Electric Vehicle Batteries: Status and Perspectives of Data-Driven Diagnosis and Prognosis

Mass marketing of battery-electric vehicles (EVs) will require that car buyers have high confidence in the performance, reliability and safety of the battery in their vehicles. Over the past decade, steady progress has been made towards the development of advanced battery diagnostic and prognostic t...

Full description

Saved in:
Bibliographic Details
Published in:Batteries (Basel) 2022-10, Vol.8 (10), p.142
Main Authors: Zhao, Jingyuan, Burke, Andrew F.
Format: Article
Language:English
Subjects:
Artificial intelligence
Automobiles, Electric
Batteries
battery
data-driven
Datasets
Deep learning
Diagnosis
Electric vehicles
Laboratories
Lithium
Machine learning
Neural networks
Physics
Power
Product safety
prognosis
R&D
Reliability (Engineering)
Research & development
safety
state of health
Supply and demand
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mass marketing of battery-electric vehicles (EVs) will require that car buyers have high confidence in the performance, reliability and safety of the battery in their vehicles. Over the past decade, steady progress has been made towards the development of advanced battery diagnostic and prognostic technologies using data-driven methods that can be used to inform EV owners of the condition of their battery over its lifetime. The research has shown promise for accurately predicting battery state of health (SOH), state of safety (SOS), cycle life, the remaining useful life (RUL), and indicators of cells with high risk of failure (i.e., weak cells). These methods yield information about the battery that would be of great interest to EV owners, but at present it is not shared with them. This paper is concerned with the present status of the information available on the battery with a focus on data-driven diagnostic and prognostic approaches, and how the information would be generated in the future for the millions of EVs that will be on the road in the next decade. Finally, future trends and key challenges for the prognostics and health management of the batteries in real-world EV applications are presented from four perspectives (cloud-edge interaction, full-scale diagnosis, artificial intelligence and electronic health reports) are discussed.
ISSN:2313-0105
2313-0105
DOI:10.3390/batteries8100142