LIBs) are key issues in battery applications. Accurate prediction of the state-of-health (SOH) of LIBs can reduce or even avoid battery-related accidents. In this paper, a new back-propagation neural network (BPNN) is proposed to predict the SOH o...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications 2023-07, Vol.35 (19), p.14169-14182
Main Authors: Chen, Liping, Xu, Changcheng, Bao, Xinyuan, Lopes, António, Li, Penghua, Zhang, Chaolong
Format: Article
Language:English
Subjects:
Accuracy
Artificial Intelligence
Artificial neural networks
Automation
Back propagation
Back propagation networks
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Datasets
Emission standards
Engineering
Image Processing and Computer Vision
Lithium
Lithium-ion batteries
Methods
Neural networks
Original Article
Probability and Statistics in Computer Science
Propagation
Rechargeable batteries
Saturn
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The reliability and safety of lithium-ion batteries (LIBs) are key issues in battery applications. Accurate prediction of the state-of-health (SOH) of LIBs can reduce or even avoid battery-related accidents. In this paper, a new back-propagation neural network (BPNN) is proposed to predict the SOH of LIBs. The BPNN uses as input the LIB voltage, current and temperature, as well as the charging time, since it is strongly correlated with the SOH. The number of hidden layer nodes is adaptively set based on the training data in order to improve the generalization capability of the BPNN. The effectiveness and robustness of the proposed scheme is verified using four distinct battery datasets and different training data. Experimental results show that the new BPNN is able to accurately predict the SOH of LIBs, revealing superiority when compared to other alternatives.
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-023-08471-7