Online RNN model for soc prediction in next generation hybrid car batteries

Steven Hespeler; Donovan Fuqua

Online RNN model for soc prediction in next generation hybrid car batteries

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

2 Scopus citations

Abstract

This investigation presents a data-driven Long-short Term Memory (LSTM) battery model for predicting State of Charge (SOC) for a lithium-ion battery (LiFePO4) during Electric Vehicle (EV) operation. The LSTM builds and updates a model using multivariate inputs that include physical properties, voltage, current, and temperature during operation. The goal of training is to accurately predict future SOC from multiple training examples using an online learning scheme. Initial results demonstrate excellent prediction with a Root Mean Square Error (RMSE) ranging from 0.372 < RMSE < 0.534 which outperforms results from literature that utilized other neural network algorithms.

Original language	English
Title of host publication	Proceedings of the 2020 IISE Annual Conference
Editors	L. Cromarty, R. Shirwaiker, P. Wang
Publisher	Institute of Industrial and Systems Engineers, IISE
Pages	97-102
Number of pages	6
ISBN (Electronic)	9781713827818
State	Published - 2020
Externally published	Yes
Event	2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020 - Virtual, Online, United States Duration: Nov 1 2020 → Nov 3 2020

Publication series

Name	Proceedings of the 2020 IISE Annual Conference

Conference

Conference	2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020
Country/Territory	United States
City	Virtual, Online
Period	11/1/20 → 11/3/20

Bibliographical note

Publisher Copyright:
© Proceedings of the 2020 IISE Annual. All Rights Reserved.

Keywords

Deep Learning
Reliability Engineering
Sustainable System

UN SDGs

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

Cite this

@inproceedings{4ad01506ed484e97a7e0fb49acab8f77,

title = "Online RNN model for soc prediction in next generation hybrid car batteries",

abstract = "This investigation presents a data-driven Long-short Term Memory (LSTM) battery model for predicting State of Charge (SOC) for a lithium-ion battery (LiFePO4) during Electric Vehicle (EV) operation. The LSTM builds and updates a model using multivariate inputs that include physical properties, voltage, current, and temperature during operation. The goal of training is to accurately predict future SOC from multiple training examples using an online learning scheme. Initial results demonstrate excellent prediction with a Root Mean Square Error (RMSE) ranging from 0.372 < RMSE < 0.534 which outperforms results from literature that utilized other neural network algorithms.",

keywords = "Deep Learning, Reliability Engineering, Sustainable System",

author = "Steven Hespeler and Donovan Fuqua",

note = "Publisher Copyright: {\textcopyright} Proceedings of the 2020 IISE Annual. All Rights Reserved.; 2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020 ; Conference date: 01-11-2020 Through 03-11-2020",

year = "2020",

language = "English",

series = "Proceedings of the 2020 IISE Annual Conference",

publisher = "Institute of Industrial and Systems Engineers, IISE",

pages = "97--102",

editor = "L. Cromarty and R. Shirwaiker and P. Wang",

booktitle = "Proceedings of the 2020 IISE Annual Conference",

}

Hespeler, S & Fuqua, D 2020, Online RNN model for soc prediction in next generation hybrid car batteries. in L Cromarty, R Shirwaiker & P Wang (eds), Proceedings of the 2020 IISE Annual Conference. Proceedings of the 2020 IISE Annual Conference, Institute of Industrial and Systems Engineers, IISE, pp. 97-102, 2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020, Virtual, Online, United States, 11/1/20.

Online RNN model for soc prediction in next generation hybrid car batteries. / Hespeler, Steven; Fuqua, Donovan.
Proceedings of the 2020 IISE Annual Conference. ed. / L. Cromarty; R. Shirwaiker; P. Wang. Institute of Industrial and Systems Engineers, IISE, 2020. p. 97-102 (Proceedings of the 2020 IISE Annual Conference).

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

TY - GEN

T1 - Online RNN model for soc prediction in next generation hybrid car batteries

AU - Hespeler, Steven

AU - Fuqua, Donovan

PY - 2020

Y1 - 2020

N2 - This investigation presents a data-driven Long-short Term Memory (LSTM) battery model for predicting State of Charge (SOC) for a lithium-ion battery (LiFePO4) during Electric Vehicle (EV) operation. The LSTM builds and updates a model using multivariate inputs that include physical properties, voltage, current, and temperature during operation. The goal of training is to accurately predict future SOC from multiple training examples using an online learning scheme. Initial results demonstrate excellent prediction with a Root Mean Square Error (RMSE) ranging from 0.372 < RMSE < 0.534 which outperforms results from literature that utilized other neural network algorithms.

AB - This investigation presents a data-driven Long-short Term Memory (LSTM) battery model for predicting State of Charge (SOC) for a lithium-ion battery (LiFePO4) during Electric Vehicle (EV) operation. The LSTM builds and updates a model using multivariate inputs that include physical properties, voltage, current, and temperature during operation. The goal of training is to accurately predict future SOC from multiple training examples using an online learning scheme. Initial results demonstrate excellent prediction with a Root Mean Square Error (RMSE) ranging from 0.372 < RMSE < 0.534 which outperforms results from literature that utilized other neural network algorithms.

KW - Deep Learning

KW - Reliability Engineering

KW - Sustainable System

UR - http://www.scopus.com/inward/record.url?scp=85105681286&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85105681286

T3 - Proceedings of the 2020 IISE Annual Conference

SP - 97

EP - 102

BT - Proceedings of the 2020 IISE Annual Conference

A2 - Cromarty, L.

A2 - Shirwaiker, R.

A2 - Wang, P.

PB - Institute of Industrial and Systems Engineers, IISE

T2 - 2020 Institute of Industrial and Systems Engineers Annual Conference and Expo, IISE 2020

Y2 - 1 November 2020 through 3 November 2020

ER -

Online RNN model for soc prediction in next generation hybrid car batteries

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Other files and links

Fingerprint

Cite this