Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation

Xin Sui; Shan He; Jinhao Meng; Remus Teodorescu; Daniel-Ioan Stroe

doi:10.1109/ECCE44975.2020.9236267

Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation

Xin Sui, Shan He, Jinhao Meng, Remus Teodorescu, Daniel-Ioan Stroe

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

1 Citationer (Scopus)

79 Downloads (Pure)

Abstract

Sample entropy (SE) has been used as a feature to estimate the state of health (SOH) of batteries as it can capture the voltage variation during battery degradation. However, the SE shows an obvious change when the battery is aged at different temperatures, leading to a decrease in the estimation accuracy. Therefore, the fuzzy entropy (FE), is proposed as a feature in terms of temperature variation. The FESOH is used as the input-output data pair of support vector machine, then the single-temperature model, full temperature model, and partial-temperature model are established. Compared with the SE-based method, FE-based method not only has better estimation accuracy, but also decreases the dependence on the size of training data. Finally, the effectiveness of the proposed method is verified by the experimental results.

Originalsprog	Engelsk
Titel	2020 IEEE Energy Conversion Congress and Exposition (ECCE)
Antal sider	6
Forlag	IEEE (Institute of Electrical and Electronics Engineers)
Publikationsdato	okt. 2020
Sider	4401-4406
ISBN (Trykt)	978-1-7281-5827-3
ISBN (Elektronisk)	978-1-7281-5826-6
DOI	https://doi.org/10.1109/ECCE44975.2020.9236267
Status	Udgivet - okt. 2020
Begivenhed	2020 IEEE Energy Conversion Congress and Exposition (ECCE 2020) - Detroit, USA Varighed: 11 okt. 2020 → 15 okt. 2020 https://www.ieee-ecce.org/2020/

Konference

Konference	2020 IEEE Energy Conversion Congress and Exposition (ECCE 2020)
Land/Område	USA
By	Detroit
Periode	11/10/2020 → 15/10/2020
Internetadresse	https://www.ieee-ecce.org/2020/

Navn	IEEE Energy Conversion Congress and Exposition
ISSN	2329-3721

Adgang til dokumentet

10.1109/ECCE44975.2020.9236267

Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature VariationAccepteret manuskript, 501 KB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Robust State of Health Estimation for Lithium-ion Batteries using Machine Learning
Sui, X. (PI (principal investigator)), Teodorescu, R. (Supervisor) & Stroe, D.-I. (Supervisor)
01/11/2018 → 31/10/2021
Projekter: Projekt › Ph.d.-projekt

Citationsformater

@inproceedings{525aa17da15c483a9ebb24f8664fb51d,

title = "Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation",

abstract = "Sample entropy (SE) has been used as a feature to estimate the state of health (SOH) of batteries as it can capture the voltage variation during battery degradation. However, the SE shows an obvious change when the battery is aged at different temperatures, leading to a decrease in the estimation accuracy. Therefore, the fuzzy entropy (FE), is proposed as a feature in terms of temperature variation. The FESOH is used as the input-output data pair of support vector machine, then the single-temperature model, full temperature model, and partial-temperature model are established. Compared with the SE-based method, FE-based method not only has better estimation accuracy, but also decreases the dependence on the size of training data. Finally, the effectiveness of the proposed method is verified by the experimental results.",

author = "Xin Sui and Shan He and Jinhao Meng and Remus Teodorescu and Daniel-Ioan Stroe",

year = "2020",

month = oct,

doi = "10.1109/ECCE44975.2020.9236267",

language = "English",

isbn = "978-1-7281-5827-3",

series = "IEEE Energy Conversion Congress and Exposition",

pages = "4401--4406",

booktitle = "2020 IEEE Energy Conversion Congress and Exposition (ECCE)",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

address = "United States",

note = "2020 IEEE Energy Conversion Congress and Exposition (ECCE 2020), ECCE 2020 ; Conference date: 11-10-2020 Through 15-10-2020",

url = "https://www.ieee-ecce.org/2020/",

}

Sui, X , He, S, Meng, J, Teodorescu, R & Stroe, D-I 2020, Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation. i 2020 IEEE Energy Conversion Congress and Exposition (ECCE). IEEE (Institute of Electrical and Electronics Engineers), IEEE Energy Conversion Congress and Exposition, s. 4401-4406, 2020 IEEE Energy Conversion Congress and Exposition (ECCE 2020), Detroit, Michigan, USA, 11/10/2020. https://doi.org/10.1109/ECCE44975.2020.9236267

Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation. / Sui, Xin ; He, Shan; Meng, Jinhao et al.
2020 IEEE Energy Conversion Congress and Exposition (ECCE). IEEE (Institute of Electrical and Electronics Engineers), 2020. s. 4401-4406 (IEEE Energy Conversion Congress and Exposition).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation

AU - Sui, Xin

AU - He, Shan

AU - Meng, Jinhao

AU - Teodorescu, Remus

AU - Stroe, Daniel-Ioan

PY - 2020/10

Y1 - 2020/10

N2 - Sample entropy (SE) has been used as a feature to estimate the state of health (SOH) of batteries as it can capture the voltage variation during battery degradation. However, the SE shows an obvious change when the battery is aged at different temperatures, leading to a decrease in the estimation accuracy. Therefore, the fuzzy entropy (FE), is proposed as a feature in terms of temperature variation. The FESOH is used as the input-output data pair of support vector machine, then the single-temperature model, full temperature model, and partial-temperature model are established. Compared with the SE-based method, FE-based method not only has better estimation accuracy, but also decreases the dependence on the size of training data. Finally, the effectiveness of the proposed method is verified by the experimental results.

AB - Sample entropy (SE) has been used as a feature to estimate the state of health (SOH) of batteries as it can capture the voltage variation during battery degradation. However, the SE shows an obvious change when the battery is aged at different temperatures, leading to a decrease in the estimation accuracy. Therefore, the fuzzy entropy (FE), is proposed as a feature in terms of temperature variation. The FESOH is used as the input-output data pair of support vector machine, then the single-temperature model, full temperature model, and partial-temperature model are established. Compared with the SE-based method, FE-based method not only has better estimation accuracy, but also decreases the dependence on the size of training data. Finally, the effectiveness of the proposed method is verified by the experimental results.

U2 - 10.1109/ECCE44975.2020.9236267

DO - 10.1109/ECCE44975.2020.9236267

M3 - Article in proceeding

SN - 978-1-7281-5827-3

T3 - IEEE Energy Conversion Congress and Exposition

SP - 4401

EP - 4406

BT - 2020 IEEE Energy Conversion Congress and Exposition (ECCE)

PB - IEEE (Institute of Electrical and Electronics Engineers)

T2 - 2020 IEEE Energy Conversion Congress and Exposition (ECCE 2020)

Y2 - 11 October 2020 through 15 October 2020

ER -

Sui X , He S, Meng J, Teodorescu R , Stroe DI. Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation. I 2020 IEEE Energy Conversion Congress and Exposition (ECCE). IEEE (Institute of Electrical and Electronics Engineers). 2020. s. 4401-4406. (IEEE Energy Conversion Congress and Exposition). doi: 10.1109/ECCE44975.2020.9236267

Fuzzy Entropy-Based State of Health Estimation of LiFePO4 Batteries Considering Temperature Variation

Abstract

Konference

Adgang til dokumentet

AUB Link

Fingeraftryk

Projekter

Robust State of Health Estimation for Lithium-ion Batteries using Machine Learning

Citationsformater