Battery state-of-health estimation using machine learning

Daniel-Ioan Stroe; Xin Sui

doi:10.1016/B978-0-323-85622-5.00010-9

Battery state-of-health estimation using machine learning

Daniel-Ioan Stroe^*, Xin Sui

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Book chapter › Research › peer-review

Abstract

Over the years, lithium–ion batteries have developed as a key enabling technology for the green transition. Although many of these batteries’ characteristics, such as energy density, power capability, and cost, have gradually improved, uncertainties remain concerning their performance over their lifetimes. Thus, to ensure reliable and efficient battery operation, the battery's available performance, known as its state of health (SOH), must be known at every moment. This chapter introduces the most common battery SOH estimation methods, from direct measurements to deep neural networks, discussing their key performance metrics, advantages, and drawbacks.

Original language	English
Title of host publication	Control of Power Electronic Converters and Systems : Volume 4
Editors	Frede Blaabjerg
Number of pages	48
Volume	4
Publisher	Academic Press
Publication date	1 Jan 2024
Edition	1
Pages	383-430
Chapter	13
ISBN (Print)	978-0-323-85623-2
ISBN (Electronic)	978-0-323-85622-5
DOIs	https://doi.org/10.1016/B978-0-323-85622-5.00010-9
Publication status	Published - 1 Jan 2024

Keywords

Capacity Fade
Lithium-Ion Battery
Machine Learning
Resistance Increase
State-of-Health
Lithium-ion battery
Linear regression
Neural networks
Machine learning
State-of-health
Support vector machine

UN SDGs

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

Access to Document

10.1016/B978-0-323-85622-5.00010-9

AUB Link

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

Cite this

@inbook{a912210a76d64bd0bf4c5640a030e7ee,

title = "Battery state-of-health estimation using machine learning",

abstract = "Over the years, lithium–ion batteries have developed as a key enabling technology for the green transition. Although many of these batteries{\textquoteright} characteristics, such as energy density, power capability, and cost, have gradually improved, uncertainties remain concerning their performance over their lifetimes. Thus, to ensure reliable and efficient battery operation, the battery's available performance, known as its state of health (SOH), must be known at every moment. This chapter introduces the most common battery SOH estimation methods, from direct measurements to deep neural networks, discussing their key performance metrics, advantages, and drawbacks.",

keywords = "Capacity Fade, Lithium-Ion Battery, Machine Learning, Resistance Increase, State-of-Health, Lithium-ion battery, Linear regression, Neural networks, Machine learning, State-of-health, Support vector machine",

author = "Daniel-Ioan Stroe and Xin Sui",

year = "2024",

month = jan,

day = "1",

doi = "10.1016/B978-0-323-85622-5.00010-9",

language = "English",

isbn = "978-0-323-85623-2",

volume = "4",

pages = "383--430",

editor = "Frede Blaabjerg",

booktitle = "Control of Power Electronic Converters and Systems",

publisher = "Academic Press",

address = "United States",

edition = "1",

}

TY - CHAP

T1 - Battery state-of-health estimation using machine learning

AU - Stroe, Daniel-Ioan

AU - Sui, Xin

PY - 2024/1/1

Y1 - 2024/1/1

N2 - Over the years, lithium–ion batteries have developed as a key enabling technology for the green transition. Although many of these batteries’ characteristics, such as energy density, power capability, and cost, have gradually improved, uncertainties remain concerning their performance over their lifetimes. Thus, to ensure reliable and efficient battery operation, the battery's available performance, known as its state of health (SOH), must be known at every moment. This chapter introduces the most common battery SOH estimation methods, from direct measurements to deep neural networks, discussing their key performance metrics, advantages, and drawbacks.

AB - Over the years, lithium–ion batteries have developed as a key enabling technology for the green transition. Although many of these batteries’ characteristics, such as energy density, power capability, and cost, have gradually improved, uncertainties remain concerning their performance over their lifetimes. Thus, to ensure reliable and efficient battery operation, the battery's available performance, known as its state of health (SOH), must be known at every moment. This chapter introduces the most common battery SOH estimation methods, from direct measurements to deep neural networks, discussing their key performance metrics, advantages, and drawbacks.

KW - Capacity Fade

KW - Lithium-Ion Battery

KW - Machine Learning

KW - Resistance Increase

KW - State-of-Health

KW - Lithium-ion battery

KW - Linear regression

KW - Neural networks

KW - Machine learning

KW - State-of-health

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85189599807&partnerID=8YFLogxK

U2 - 10.1016/B978-0-323-85622-5.00010-9

DO - 10.1016/B978-0-323-85622-5.00010-9

M3 - Book chapter

SN - 978-0-323-85623-2

VL - 4

SP - 383

EP - 430

BT - Control of Power Electronic Converters and Systems

A2 - Blaabjerg, Frede

PB - Academic Press

ER -

Battery state-of-health estimation using machine learning

Abstract

Keywords

UN SDGs

Access to Document

AUB Link

Other files and links

Fingerprint

Control of Power Electronic Converters and Systems: Volume 4

Cite this