Ultrafast Feature Extraction for Lithium-Ion Battery Health Assessment

Xin Sui; Shan He; Remus Teodorescu

doi:10.23919/EPE23ECCEEurope58414.2023.10264315

Ultrafast Feature Extraction for Lithium-Ion Battery Health Assessment

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

Machine learning (ML) becomes an important technology in battery health assessment. The mapping from feature usually extracted from charging voltage or temperature to unmeasurable state of health (SOH) can be found by training a ML-based SOH estimator. However, the feature may become invalid when operation conditions change or be inaccessible from incomplete charging. For tackling these challenges, various entropies are investigated thoughtfully. Afterwards, spectral entropy and its variants, i.e., composite multi-scale entropy and hierarchical entropy are screened out. Ultrafast SOH feature extraction is therefore achieved where only 2 seconds of voltage data is needed. Finally, the effectiveness of the proposed method is verified by using the accelerated aging dataset from NMC batteries.

Original language	English
Title of host publication	2023 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe
Publisher	IEEE (Institute of Electrical and Electronics Engineers)
Publication date	2023
Article number	10264315
ISBN (Electronic)	9789075815412
DOIs	https://doi.org/10.23919/EPE23ECCEEurope58414.2023.10264315
Publication status	Published - 2023
Event	25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe - Aalborg, Denmark Duration: 4 Sept 2023 → 8 Sept 2023

Conference

Conference	25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe
Country/Territory	Denmark
City	Aalborg
Period	04/09/2023 → 08/09/2023

Bibliographical note

Publisher Copyright:
© 2023 EPE Association.

Keywords

Entropy
Feature engineering
Health assessment
Lithium-ion battery
Machine learning

Access to Document

10.23919/EPE23ECCEEurope58414.2023.10264315

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{f36da04a8f184c6ab7da889c0e229167,

title = "Ultrafast Feature Extraction for Lithium-Ion Battery Health Assessment",

abstract = "Machine learning (ML) becomes an important technology in battery health assessment. The mapping from feature usually extracted from charging voltage or temperature to unmeasurable state of health (SOH) can be found by training a ML-based SOH estimator. However, the feature may become invalid when operation conditions change or be inaccessible from incomplete charging. For tackling these challenges, various entropies are investigated thoughtfully. Afterwards, spectral entropy and its variants, i.e., composite multi-scale entropy and hierarchical entropy are screened out. Ultrafast SOH feature extraction is therefore achieved where only 2 seconds of voltage data is needed. Finally, the effectiveness of the proposed method is verified by using the accelerated aging dataset from NMC batteries.",

keywords = "Entropy, Feature engineering, Health assessment, Lithium-ion battery, Machine learning",

author = "Xin Sui and Shan He and Remus Teodorescu",

note = "Publisher Copyright: {\textcopyright} 2023 EPE Association.; 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe ; Conference date: 04-09-2023 Through 08-09-2023",

year = "2023",

doi = "10.23919/EPE23ECCEEurope58414.2023.10264315",

language = "English",

booktitle = "2023 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe",

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

address = "United States",

}

Sui, X , He, S & Teodorescu, R 2023, Ultrafast Feature Extraction for Lithium-Ion Battery Health Assessment. in 2023 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe., 10264315, IEEE (Institute of Electrical and Electronics Engineers), 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe, Aalborg, Denmark, 04/09/2023. https://doi.org/10.23919/EPE23ECCEEurope58414.2023.10264315

Ultrafast Feature Extraction for Lithium-Ion Battery Health Assessment. / Sui, Xin ; He, Shan ; Teodorescu, Remus.
2023 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe. IEEE (Institute of Electrical and Electronics Engineers), 2023. 10264315.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Ultrafast Feature Extraction for Lithium-Ion Battery Health Assessment

AU - Sui, Xin

AU - He, Shan

AU - Teodorescu, Remus

PY - 2023

Y1 - 2023

N2 - Machine learning (ML) becomes an important technology in battery health assessment. The mapping from feature usually extracted from charging voltage or temperature to unmeasurable state of health (SOH) can be found by training a ML-based SOH estimator. However, the feature may become invalid when operation conditions change or be inaccessible from incomplete charging. For tackling these challenges, various entropies are investigated thoughtfully. Afterwards, spectral entropy and its variants, i.e., composite multi-scale entropy and hierarchical entropy are screened out. Ultrafast SOH feature extraction is therefore achieved where only 2 seconds of voltage data is needed. Finally, the effectiveness of the proposed method is verified by using the accelerated aging dataset from NMC batteries.

AB - Machine learning (ML) becomes an important technology in battery health assessment. The mapping from feature usually extracted from charging voltage or temperature to unmeasurable state of health (SOH) can be found by training a ML-based SOH estimator. However, the feature may become invalid when operation conditions change or be inaccessible from incomplete charging. For tackling these challenges, various entropies are investigated thoughtfully. Afterwards, spectral entropy and its variants, i.e., composite multi-scale entropy and hierarchical entropy are screened out. Ultrafast SOH feature extraction is therefore achieved where only 2 seconds of voltage data is needed. Finally, the effectiveness of the proposed method is verified by using the accelerated aging dataset from NMC batteries.

KW - Entropy

KW - Feature engineering

KW - Health assessment

KW - Lithium-ion battery

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85175196288&partnerID=8YFLogxK

U2 - 10.23919/EPE23ECCEEurope58414.2023.10264315

DO - 10.23919/EPE23ECCEEurope58414.2023.10264315

M3 - Article in proceeding

AN - SCOPUS:85175196288

BT - 2023 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe

PB - IEEE (Institute of Electrical and Electronics Engineers)

T2 - 25th European Conference on Power Electronics and Applications, EPE 2023 ECCE Europe

Y2 - 4 September 2023 through 8 September 2023

ER -

Ultrafast Feature Extraction for Lithium-Ion Battery Health Assessment

Abstract

Conference

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this