SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation

Jiusi Zhang; Jilun Tian; Yuchen Jiang; Hao Luo; Cong Sheng Huang; Mo Yuen Chow; Shen Yin

doi:10.1109/IESES53571.2023.10253731

SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation

Jiusi Zhang
, Jilun Tian
, Yuchen Jiang
, Hao Luo
, Cong Sheng Huang
, Mo Yuen Chow
, Shen Yin

School of Astronautics

Harbin Institute of Technology
National Taipei University of Technology
North Carolina State University
Norwegian University of Science and Technology

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

3 Scopus citations

Abstract

Lithium-ion batteries are widely applied in sustainable energy conversion system. Consequently, it is of great research significance to accurately estimate the state of health (SOH) of batteries. To effectively model the input features at the spatial level, this article proposes a self-attention graph pooling convolutional network (SAGPCN) to estimate the SOH. The advantages of SAGPCN proposed in this paper can be reflected as follows: (1) The SAGPCN can consider node characteristics and graph topology, which focuses the attention on key parts of the graph. (2) The SAGPCN designs a self-attention mechanism to reserve significant nodes and delete secondary nodes, so as to optimize the network structure. A real-world dataset is adopted to evaluate the proposed battery SOH estimation approach in this paper. Experimental results represent that the estimation performance of the proposed SAGPCN is better than some data-driven SOH prediction approaches.

Original language	English
Title of host publication	2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350324754
DOIs	https://doi.org/10.1109/IESES53571.2023.10253731
State	Published - 2023
Event	3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023 - Shanghai, China Duration: 26 Jul 2023 → 28 Jul 2023

Publication series

Name	2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023

Conference

Conference	3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023
Country/Territory	China
City	Shanghai
Period	26/07/23 → 28/07/23

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Estimation
Lithium-ion battery
Self-attention graph pooling convolutional network
State of health

Access to Document

10.1109/IESES53571.2023.10253731

Cite this

Zhang, J., Tian, J., Jiang, Y., Luo, H., Huang, C. S., Chow, M. Y., & Yin, S. (2023). SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation. In 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023 (2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IESES53571.2023.10253731

Zhang, Jiusi ; Tian, Jilun ; Jiang, Yuchen et al. / SAGPCN : Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation. 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023).

@inproceedings{fd6145a951ca497083dc9fadb7ecdf82,

title = "SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation",

abstract = "Lithium-ion batteries are widely applied in sustainable energy conversion system. Consequently, it is of great research significance to accurately estimate the state of health (SOH) of batteries. To effectively model the input features at the spatial level, this article proposes a self-attention graph pooling convolutional network (SAGPCN) to estimate the SOH. The advantages of SAGPCN proposed in this paper can be reflected as follows: (1) The SAGPCN can consider node characteristics and graph topology, which focuses the attention on key parts of the graph. (2) The SAGPCN designs a self-attention mechanism to reserve significant nodes and delete secondary nodes, so as to optimize the network structure. A real-world dataset is adopted to evaluate the proposed battery SOH estimation approach in this paper. Experimental results represent that the estimation performance of the proposed SAGPCN is better than some data-driven SOH prediction approaches.",

keywords = "Estimation, Lithium-ion battery, Self-attention graph pooling convolutional network, State of health",

author = "Jiusi Zhang and Jilun Tian and Yuchen Jiang and Hao Luo and Huang, \{Cong Sheng\} and Chow, \{Mo Yuen\} and Shen Yin",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023 ; Conference date: 26-07-2023 Through 28-07-2023",

year = "2023",

doi = "10.1109/IESES53571.2023.10253731",

language = "英语",

series = "2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023",

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

booktitle = "2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023",

address = "美国",

}

Zhang, J, Tian, J, Jiang, Y , Luo, H, Huang, CS, Chow, MY & Yin, S 2023, SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation. in 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023. 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023, Institute of Electrical and Electronics Engineers Inc., 3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023, Shanghai, China, 26/07/23. https://doi.org/10.1109/IESES53571.2023.10253731

SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation. / Zhang, Jiusi; Tian, Jilun; Jiang, Yuchen et al.
2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023).

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

TY - GEN

T1 - SAGPCN

T2 - 3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023

AU - Zhang, Jiusi

AU - Tian, Jilun

AU - Jiang, Yuchen

AU - Luo, Hao

AU - Huang, Cong Sheng

AU - Chow, Mo Yuen

AU - Yin, Shen

PY - 2023

Y1 - 2023

N2 - Lithium-ion batteries are widely applied in sustainable energy conversion system. Consequently, it is of great research significance to accurately estimate the state of health (SOH) of batteries. To effectively model the input features at the spatial level, this article proposes a self-attention graph pooling convolutional network (SAGPCN) to estimate the SOH. The advantages of SAGPCN proposed in this paper can be reflected as follows: (1) The SAGPCN can consider node characteristics and graph topology, which focuses the attention on key parts of the graph. (2) The SAGPCN designs a self-attention mechanism to reserve significant nodes and delete secondary nodes, so as to optimize the network structure. A real-world dataset is adopted to evaluate the proposed battery SOH estimation approach in this paper. Experimental results represent that the estimation performance of the proposed SAGPCN is better than some data-driven SOH prediction approaches.

AB - Lithium-ion batteries are widely applied in sustainable energy conversion system. Consequently, it is of great research significance to accurately estimate the state of health (SOH) of batteries. To effectively model the input features at the spatial level, this article proposes a self-attention graph pooling convolutional network (SAGPCN) to estimate the SOH. The advantages of SAGPCN proposed in this paper can be reflected as follows: (1) The SAGPCN can consider node characteristics and graph topology, which focuses the attention on key parts of the graph. (2) The SAGPCN designs a self-attention mechanism to reserve significant nodes and delete secondary nodes, so as to optimize the network structure. A real-world dataset is adopted to evaluate the proposed battery SOH estimation approach in this paper. Experimental results represent that the estimation performance of the proposed SAGPCN is better than some data-driven SOH prediction approaches.

KW - Estimation

KW - Lithium-ion battery

KW - Self-attention graph pooling convolutional network

KW - State of health

UR - https://www.scopus.com/pages/publications/85174302866

U2 - 10.1109/IESES53571.2023.10253731

DO - 10.1109/IESES53571.2023.10253731

M3 - 会议稿件

AN - SCOPUS:85174302866

T3 - 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023

BT - 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 26 July 2023 through 28 July 2023

ER -

Zhang J, Tian J, Jiang Y , Luo H, Huang CS, Chow MY et al. SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation. In 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023). doi: 10.1109/IESES53571.2023.10253731

SAGPCN: Self-Attention Graph Pooling Convolutional Network for Battery State of Health Estimation

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this