1.

Record Nr.

UNINA9911007155703321

Autore

Wang Shunli

Titolo

AI for Status Monitoring of Utility Scale Batteries

Pubbl/distr/stampa

Stevenage : , : Institution of Engineering & Technology, , 2023

©2022

ISBN

1-83724-508-8

1-5231-5354-7

1-83953-739-6

Edizione

[1st ed.]

Descrizione fisica

1 online resource (385 pages)

Collana

Energy Engineering

Altri autori (Persone)

LiuKailong

WangYujie

StroeDaniel-Ioan

FernándezCarlos (Lecturer in Analytical Chemistry)

GuerreroJosep M

Disciplina

006.31

Soggetti

Machine learning

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Nota di contenuto

Cover -- Halftitle Page -- Series Page -- Title Page -- Copyright -- Contents -- About the Authors -- Foreword -- Preface -- List of contributors -- 1 Introduction --   1.1 Motivation for utility-scale battery deployment --   1.2 Definition of AI in the context of battery management --   1.3 Advantages of using AI for battery management -- 2 Utility-­scale lithium-­ion battery system characteristics --   2.1 Overview of lithium-ion batteries --     2.1.1 Battery working principle --     2.1.2 Principles of status monitoring of utility-scale batteries --   2.2 Lithium-ion batteries --     2.2.1 Lithium iron phosphate batteries --     2.2.2 Lithium cobaltate oxide batteries --     2.2.3 Lithium manganese oxide batteries --   2.3 Large capacity lithium-ion batteries --     2.3.1 Application areas of utility-scale batteries --     2.3.2 Characteristics of utility-scale battery systems --     2.3.3 Operational challenges of utility-scale battery systems -- 3 AI-­based equivalent modeling and parameter identification --   3.1 Overview of battery equivalent circuit



modeling --   3.2 Modeling types and concepts --   3.3 Equivalent circuit modeling methods

Sommario/riassunto

Utility-scale Li-ion batteries are poised to play key roles for the clean energy system, but their failure has severe effects. AI can help with their monitoring and management. This work covers machine learning, neural networks, and deep learning, for battery modeling.