Electrochemical impedance spectroscopy image transformation-based convolutional neural network for diagnosis of external environment classification affecting abnormal aging of Li-ion batteries

Dongho Han, Sanguk Kwon, Miyoung Lee, Jonghoon Kim and Kisoo Yoo

Applied Energy, 2023, vol. 345, issue C, No S0306261923007006

Abstract: Various electric mobilities are being developed that use Lithium (Li)-ion batteries as the primary power source for target applications. Especially, with the widespread adoption of electric vehicle (EV), the significance of battery management system (BMS) which are closely related to the stable operation of Li-ion batteries, is also increasing. Diagnosing the external environment is essential because the aging pattern of the battery varies depending on the environment condition in which the battery is exposed and can cause abnormal failures. This study presents an approach for classifying the external environment using electrochemical impedance spectroscopy (EIS) as an indicator, which is closely related to the internal chemical characteristics of the batteries. Recurrence plot (RP) algorithm is applied to improve the performance of convolution neural network (CNN) used as classification model as well as original EIS image. According to the frequency at which the main parameters of the Randles circuit model are derived, an additional dataset is constructed based on the selected 3-points. This paper presents the results of the classification from the external environment based on the three methods and derives a statistical evaluation metric to prove the stability and performance of the model. Moreover, it is also suggested that the appropriate method can be selected based on the desired cost by deriving the detailed model loss and accuracy for the training epoch, which is a trade-off relationship for each method.

Keywords: Electric vehicle; External environment classification; Electrochemical impedance spectroscopy; Image data-processing; Convolution neural network (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261923007006
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:345:y:2023:i:c:s0306261923007006

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2023.121336

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().