Remaining Useful Life Prediction Based on CNN Method

Chang’an Wei; Shuchen Yue; Shuang Bai

doi:10.1007/978-981-19-3927-3_30

Remaining Useful Life Prediction Based on CNN Method

Chang’an Wei^*
, Shuchen Yue
, Shuang Bai

^*Corresponding author for this work

School of Electronics and Information Engineering

Harbin Institute of Technology
Ltd.

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

3 Scopus citations

Abstract

Lithium battery remaining life prediction plays an important role in battery health management system. In recent years, with the continuous development of artificial intelligence and deep learning, its various methods have gone deep into various fields and brought new methods to battery life prediction. This paper studies the public data set of lithium battery, preprocesses the data set such as feature extraction, and constructs a convolution neural network model to predict the remaining life of Lithium-ion battery. This paper studies NASA’s PCoE Li-ion battery data, analysed its original parameters and obtained the typical features, which are sent into constructed network. Also, this study compares CNN prediction to other data-driven RUL prediction approaches with an eye on the accuracy and RMSE. The final experiment shows that the life prediction result is better than other existing methods.

Original language	English
Title of host publication	6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021
Editors	Yuriy S. Shmaliy, Abdelhalim Abdelnaby Zekry
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	309-316
Number of pages	8
ISBN (Print)	9789811939266
DOIs	https://doi.org/10.1007/978-981-19-3927-3_30
State	Published - 2022
Event	6th International Conference on Computing, Control, and Industrial Engineering, CCIE 2021 - Virtual, Online Duration: 15 Jan 2022 → 16 Jan 2022

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	920 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	6th International Conference on Computing, Control, and Industrial Engineering, CCIE 2021
City	Virtual, Online
Period	15/01/22 → 16/01/22

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

CNN model
Lithium-ion battery
Remaining life prediction

Access to Document

10.1007/978-981-19-3927-3_30

Cite this

Wei, C., Yue, S., & Bai, S. (2022). Remaining Useful Life Prediction Based on CNN Method. In Y. S. Shmaliy, & A. Abdelnaby Zekry (Eds.), 6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021 (pp. 309-316). (Lecture Notes in Electrical Engineering; Vol. 920 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-3927-3_30

Wei, Chang’an ; Yue, Shuchen ; Bai, Shuang. / Remaining Useful Life Prediction Based on CNN Method. 6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021. editor / Yuriy S. Shmaliy ; Abdelhalim Abdelnaby Zekry. Springer Science and Business Media Deutschland GmbH, 2022. pp. 309-316 (Lecture Notes in Electrical Engineering).

@inproceedings{0aea9817a0f846218cae4ea572ba2b71,

title = "Remaining Useful Life Prediction Based on CNN Method",

abstract = "Lithium battery remaining life prediction plays an important role in battery health management system. In recent years, with the continuous development of artificial intelligence and deep learning, its various methods have gone deep into various fields and brought new methods to battery life prediction. This paper studies the public data set of lithium battery, preprocesses the data set such as feature extraction, and constructs a convolution neural network model to predict the remaining life of Lithium-ion battery. This paper studies NASA{\textquoteright}s PCoE Li-ion battery data, analysed its original parameters and obtained the typical features, which are sent into constructed network. Also, this study compares CNN prediction to other data-driven RUL prediction approaches with an eye on the accuracy and RMSE. The final experiment shows that the life prediction result is better than other existing methods.",

keywords = "CNN model, Lithium-ion battery, Remaining life prediction",

author = "Chang{\textquoteright}an Wei and Shuchen Yue and Shuang Bai",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 6th International Conference on Computing, Control, and Industrial Engineering, CCIE 2021 ; Conference date: 15-01-2022 Through 16-01-2022",

year = "2022",

doi = "10.1007/978-981-19-3927-3\_30",

language = "英语",

isbn = "9789811939266",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "309--316",

editor = "\{S. Shmaliy\}, Yuriy and \{Abdelnaby Zekry\}, Abdelhalim",

booktitle = "6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021",

address = "德国",

}

Wei, C, Yue, S & Bai, S 2022, Remaining Useful Life Prediction Based on CNN Method. in Y S. Shmaliy & A Abdelnaby Zekry (eds), 6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021. Lecture Notes in Electrical Engineering, vol. 920 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 309-316, 6th International Conference on Computing, Control, and Industrial Engineering, CCIE 2021, Virtual, Online, 15/01/22. https://doi.org/10.1007/978-981-19-3927-3_30

Remaining Useful Life Prediction Based on CNN Method. / Wei, Chang’an; Yue, Shuchen; Bai, Shuang.
6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021. ed. / Yuriy S. Shmaliy; Abdelhalim Abdelnaby Zekry. Springer Science and Business Media Deutschland GmbH, 2022. p. 309-316 (Lecture Notes in Electrical Engineering; Vol. 920 LNEE).

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

TY - GEN

T1 - Remaining Useful Life Prediction Based on CNN Method

AU - Wei, Chang’an

AU - Yue, Shuchen

AU - Bai, Shuang

PY - 2022

Y1 - 2022

N2 - Lithium battery remaining life prediction plays an important role in battery health management system. In recent years, with the continuous development of artificial intelligence and deep learning, its various methods have gone deep into various fields and brought new methods to battery life prediction. This paper studies the public data set of lithium battery, preprocesses the data set such as feature extraction, and constructs a convolution neural network model to predict the remaining life of Lithium-ion battery. This paper studies NASA’s PCoE Li-ion battery data, analysed its original parameters and obtained the typical features, which are sent into constructed network. Also, this study compares CNN prediction to other data-driven RUL prediction approaches with an eye on the accuracy and RMSE. The final experiment shows that the life prediction result is better than other existing methods.

AB - Lithium battery remaining life prediction plays an important role in battery health management system. In recent years, with the continuous development of artificial intelligence and deep learning, its various methods have gone deep into various fields and brought new methods to battery life prediction. This paper studies the public data set of lithium battery, preprocesses the data set such as feature extraction, and constructs a convolution neural network model to predict the remaining life of Lithium-ion battery. This paper studies NASA’s PCoE Li-ion battery data, analysed its original parameters and obtained the typical features, which are sent into constructed network. Also, this study compares CNN prediction to other data-driven RUL prediction approaches with an eye on the accuracy and RMSE. The final experiment shows that the life prediction result is better than other existing methods.

KW - CNN model

KW - Lithium-ion battery

KW - Remaining life prediction

UR - https://www.scopus.com/pages/publications/85135082314

U2 - 10.1007/978-981-19-3927-3_30

DO - 10.1007/978-981-19-3927-3_30

M3 - 会议稿件

AN - SCOPUS:85135082314

SN - 9789811939266

T3 - Lecture Notes in Electrical Engineering

SP - 309

EP - 316

BT - 6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021

A2 - S. Shmaliy, Yuriy

A2 - Abdelnaby Zekry, Abdelhalim

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th International Conference on Computing, Control, and Industrial Engineering, CCIE 2021

Y2 - 15 January 2022 through 16 January 2022

ER -

Wei C, Yue S, Bai S. Remaining Useful Life Prediction Based on CNN Method. In S. Shmaliy Y, Abdelnaby Zekry A, editors, 6th International Technical Conference on Advances in Computing, Control and Industrial Engineering, CCIE 2021. Springer Science and Business Media Deutschland GmbH. 2022. p. 309-316. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-19-3927-3_30

Remaining Useful Life Prediction Based on CNN Method

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this