Modeling of electric vehicle batteries using RBF neural networks

Cheng Zhang; Zhile Yang; Kang Li

doi:10.1109/ComManTel.2014.6825590

Modeling of electric vehicle batteries using RBF neural networks

Cheng Zhang, Zhile Yang, Kang Li

Queen's University Belfast

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

11 Citations (Scopus)

50 Downloads (Pure)

Abstract

Electric Vehicles (EVs) are promised to significantly reduce the consumption of conventional fossil fuels in the transport sector as well as to limit the overwhelming greenhouse gas emissions. An accurate battery model is indispensable for the design of charging and discharging control of EVs. A new Radial Basis Function (RBF) modelling approach, which combines the Levenberg-Marquardt method to tune the non-linear parameters and an input selection approach for confining the number of input variables is proposed to model the batteries of EVs. Experimental results on modelling Li-ion batteries show that the resultant models have achieved high accuracy on training data and desirable generalization performance on unseen data.

Original language	English
Title of host publication	2014 International Conference on Computing, Management and Telecommunications (ComManTel)
Publisher	IEEE
Pages	116-121
Number of pages	6
ISBN (Print)	978-1-4799-2903-0
DOIs	https://doi.org/10.1109/ComManTel.2014.6825590
Publication status	Published - 5 Jun 2014
Externally published	Yes

Bibliographical note

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

Keywords

Batteries
Computational modeling
Artificial neural networks
Training
Optimization
Data models

Access to Document

10.1109/ComManTel.2014.6825590

Post-PrintAccepted author manuscript, 516 KBLicence: Unspecified

Cite this

@inproceedings{4d3dae9141e74a35bf32d4ee8d6ddb89,

title = "Modeling of electric vehicle batteries using RBF neural networks",

abstract = "Electric Vehicles (EVs) are promised to significantly reduce the consumption of conventional fossil fuels in the transport sector as well as to limit the overwhelming greenhouse gas emissions. An accurate battery model is indispensable for the design of charging and discharging control of EVs. A new Radial Basis Function (RBF) modelling approach, which combines the Levenberg-Marquardt method to tune the non-linear parameters and an input selection approach for confining the number of input variables is proposed to model the batteries of EVs. Experimental results on modelling Li-ion batteries show that the resultant models have achieved high accuracy on training data and desirable generalization performance on unseen data.",

keywords = "Batteries, Computational modeling, Artificial neural networks, Training, Optimization, Data models",

author = "Cheng Zhang and Zhile Yang and Kang Li",

note = "{\textcopyright} 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright {\textcopyright} and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. ",

year = "2014",

month = jun,

day = "5",

doi = "10.1109/ComManTel.2014.6825590",

language = "English",

isbn = "978-1-4799-2903-0",

pages = "116--121",

booktitle = "2014 International Conference on Computing, Management and Telecommunications (ComManTel)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Modeling of electric vehicle batteries using RBF neural networks

AU - Zhang, Cheng

AU - Yang, Zhile

AU - Li, Kang

N1 - © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

PY - 2014/6/5

Y1 - 2014/6/5

N2 - Electric Vehicles (EVs) are promised to significantly reduce the consumption of conventional fossil fuels in the transport sector as well as to limit the overwhelming greenhouse gas emissions. An accurate battery model is indispensable for the design of charging and discharging control of EVs. A new Radial Basis Function (RBF) modelling approach, which combines the Levenberg-Marquardt method to tune the non-linear parameters and an input selection approach for confining the number of input variables is proposed to model the batteries of EVs. Experimental results on modelling Li-ion batteries show that the resultant models have achieved high accuracy on training data and desirable generalization performance on unseen data.

AB - Electric Vehicles (EVs) are promised to significantly reduce the consumption of conventional fossil fuels in the transport sector as well as to limit the overwhelming greenhouse gas emissions. An accurate battery model is indispensable for the design of charging and discharging control of EVs. A new Radial Basis Function (RBF) modelling approach, which combines the Levenberg-Marquardt method to tune the non-linear parameters and an input selection approach for confining the number of input variables is proposed to model the batteries of EVs. Experimental results on modelling Li-ion batteries show that the resultant models have achieved high accuracy on training data and desirable generalization performance on unseen data.

KW - Batteries

KW - Computational modeling

KW - Artificial neural networks

KW - Training

KW - Optimization

KW - Data models

U2 - 10.1109/ComManTel.2014.6825590

DO - 10.1109/ComManTel.2014.6825590

M3 - Conference proceeding

SN - 978-1-4799-2903-0

SP - 116

EP - 121

BT - 2014 International Conference on Computing, Management and Telecommunications (ComManTel)

PB - IEEE

ER -

Modeling of electric vehicle batteries using RBF neural networks

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this