Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge

Varsha Pendyala; F. N.U. Nishanth

doi:10.1109/ONCON56984.2022.10127051

Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge

Varsha Pendyala, F. N.U. Nishanth

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

1 Scopus citations

Abstract

Depleting fossil fuel reserves, concerns over air pollution and global warming position electric vehicles as compelling alternatives to conventional vehicles with internal combustion engines. A large portion of the commercially available electric vehicles today are of the battery-electric type, which use batteries to store energy. Accurate computation of the battery state of charge is critical to ensure that a reasonable estimate of the vehicle range is available before the batteries need to be recharged. Conventional approaches to estimate battery state of charge rely on the battery equivalent circuit models and state observers. However, the non-linearity of the battery properties combined with their dependence on temperature and driving cycle render these approaches inaccurate, necessitating the development of robust techniques that can overcome these drawbacks and accurately estimate the state of charge. This paper first reviews the conventional techniques to estimate the battery state of charge and identifies their limitations. Next, a machine learning technique is developed to accurately estimate the battery state of charge and it's performance is evaluated over drive cycle data that was experimentally collected from a commercial electric vehicle under different test conditions. The results show the suitability of the developed technique to accurately estimate the battery state of charge with RMS errors less than 3% under most operating conditions and standard driving cycles.

Original language	English
Title of host publication	1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350398069
DOIs	https://doi.org/10.1109/ONCON56984.2022.10127051
State	Published - 2022
Externally published	Yes
Event	1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022 - Kharagpur, India Duration: Dec 9 2022 → Dec 11 2022

Publication series

Name	1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

Conference

Conference	1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022
Country/Territory	India
City	Kharagpur
Period	12/9/22 → 12/11/22

Funding

The authors are grateful to Dr Phil Kollmeyer and Mina Naguib at the McMaster Automotive Resource Centre (MARC), McMaster University, Canada for providing the blind testing tool to evaluate our developed model. The authors also thank Sangwhee Lee, Nathan Petersen and Shalini Manna at the Wisconsin Electric Machines and Power Electronics Consortium (WEMPEC) at the University of Wisconsin- Madison for insightful discussions on physics-based modeling of batteries.

Keywords

artificial neural network
batteries
battery state of charge estimation
deep learning
electric vehicles
Machine learning
multi-layer perceptron

Access to Document

10.1109/ONCON56984.2022.10127051

Cite this

Pendyala, V., & Nishanth, F. N. U. (2022). Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge. In 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022 (1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ONCON56984.2022.10127051

@inproceedings{b88850cce5ef4e1791b2cdc939eb886c,

title = "Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge",

abstract = "Depleting fossil fuel reserves, concerns over air pollution and global warming position electric vehicles as compelling alternatives to conventional vehicles with internal combustion engines. A large portion of the commercially available electric vehicles today are of the battery-electric type, which use batteries to store energy. Accurate computation of the battery state of charge is critical to ensure that a reasonable estimate of the vehicle range is available before the batteries need to be recharged. Conventional approaches to estimate battery state of charge rely on the battery equivalent circuit models and state observers. However, the non-linearity of the battery properties combined with their dependence on temperature and driving cycle render these approaches inaccurate, necessitating the development of robust techniques that can overcome these drawbacks and accurately estimate the state of charge. This paper first reviews the conventional techniques to estimate the battery state of charge and identifies their limitations. Next, a machine learning technique is developed to accurately estimate the battery state of charge and it's performance is evaluated over drive cycle data that was experimentally collected from a commercial electric vehicle under different test conditions. The results show the suitability of the developed technique to accurately estimate the battery state of charge with RMS errors less than 3% under most operating conditions and standard driving cycles.",

keywords = "artificial neural network, batteries, battery state of charge estimation, deep learning, electric vehicles, Machine learning, multi-layer perceptron",

author = "Varsha Pendyala and Nishanth, {F. N.U.}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022 ; Conference date: 09-12-2022 Through 11-12-2022",

year = "2022",

doi = "10.1109/ONCON56984.2022.10127051",

language = "English",

series = "1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022",

}

Pendyala, V & Nishanth, FNU 2022, Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge. in 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022. 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022, Institute of Electrical and Electronics Engineers Inc., 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022, Kharagpur, India, 12/9/22. https://doi.org/10.1109/ONCON56984.2022.10127051

Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge. / Pendyala, Varsha; Nishanth, F. N.U.
1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022).

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

TY - GEN

T1 - Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge

AU - Pendyala, Varsha

AU - Nishanth, F. N.U.

PY - 2022

Y1 - 2022

N2 - Depleting fossil fuel reserves, concerns over air pollution and global warming position electric vehicles as compelling alternatives to conventional vehicles with internal combustion engines. A large portion of the commercially available electric vehicles today are of the battery-electric type, which use batteries to store energy. Accurate computation of the battery state of charge is critical to ensure that a reasonable estimate of the vehicle range is available before the batteries need to be recharged. Conventional approaches to estimate battery state of charge rely on the battery equivalent circuit models and state observers. However, the non-linearity of the battery properties combined with their dependence on temperature and driving cycle render these approaches inaccurate, necessitating the development of robust techniques that can overcome these drawbacks and accurately estimate the state of charge. This paper first reviews the conventional techniques to estimate the battery state of charge and identifies their limitations. Next, a machine learning technique is developed to accurately estimate the battery state of charge and it's performance is evaluated over drive cycle data that was experimentally collected from a commercial electric vehicle under different test conditions. The results show the suitability of the developed technique to accurately estimate the battery state of charge with RMS errors less than 3% under most operating conditions and standard driving cycles.

AB - Depleting fossil fuel reserves, concerns over air pollution and global warming position electric vehicles as compelling alternatives to conventional vehicles with internal combustion engines. A large portion of the commercially available electric vehicles today are of the battery-electric type, which use batteries to store energy. Accurate computation of the battery state of charge is critical to ensure that a reasonable estimate of the vehicle range is available before the batteries need to be recharged. Conventional approaches to estimate battery state of charge rely on the battery equivalent circuit models and state observers. However, the non-linearity of the battery properties combined with their dependence on temperature and driving cycle render these approaches inaccurate, necessitating the development of robust techniques that can overcome these drawbacks and accurately estimate the state of charge. This paper first reviews the conventional techniques to estimate the battery state of charge and identifies their limitations. Next, a machine learning technique is developed to accurately estimate the battery state of charge and it's performance is evaluated over drive cycle data that was experimentally collected from a commercial electric vehicle under different test conditions. The results show the suitability of the developed technique to accurately estimate the battery state of charge with RMS errors less than 3% under most operating conditions and standard driving cycles.

KW - artificial neural network

KW - batteries

KW - battery state of charge estimation

KW - deep learning

KW - electric vehicles

KW - Machine learning

KW - multi-layer perceptron

UR - http://www.scopus.com/inward/record.url?scp=85161302403&partnerID=8YFLogxK

U2 - 10.1109/ONCON56984.2022.10127051

DO - 10.1109/ONCON56984.2022.10127051

M3 - Conference contribution

AN - SCOPUS:85161302403

T3 - 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

BT - 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022

Y2 - 9 December 2022 through 11 December 2022

ER -

Pendyala V, Nishanth FNU. Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge. In 1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (1st IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2022). doi: 10.1109/ONCON56984.2022.10127051

Development of a Machine Learning Technique to Accurately Estimate Battery State of Charge

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this