A data-driven method based on recurrent neural network method for online capacity estimation of lithium-ion batteries

Sahar Khaleghi; Seyed Hamidreza Beheshti; Maitane Berecibar; Joeri Van Mierlo

doi:10.1109/VPPC49601.2020.9330987

A data-driven method based on recurrent neural network method for online capacity estimation of lithium-ion batteries

Sahar Khaleghi, Seyed Hamidreza Beheshti, Maitane Berecibar, Joeri Van Mierlo

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

Abstract

lithium-ion batteries are a convenient choice for various energy storage systems (ESS) such as electric and hybrid vehicles. Nevertheless, the characterization of capacity degradation is critical to ensure the proper performance of lithium-ion batteries. This paper presents a data-driven technique based on a recurrent neural network called nonlinear autoregressive exogenous neural network (NARX) to estimate the capacity degradation of lithium-ion batteries. The voltage charging curves, extracted from twelve nickel manganese cobalt oxide (NMC) cells with different aging trends are used to develop a predictive model for capacity estimation. The results demonstrate that the proposed model is able to estimate capacity with high accuracy and low complexity.

Original language	English
Title of host publication	2020 IEEE Vehicle Power and Propulsion Conference (VPPC)
Place of Publication	Gijon, Spain
Publisher	IEEE
Pages	1 to 7
Number of pages	7
ISBN (Electronic)	9781728189598
DOIs	https://doi.org/10.1109/VPPC49601.2020.9330987
Publication status	Published - Nov 2020

Access to Document

10.1109/VPPC49601.2020.9330987

Fingerprint Dive into the research topics of 'A data-driven method based on recurrent neural network method for online capacity estimation of lithium-ion batteries'. Together they form a unique fingerprint.

Cite this

@inproceedings{ffcd9e26adaf4729850e27a7f8ea7539,

title = "A data-driven method based on recurrent neural network method for online capacity estimation of lithium-ion batteries",

abstract = "lithium-ion batteries are a convenient choice for various energy storage systems (ESS) such as electric and hybrid vehicles. Nevertheless, the characterization of capacity degradation is critical to ensure the proper performance of lithium-ion batteries. This paper presents a data-driven technique based on a recurrent neural network called nonlinear autoregressive exogenous neural network (NARX) to estimate the capacity degradation of lithium-ion batteries. The voltage charging curves, extracted from twelve nickel manganese cobalt oxide (NMC) cells with different aging trends are used to develop a predictive model for capacity estimation. The results demonstrate that the proposed model is able to estimate capacity with high accuracy and low complexity.",

author = "Sahar Khaleghi and Beheshti, {Seyed Hamidreza} and Maitane Berecibar and {Van Mierlo}, Joeri",

year = "2020",

month = "11",

doi = "10.1109/VPPC49601.2020.9330987",

language = "English",

pages = "1 to 7",

booktitle = "2020 IEEE Vehicle Power and Propulsion Conference (VPPC)",

publisher = "IEEE",

}

A data-driven method based on recurrent neural network method for online capacity estimation of lithium-ion batteries. / Khaleghi, Sahar ; Beheshti, Seyed Hamidreza ; Berecibar, Maitane ; Van Mierlo, Joeri.

2020 IEEE Vehicle Power and Propulsion Conference (VPPC). Gijon, Spain : IEEE, 2020. p. 1 to 7 9330987.

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

TY - GEN

T1 - A data-driven method based on recurrent neural network method for online capacity estimation of lithium-ion batteries

AU - Khaleghi, Sahar

AU - Beheshti, Seyed Hamidreza

AU - Berecibar, Maitane

AU - Van Mierlo, Joeri

PY - 2020/11

Y1 - 2020/11

N2 - lithium-ion batteries are a convenient choice for various energy storage systems (ESS) such as electric and hybrid vehicles. Nevertheless, the characterization of capacity degradation is critical to ensure the proper performance of lithium-ion batteries. This paper presents a data-driven technique based on a recurrent neural network called nonlinear autoregressive exogenous neural network (NARX) to estimate the capacity degradation of lithium-ion batteries. The voltage charging curves, extracted from twelve nickel manganese cobalt oxide (NMC) cells with different aging trends are used to develop a predictive model for capacity estimation. The results demonstrate that the proposed model is able to estimate capacity with high accuracy and low complexity.

AB - lithium-ion batteries are a convenient choice for various energy storage systems (ESS) such as electric and hybrid vehicles. Nevertheless, the characterization of capacity degradation is critical to ensure the proper performance of lithium-ion batteries. This paper presents a data-driven technique based on a recurrent neural network called nonlinear autoregressive exogenous neural network (NARX) to estimate the capacity degradation of lithium-ion batteries. The voltage charging curves, extracted from twelve nickel manganese cobalt oxide (NMC) cells with different aging trends are used to develop a predictive model for capacity estimation. The results demonstrate that the proposed model is able to estimate capacity with high accuracy and low complexity.

UR - http://www.scopus.com/inward/record.url?scp=85101958704&partnerID=8YFLogxK

U2 - 10.1109/VPPC49601.2020.9330987

DO - 10.1109/VPPC49601.2020.9330987

M3 - Conference paper

SP - 1 to 7

BT - 2020 IEEE Vehicle Power and Propulsion Conference (VPPC)

PB - IEEE

CY - Gijon, Spain

ER -