A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry

Sibo Zeng; Sheng Chen; Yang Yu

doi:10.3233/FAIA231383

A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry

Sibo Zeng, Sheng Chen^*, Yang Yu

^*Corresponding author for this work

Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

28 Downloads (Pure)

Abstract

Precise estimation of Lithium-ion battery capacity is critical for the battery management system (BMS). This paper proposed an innovative method that combinates convolutional neural network and feature curves which are incremental capacity analysis (ICA) and differential thermal voltammetry (DTV). Rather than extracting feature parameters of the IC curve as done in available research, the present method uses the whole IC and DTV curves in a certain range of voltage as the input to avoid complicated annual feature extraction and correlation analysis. The result shows that the max error of capacity estimation is less than 4.46 %, the mean absolute percentage error is less than 1.29 % for each battery, and overall MAPE is below 1.19 %.

Original language	English
Title of host publication	Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023)
Editors	Chenglizhao Chen
Publisher	IOP Publishing
Pages	839-849
Number of pages	11
ISBN (Electronic)	9781643684857
ISBN (Print)	9781643684840
DOIs	https://doi.org/10.3233/FAIA231383
Publication status	Published - 12 Feb 2024
Event	2023 5th International Conference on Artificial Intelligence Technologies and Applications - Changchun University of Science and Technology, Changchun, China Duration: 30 Jun 2023 → 2 Jul 2023 http://2023.ic-aita.org/

Publication series

Name	Frontiers in Artificial Intelligence and Applications
Volume	382
ISSN (Print)	0922-6389
ISSN (Electronic)	1879-8314

Conference

Conference	2023 5th International Conference on Artificial Intelligence Technologies and Applications
Abbreviated title	ICAITA 2023
Country/Territory	China
City	Changchun
Period	30/06/23 → 2/07/23
Internet address	http://2023.ic-aita.org/

Keywords

convolutional neural network
differential thermal voltammetry
incremental capacity analysis
Li-ion battery

ASJC Scopus subject areas

Artificial Intelligence

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Documents and Links

10.3233/FAIA231383

Final published versionFinal published version, 1.32 MBLicence: CC BY-NC

Cite this

Zeng, S., Chen, S., & Yu, Y. (2024). A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry. In C. Chen (Ed.), Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023) (pp. 839-849). (Frontiers in Artificial Intelligence and Applications; Vol. 382). IOP Publishing. https://doi.org/10.3233/FAIA231383

Zeng, Sibo ; Chen, Sheng ; Yu, Yang. / A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry. Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023). editor / Chenglizhao Chen. IOP Publishing, 2024. pp. 839-849 (Frontiers in Artificial Intelligence and Applications).

@inproceedings{30c47ec9f652492ebaf9d9b2df0dce52,

title = "A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry",

abstract = "Precise estimation of Lithium-ion battery capacity is critical for the battery management system (BMS). This paper proposed an innovative method that combinates convolutional neural network and feature curves which are incremental capacity analysis (ICA) and differential thermal voltammetry (DTV). Rather than extracting feature parameters of the IC curve as done in available research, the present method uses the whole IC and DTV curves in a certain range of voltage as the input to avoid complicated annual feature extraction and correlation analysis. The result shows that the max error of capacity estimation is less than 4.46 %, the mean absolute percentage error is less than 1.29 % for each battery, and overall MAPE is below 1.19 %.",

keywords = "convolutional neural network, differential thermal voltammetry, incremental capacity analysis, Li-ion battery",

author = "Sibo Zeng and Sheng Chen and Yang Yu",

year = "2024",

month = feb,

day = "12",

doi = "10.3233/FAIA231383",

language = "English",

isbn = "9781643684840",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOP Publishing",

pages = "839--849",

editor = "Chenglizhao Chen",

booktitle = "Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023)",

note = "2023 5th International Conference on Artificial Intelligence Technologies and Applications , ICAITA 2023 ; Conference date: 30-06-2023 Through 02-07-2023",

url = "http://2023.ic-aita.org/",

}

Zeng, S, Chen, S & Yu, Y 2024, A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry. in C Chen (ed.), Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023). Frontiers in Artificial Intelligence and Applications, vol. 382, IOP Publishing, pp. 839-849, 2023 5th International Conference on Artificial Intelligence Technologies and Applications , Changchun, China, 30/06/23. https://doi.org/10.3233/FAIA231383

A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry. / Zeng, Sibo; Chen, Sheng; Yu, Yang.
Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023). ed. / Chenglizhao Chen. IOP Publishing, 2024. p. 839-849 (Frontiers in Artificial Intelligence and Applications; Vol. 382).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry

AU - Zeng, Sibo

AU - Chen, Sheng

AU - Yu, Yang

PY - 2024/2/12

Y1 - 2024/2/12

N2 - Precise estimation of Lithium-ion battery capacity is critical for the battery management system (BMS). This paper proposed an innovative method that combinates convolutional neural network and feature curves which are incremental capacity analysis (ICA) and differential thermal voltammetry (DTV). Rather than extracting feature parameters of the IC curve as done in available research, the present method uses the whole IC and DTV curves in a certain range of voltage as the input to avoid complicated annual feature extraction and correlation analysis. The result shows that the max error of capacity estimation is less than 4.46 %, the mean absolute percentage error is less than 1.29 % for each battery, and overall MAPE is below 1.19 %.

AB - Precise estimation of Lithium-ion battery capacity is critical for the battery management system (BMS). This paper proposed an innovative method that combinates convolutional neural network and feature curves which are incremental capacity analysis (ICA) and differential thermal voltammetry (DTV). Rather than extracting feature parameters of the IC curve as done in available research, the present method uses the whole IC and DTV curves in a certain range of voltage as the input to avoid complicated annual feature extraction and correlation analysis. The result shows that the max error of capacity estimation is less than 4.46 %, the mean absolute percentage error is less than 1.29 % for each battery, and overall MAPE is below 1.19 %.

KW - convolutional neural network

KW - differential thermal voltammetry

KW - incremental capacity analysis

KW - Li-ion battery

U2 - 10.3233/FAIA231383

DO - 10.3233/FAIA231383

M3 - Conference contribution

SN - 9781643684840

T3 - Frontiers in Artificial Intelligence and Applications

SP - 839

EP - 849

BT - Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023)

A2 - Chen, Chenglizhao

PB - IOP Publishing

T2 - 2023 5th International Conference on Artificial Intelligence Technologies and Applications

Y2 - 30 June 2023 through 2 July 2023

ER -

Zeng S, Chen S, Yu Y. A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry. In Chen C, editor, Proceedings of the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023). IOP Publishing. 2024. p. 839-849. (Frontiers in Artificial Intelligence and Applications). doi: 10.3233/FAIA231383

A deep learning capacity estimation method based on incremental capacity analysis and differential thermal voltammetry

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Documents and Links

Fingerprint

Cite this