Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network

Mengyao Geng; Huixing Meng; Xu An; Jinduo Xing

doi:10.1109/ICRMS55680.2022.9944563

Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network

Mengyao Geng
, Huixing Meng^*
, Xu An
, Jinduo Xing

^*Corresponding author for this work

School of Mechatronical Engineering

Beijing Institute of Technology
Beijing University of Civil Engineering and Architecture

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

1 Citation (Scopus)

Abstract

The accurate degradation prediction of Lithium-ion batteries is beneficial to the reliability and safety of battery-driven systems. In this paper, a long short-term memory network (LSTM) model is utilized to predict the capacity degradation trend using partial charge and discharge features of Lithium-ion batteries. Firstly, significant features are extracted from the original charge and discharge data. Then the Pearson correlation coefficient is adopted to filter the features with high correlation coefficients. Selected features are subsequently treated as the input of the prediction model. Finally, a LSTM model is developed and associated hyperparameters are established by Adam algorithm. The proposed method is validated by experimental results on the NASA battery dataset.

Original language	English
Title of host publication	13th International Conference on Reliability, Maintainability, and Safety
Subtitle of host publication	Reliability and Safety of Intelligent Systems, ICRMS 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	265-269
Number of pages	5
ISBN (Electronic)	9781665486903
DOIs	https://doi.org/10.1109/ICRMS55680.2022.9944563
Publication status	Published - 2022
Event	13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022 - Hong Kong, China Duration: 21 Aug 2022 → 24 Aug 2022

Publication series

Name	13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022

Conference

Conference	13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022
Country/Territory	China
City	Hong Kong
Period	21/08/22 → 24/08/22

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

LSTM
Lithium-ion batteries
degradation
feature extraction

Access to Document

10.1109/ICRMS55680.2022.9944563

Cite this

Geng, M., Meng, H., An, X., & Xing, J. (2022). Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network. In 13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022 (pp. 265-269). (13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRMS55680.2022.9944563

Geng, Mengyao ; Meng, Huixing ; An, Xu et al. / Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network. 13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 265-269 (13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022).

@inproceedings{303ee0934afc41f997273c9e024d0834,

title = "Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network",

abstract = "The accurate degradation prediction of Lithium-ion batteries is beneficial to the reliability and safety of battery-driven systems. In this paper, a long short-term memory network (LSTM) model is utilized to predict the capacity degradation trend using partial charge and discharge features of Lithium-ion batteries. Firstly, significant features are extracted from the original charge and discharge data. Then the Pearson correlation coefficient is adopted to filter the features with high correlation coefficients. Selected features are subsequently treated as the input of the prediction model. Finally, a LSTM model is developed and associated hyperparameters are established by Adam algorithm. The proposed method is validated by experimental results on the NASA battery dataset.",

keywords = "LSTM, Lithium-ion batteries, degradation, feature extraction",

author = "Mengyao Geng and Huixing Meng and Xu An and Jinduo Xing",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022 ; Conference date: 21-08-2022 Through 24-08-2022",

year = "2022",

doi = "10.1109/ICRMS55680.2022.9944563",

language = "English",

series = "13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "265--269",

booktitle = "13th International Conference on Reliability, Maintainability, and Safety",

address = "United States",

}

Geng, M, Meng, H, An, X & Xing, J 2022, Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network. in 13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022. 13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022, Institute of Electrical and Electronics Engineers Inc., pp. 265-269, 13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022, Hong Kong, China, 21/08/22. https://doi.org/10.1109/ICRMS55680.2022.9944563

Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network. / Geng, Mengyao; Meng, Huixing; An, Xu et al.
13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 265-269 (13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022).

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

TY - GEN

T1 - Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network

AU - Geng, Mengyao

AU - Meng, Huixing

AU - An, Xu

AU - Xing, Jinduo

PY - 2022

Y1 - 2022

N2 - The accurate degradation prediction of Lithium-ion batteries is beneficial to the reliability and safety of battery-driven systems. In this paper, a long short-term memory network (LSTM) model is utilized to predict the capacity degradation trend using partial charge and discharge features of Lithium-ion batteries. Firstly, significant features are extracted from the original charge and discharge data. Then the Pearson correlation coefficient is adopted to filter the features with high correlation coefficients. Selected features are subsequently treated as the input of the prediction model. Finally, a LSTM model is developed and associated hyperparameters are established by Adam algorithm. The proposed method is validated by experimental results on the NASA battery dataset.

AB - The accurate degradation prediction of Lithium-ion batteries is beneficial to the reliability and safety of battery-driven systems. In this paper, a long short-term memory network (LSTM) model is utilized to predict the capacity degradation trend using partial charge and discharge features of Lithium-ion batteries. Firstly, significant features are extracted from the original charge and discharge data. Then the Pearson correlation coefficient is adopted to filter the features with high correlation coefficients. Selected features are subsequently treated as the input of the prediction model. Finally, a LSTM model is developed and associated hyperparameters are established by Adam algorithm. The proposed method is validated by experimental results on the NASA battery dataset.

KW - LSTM

KW - Lithium-ion batteries

KW - degradation

KW - feature extraction

UR - https://www.scopus.com/pages/publications/85143055570

U2 - 10.1109/ICRMS55680.2022.9944563

DO - 10.1109/ICRMS55680.2022.9944563

M3 - Conference contribution

AN - SCOPUS:85143055570

T3 - 13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022

SP - 265

EP - 269

BT - 13th International Conference on Reliability, Maintainability, and Safety

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th International Conference on Reliability, Maintainability, and Safety, ICRMS 2022

Y2 - 21 August 2022 through 24 August 2022

ER -

Geng M, Meng H, An X, Xing J. Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network. In 13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 265-269. (13th International Conference on Reliability, Maintainability, and Safety: Reliability and Safety of Intelligent Systems, ICRMS 2022). doi: 10.1109/ICRMS55680.2022.9944563

Degradation Prognostics of Lithium-ion Batteries Based on Partial Features and Long Short-term Memory Network

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this