State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks

Qian Liu; Wanjun Lei; Yichao Gao; Jiaqi Zhao; Yize Liu

doi:10.1109/PEAS58692.2023.10395250

State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks

Qian Liu
, Wanjun Lei
, Yichao Gao
, Jiaqi Zhao
, Yize Liu

School of Electrical Engineering

Xi'an Jiaotong University

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

Abstract

There is increasingly active work related to Lithium-ion batteries which are widely used for mobile power products, electric vehicles and smart grids. State of charge (SOC) and state of energy (SOE) are key to Lithium-ion battery management. In order to improve accuracy of the battery model, the fractional-order equivalent circuit is used for Lithium-ion battery modeling and its parameters are obtained by genetic algorithm (GA). The developed method for co-estimation of SOC and SOE combines adaptive extended Kalman filter (AEKF) and the recurrent neural network (RNN) with long-short term memory (LSTM) cells. Experiments are set to evaluate the effectiveness of the proposed method under different working conditions. The mean absolute error (MAE) achieved on two working conditions is below 0.5%, indicating the AEKF-LSTM-RNN has excellent capability of achieving accurate and robust battery state estimation.

Original language	English
Title of host publication	PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	892-899
Number of pages	8
ISBN (Electronic)	9798350313765
DOIs	https://doi.org/10.1109/PEAS58692.2023.10395250
State	Published - 2023
Event	2nd IEEE International Power Electronics and Application Symposium, PEAS 2023 - Guangzhou, China Duration: 10 Nov 2023 → 13 Nov 2023

Publication series

Name	PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings

Conference

Conference	2nd IEEE International Power Electronics and Application Symposium, PEAS 2023
Country/Territory	China
City	Guangzhou
Period	10/11/23 → 13/11/23

Keywords

Lithium-ion battery
adaptive extended Kalman filter
long short-term memory
state of charge
state of energy

UN SDGs

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

Access to Document

10.1109/PEAS58692.2023.10395250

Cite this

Liu, Q., Lei, W., Gao, Y., Zhao, J., & Liu, Y. (2023). State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks. In PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings (pp. 892-899). (PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PEAS58692.2023.10395250

Liu, Qian ; Lei, Wanjun ; Gao, Yichao et al. / State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks. PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 892-899 (PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings).

@inproceedings{04cbc2cb2aa2456a98399d0a799e0c5d,

title = "State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks",

abstract = "There is increasingly active work related to Lithium-ion batteries which are widely used for mobile power products, electric vehicles and smart grids. State of charge (SOC) and state of energy (SOE) are key to Lithium-ion battery management. In order to improve accuracy of the battery model, the fractional-order equivalent circuit is used for Lithium-ion battery modeling and its parameters are obtained by genetic algorithm (GA). The developed method for co-estimation of SOC and SOE combines adaptive extended Kalman filter (AEKF) and the recurrent neural network (RNN) with long-short term memory (LSTM) cells. Experiments are set to evaluate the effectiveness of the proposed method under different working conditions. The mean absolute error (MAE) achieved on two working conditions is below 0.5\%, indicating the AEKF-LSTM-RNN has excellent capability of achieving accurate and robust battery state estimation.",

keywords = "Lithium-ion battery, adaptive extended Kalman filter, long short-term memory, state of charge, state of energy",

author = "Qian Liu and Wanjun Lei and Yichao Gao and Jiaqi Zhao and Yize Liu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2nd IEEE International Power Electronics and Application Symposium, PEAS 2023 ; Conference date: 10-11-2023 Through 13-11-2023",

year = "2023",

doi = "10.1109/PEAS58692.2023.10395250",

language = "英语",

series = "PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings",

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

pages = "892--899",

booktitle = "PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings",

}

Liu, Q, Lei, W, Gao, Y, Zhao, J & Liu, Y 2023, State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks. in PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings. PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 892-899, 2nd IEEE International Power Electronics and Application Symposium, PEAS 2023, Guangzhou, China, 10/11/23. https://doi.org/10.1109/PEAS58692.2023.10395250

State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks. / Liu, Qian; Lei, Wanjun; Gao, Yichao et al.
PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. p. 892-899 (PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings).

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

TY - GEN

T1 - State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks

AU - Liu, Qian

AU - Lei, Wanjun

AU - Gao, Yichao

AU - Zhao, Jiaqi

AU - Liu, Yize

PY - 2023

Y1 - 2023

N2 - There is increasingly active work related to Lithium-ion batteries which are widely used for mobile power products, electric vehicles and smart grids. State of charge (SOC) and state of energy (SOE) are key to Lithium-ion battery management. In order to improve accuracy of the battery model, the fractional-order equivalent circuit is used for Lithium-ion battery modeling and its parameters are obtained by genetic algorithm (GA). The developed method for co-estimation of SOC and SOE combines adaptive extended Kalman filter (AEKF) and the recurrent neural network (RNN) with long-short term memory (LSTM) cells. Experiments are set to evaluate the effectiveness of the proposed method under different working conditions. The mean absolute error (MAE) achieved on two working conditions is below 0.5%, indicating the AEKF-LSTM-RNN has excellent capability of achieving accurate and robust battery state estimation.

AB - There is increasingly active work related to Lithium-ion batteries which are widely used for mobile power products, electric vehicles and smart grids. State of charge (SOC) and state of energy (SOE) are key to Lithium-ion battery management. In order to improve accuracy of the battery model, the fractional-order equivalent circuit is used for Lithium-ion battery modeling and its parameters are obtained by genetic algorithm (GA). The developed method for co-estimation of SOC and SOE combines adaptive extended Kalman filter (AEKF) and the recurrent neural network (RNN) with long-short term memory (LSTM) cells. Experiments are set to evaluate the effectiveness of the proposed method under different working conditions. The mean absolute error (MAE) achieved on two working conditions is below 0.5%, indicating the AEKF-LSTM-RNN has excellent capability of achieving accurate and robust battery state estimation.

KW - Lithium-ion battery

KW - adaptive extended Kalman filter

KW - long short-term memory

KW - state of charge

KW - state of energy

UR - https://www.scopus.com/pages/publications/85187267806

U2 - 10.1109/PEAS58692.2023.10395250

DO - 10.1109/PEAS58692.2023.10395250

M3 - 会议稿件

AN - SCOPUS:85187267806

T3 - PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings

SP - 892

EP - 899

BT - PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE International Power Electronics and Application Symposium, PEAS 2023

Y2 - 10 November 2023 through 13 November 2023

ER -

Liu Q, Lei W, Gao Y, Zhao J, Liu Y. State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks. In PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. p. 892-899. (PEAS 2023 - 2023 IEEE 2nd International Power Electronics and Application Symposium, Conference Proceedings). doi: 10.1109/PEAS58692.2023.10395250

State Estimation of Lithium-ion Batteries Using Adaptive Extended Kalman Filter and Long Short-Term Memory Networks

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this