An evolutionary framework for lithium-ion battery state of health estimation

Lei Cai, Meng Jinhao, Daniel-Ioan Stroe, Luo Guangzhao, Remus Teodorescu

Research output: Contribution to journalJournal articleResearchpeer-review

6 Citations (Scopus)

Abstract

Battery energy storage system expands the flexibility of the electricity grid, which facilitates the extensive usage of renewable energies in industrial applications. In order to ensure the techno-economical reliability of the battery energy storage system, managing the lifespan of each battery is critical. In this paper, a novel evolutionary framework is proposed to estimate the Lithium-ion battery state of health, which uniformly optimizes the two key processes of establishing a data driven estimator. The features in the degradation process of a battery are conveniently measured by a group of current pulses, which last only few seconds. The proposed evolutionary framework selects the most efficient combination of the short-term features from the current pulse test, and guarantees an optimal training process simultaneously. A hybrid encoding technology is applied to mix the feature extraction and the parameters of support vector regression in one chromosome. With the benefit of the proposed evolutionary framework, the battery state of health is estimated by using support vector regression and genetic algorithm in a more efficient way. A mission profile corresponding to batteries providing the primary frequency regulation service to the power system is used to cycle two Lithium-ion batteries for the validation of the proposed method.
Original languageEnglish
JournalJournal of Power Sources
Volume412
Pages (from-to)615-622
Number of pages8
ISSN0378-7753
DOIs
Publication statusPublished - Feb 2019

Fingerprint

Energy storage
health
electric batteries
lithium
Health
Chromosomes
Industrial applications
Feature extraction
ions
Electricity
Genetic algorithms
Degradation
energy storage
regression analysis
frequency control
renewable energy
Lithium-ion batteries
chromosomes
electricity
pulses

Keywords

  • State of health
  • Lithium-ion battery
  • Evolutionary framework
  • Feature extraction
  • Data driven method

Cite this

@article{eb844fddf25049c29f601ac09f2cae30,
title = "An evolutionary framework for lithium-ion battery state of health estimation",
abstract = "Battery energy storage system expands the flexibility of the electricity grid, which facilitates the extensive usage of renewable energies in industrial applications. In order to ensure the techno-economical reliability of the battery energy storage system, managing the lifespan of each battery is critical. In this paper, a novel evolutionary framework is proposed to estimate the Lithium-ion battery state of health, which uniformly optimizes the two key processes of establishing a data driven estimator. The features in the degradation process of a battery are conveniently measured by a group of current pulses, which last only few seconds. The proposed evolutionary framework selects the most efficient combination of the short-term features from the current pulse test, and guarantees an optimal training process simultaneously. A hybrid encoding technology is applied to mix the feature extraction and the parameters of support vector regression in one chromosome. With the benefit of the proposed evolutionary framework, the battery state of health is estimated by using support vector regression and genetic algorithm in a more efficient way. A mission profile corresponding to batteries providing the primary frequency regulation service to the power system is used to cycle two Lithium-ion batteries for the validation of the proposed method.",
keywords = "State of health, Lithium-ion battery, Evolutionary framework, Feature extraction, Data driven method",
author = "Lei Cai and Meng Jinhao and Daniel-Ioan Stroe and Luo Guangzhao and Remus Teodorescu",
year = "2019",
month = "2",
doi = "10.1016/j.jpowsour.2018.12.001",
language = "English",
volume = "412",
pages = "615--622",
journal = "Journal of Power Sources",
issn = "0378-7753",
publisher = "Elsevier",

}

An evolutionary framework for lithium-ion battery state of health estimation. / Cai, Lei; Jinhao, Meng; Stroe, Daniel-Ioan; Guangzhao, Luo; Teodorescu, Remus.

In: Journal of Power Sources, Vol. 412, 02.2019, p. 615-622.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - An evolutionary framework for lithium-ion battery state of health estimation

AU - Cai, Lei

AU - Jinhao, Meng

AU - Stroe, Daniel-Ioan

AU - Guangzhao, Luo

AU - Teodorescu, Remus

PY - 2019/2

Y1 - 2019/2

N2 - Battery energy storage system expands the flexibility of the electricity grid, which facilitates the extensive usage of renewable energies in industrial applications. In order to ensure the techno-economical reliability of the battery energy storage system, managing the lifespan of each battery is critical. In this paper, a novel evolutionary framework is proposed to estimate the Lithium-ion battery state of health, which uniformly optimizes the two key processes of establishing a data driven estimator. The features in the degradation process of a battery are conveniently measured by a group of current pulses, which last only few seconds. The proposed evolutionary framework selects the most efficient combination of the short-term features from the current pulse test, and guarantees an optimal training process simultaneously. A hybrid encoding technology is applied to mix the feature extraction and the parameters of support vector regression in one chromosome. With the benefit of the proposed evolutionary framework, the battery state of health is estimated by using support vector regression and genetic algorithm in a more efficient way. A mission profile corresponding to batteries providing the primary frequency regulation service to the power system is used to cycle two Lithium-ion batteries for the validation of the proposed method.

AB - Battery energy storage system expands the flexibility of the electricity grid, which facilitates the extensive usage of renewable energies in industrial applications. In order to ensure the techno-economical reliability of the battery energy storage system, managing the lifespan of each battery is critical. In this paper, a novel evolutionary framework is proposed to estimate the Lithium-ion battery state of health, which uniformly optimizes the two key processes of establishing a data driven estimator. The features in the degradation process of a battery are conveniently measured by a group of current pulses, which last only few seconds. The proposed evolutionary framework selects the most efficient combination of the short-term features from the current pulse test, and guarantees an optimal training process simultaneously. A hybrid encoding technology is applied to mix the feature extraction and the parameters of support vector regression in one chromosome. With the benefit of the proposed evolutionary framework, the battery state of health is estimated by using support vector regression and genetic algorithm in a more efficient way. A mission profile corresponding to batteries providing the primary frequency regulation service to the power system is used to cycle two Lithium-ion batteries for the validation of the proposed method.

KW - State of health

KW - Lithium-ion battery

KW - Evolutionary framework

KW - Feature extraction

KW - Data driven method

UR - http://www.scopus.com/inward/record.url?scp=85057610208&partnerID=8YFLogxK

U2 - 10.1016/j.jpowsour.2018.12.001

DO - 10.1016/j.jpowsour.2018.12.001

M3 - Journal article

VL - 412

SP - 615

EP - 622

JO - Journal of Power Sources

JF - Journal of Power Sources

SN - 0378-7753

ER -