Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model

Alireza Rastegarpanah; Yuan Wang; Rustam Stolkin

doi:10.1109/ICMRE54455.2022.9734081

Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model

Alireza Rastegarpanah, Yuan Wang, Rustam Stolkin

Metallurgy and Materials

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

Abstract

Accurate predicting the remaining useful life of lithium-ion batteries is essential for the market of Electrical Vehicles (EVs) and the battery industry. However, diverse ageing processes, substantial battery variability, and dynamic operating circumstances are identified as main challenges for predicting the remaining useful life (RUL) of lithium-ion batteries (LIBs). This study proposes a machine learning solution for estimating the RUL of LIBs by using a Convolutional neural network (CNN) model with an extra Long Short-term memory (LSTM) layer. The developed CNN-LSTM model is trained by a dataset containing data extracted from 124 commercial lithium-ion batteries cycled under fast-charging conditions. In this study, we use only 100 cycles to predict the remaining cycles. The developed model achieved a competitive loss value of 0.0206 and the mean absolute error value was 0.1099 for the current cycle of the battery and 0.0741 for the remaining ones.

Original language	English
Title of host publication	2022 8th International Conference on Mechatronics and Robotics Engineering (ICMRE)
Publisher	IEEE
Pages	73-78
Number of pages	6
ISBN (Electronic)	9781665483773, 9781665483766 (USB)
ISBN (Print)	9781665483780 (PoD)
DOIs	https://doi.org/10.1109/ICMRE54455.2022.9734081
Publication status	Published - 17 Mar 2022
Event	2022 The 8th International Conference on Mechatronics and Robotics Engineering - Munich, Germany Duration: 10 Feb 2022 → 12 Feb 2022

Publication series

Name	Mechatronics and Robotics Engineering (ICMRE), International Conference on

Conference

Conference	2022 The 8th International Conference on Mechatronics and Robotics Engineering
Abbreviated title	ICMRE 2022
Country/Territory	Germany
City	Munich
Period	10/02/22 → 12/02/22

Bibliographical note

Acknowledgments:
This research was conducted as part of the project called “Reuse and Recycling of Lithium-Ion Batteries” (RELIB). This work was supported by the Faraday Institution [grant number FIRG005].

Keywords

convolution neural network
Lithium-ion battery
remaining useful life
long short-term memory
electrical vehicle

UN SDGs

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

Access to Document

10.1109/ICMRE54455.2022.9734081

ReLIB - Faraday Challenge Fast Track proposal - Circular economy
Elliott, R., Lee, R., Allan, P., Slater, P., Stolkin, R., Walton, A., Overton, T., Reed, D., Anderson, P., Windridge, D. & Gough, R.
Engineering & Physical Science Research Council
1/03/18 → 30/06/21
Project: Research Councils

Cite this

Rastegarpanah, A., Wang, Y., & Stolkin, R. (2022). Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model. In 2022 8th International Conference on Mechatronics and Robotics Engineering (ICMRE) (pp. 73-78). Article 9734081 (Mechatronics and Robotics Engineering (ICMRE), International Conference on). IEEE. https://doi.org/10.1109/ICMRE54455.2022.9734081

@inproceedings{8da2ef76e04e428a8c4c023115a31b1b,

title = "Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model",

abstract = "Accurate predicting the remaining useful life of lithium-ion batteries is essential for the market of Electrical Vehicles (EVs) and the battery industry. However, diverse ageing processes, substantial battery variability, and dynamic operating circumstances are identified as main challenges for predicting the remaining useful life (RUL) of lithium-ion batteries (LIBs). This study proposes a machine learning solution for estimating the RUL of LIBs by using a Convolutional neural network (CNN) model with an extra Long Short-term memory (LSTM) layer. The developed CNN-LSTM model is trained by a dataset containing data extracted from 124 commercial lithium-ion batteries cycled under fast-charging conditions. In this study, we use only 100 cycles to predict the remaining cycles. The developed model achieved a competitive loss value of 0.0206 and the mean absolute error value was 0.1099 for the current cycle of the battery and 0.0741 for the remaining ones.",

keywords = "convolution neural network, Lithium-ion battery, remaining useful life, long short-term memory, electrical vehicle",

author = "Alireza Rastegarpanah and Yuan Wang and Rustam Stolkin",

note = "Acknowledgments: This research was conducted as part of the project called “Reuse and Recycling of Lithium-Ion Batteries” (RELIB). This work was supported by the Faraday Institution [grant number FIRG005]. ; 2022 The 8th International Conference on Mechatronics and Robotics Engineering, ICMRE 2022 ; Conference date: 10-02-2022 Through 12-02-2022",

year = "2022",

month = mar,

day = "17",

doi = "10.1109/ICMRE54455.2022.9734081",

language = "English",

isbn = "9781665483780 (PoD)",

series = "Mechatronics and Robotics Engineering (ICMRE), International Conference on",

publisher = "IEEE",

pages = "73--78",

booktitle = "2022 8th International Conference on Mechatronics and Robotics Engineering (ICMRE)",

}

Rastegarpanah, A, Wang, Y & Stolkin, R 2022, Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model. in 2022 8th International Conference on Mechatronics and Robotics Engineering (ICMRE)., 9734081, Mechatronics and Robotics Engineering (ICMRE), International Conference on, IEEE, pp. 73-78, 2022 The 8th International Conference on Mechatronics and Robotics Engineering, Munich, Germany, 10/02/22. https://doi.org/10.1109/ICMRE54455.2022.9734081

Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model. / Rastegarpanah, Alireza; Wang, Yuan; Stolkin, Rustam.
2022 8th International Conference on Mechatronics and Robotics Engineering (ICMRE). IEEE, 2022. p. 73-78 9734081 (Mechatronics and Robotics Engineering (ICMRE), International Conference on).

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

TY - GEN

T1 - Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model

AU - Rastegarpanah, Alireza

AU - Wang, Yuan

AU - Stolkin, Rustam

N1 - Acknowledgments: This research was conducted as part of the project called “Reuse and Recycling of Lithium-Ion Batteries” (RELIB). This work was supported by the Faraday Institution [grant number FIRG005].

PY - 2022/3/17

Y1 - 2022/3/17

N2 - Accurate predicting the remaining useful life of lithium-ion batteries is essential for the market of Electrical Vehicles (EVs) and the battery industry. However, diverse ageing processes, substantial battery variability, and dynamic operating circumstances are identified as main challenges for predicting the remaining useful life (RUL) of lithium-ion batteries (LIBs). This study proposes a machine learning solution for estimating the RUL of LIBs by using a Convolutional neural network (CNN) model with an extra Long Short-term memory (LSTM) layer. The developed CNN-LSTM model is trained by a dataset containing data extracted from 124 commercial lithium-ion batteries cycled under fast-charging conditions. In this study, we use only 100 cycles to predict the remaining cycles. The developed model achieved a competitive loss value of 0.0206 and the mean absolute error value was 0.1099 for the current cycle of the battery and 0.0741 for the remaining ones.

AB - Accurate predicting the remaining useful life of lithium-ion batteries is essential for the market of Electrical Vehicles (EVs) and the battery industry. However, diverse ageing processes, substantial battery variability, and dynamic operating circumstances are identified as main challenges for predicting the remaining useful life (RUL) of lithium-ion batteries (LIBs). This study proposes a machine learning solution for estimating the RUL of LIBs by using a Convolutional neural network (CNN) model with an extra Long Short-term memory (LSTM) layer. The developed CNN-LSTM model is trained by a dataset containing data extracted from 124 commercial lithium-ion batteries cycled under fast-charging conditions. In this study, we use only 100 cycles to predict the remaining cycles. The developed model achieved a competitive loss value of 0.0206 and the mean absolute error value was 0.1099 for the current cycle of the battery and 0.0741 for the remaining ones.

KW - convolution neural network

KW - Lithium-ion battery

KW - remaining useful life

KW - long short-term memory

KW - electrical vehicle

UR - https://publons.com/wos-op/publon/64155956/

U2 - 10.1109/ICMRE54455.2022.9734081

DO - 10.1109/ICMRE54455.2022.9734081

M3 - Conference contribution

SN - 9781665483780 (PoD)

T3 - Mechatronics and Robotics Engineering (ICMRE), International Conference on

SP - 73

EP - 78

BT - 2022 8th International Conference on Mechatronics and Robotics Engineering (ICMRE)

PB - IEEE

T2 - 2022 The 8th International Conference on Mechatronics and Robotics Engineering

Y2 - 10 February 2022 through 12 February 2022

ER -

Predicting the Remaining Life of Lithium-ion Batteries Using a CNN-LSTM Model

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Fingerprint

Projects

ReLIB - Faraday Challenge Fast Track proposal - Circular economy

Cite this