An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates

Asadullah Khalid; Aditya Sundararajan; Arif I. Sarwat

doi:10.1109/ITEC-India48457.2019.ITECIndia2019-1

An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates

Asadullah Khalid, Aditya Sundararajan, Arif I. Sarwat

Grid Systems Architecture

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

9 Scopus citations

Abstract

State of charge (SOC) prediction for Li-ion batteries is an essential feature of a battery management system (BMS). This paper proposes two Autoregressive Integrated Moving Average (ARIMA) models to independently forecast cell current and voltage, respectively and a Nonlinear Autoregressive neural network (NARX-net) model. The battery parameters corresponding to an unknown higher C-rate are forecasted using the parameters corresponding to known C-rates obtained experimentally using a 3.7V, 3.5Ah Li-ion battery. Four algorithms are then used to train a NARX-net to predict SOC for an unknown higher C-rate, performances of which are compared with the experimentally obtained SOC for C/10. The resulting proposed model combining ARIMA and NARX-net predicts SOC with very low error values.

Original language	English
Title of host publication	2019 IEEE Transportation Electrification Conference, ITEC-India 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728131696
DOIs	https://doi.org/10.1109/ITEC-India48457.2019.ITECIndia2019-1
State	Published - Dec 2019
Event	2019 IEEE Transportation Electrification Conference, ITEC-India 2019 - Bengaluru, India Duration: Dec 17 2019 → Dec 19 2019

Publication series

Name	2019 IEEE Transportation Electrification Conference, ITEC-India 2019

Conference

Conference	2019 IEEE Transportation Electrification Conference, ITEC-India 2019
Country/Territory	India
City	Bengaluru
Period	12/17/19 → 12/19/19

Funding

ACKNOWLEDGMENTS The material published is a result of the research supported by the National Science Foundation under the Award number CNS-1553494.

Keywords

ARIMA
NARX
battery analyzer
state of charge prediction

Access to Document

10.1109/ITEC-India48457.2019.ITECIndia2019-1

Cite this

Khalid, A., Sundararajan, A., & Sarwat, A. I. (2019). An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates. In 2019 IEEE Transportation Electrification Conference, ITEC-India 2019 Article 9080860 (2019 IEEE Transportation Electrification Conference, ITEC-India 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITEC-India48457.2019.ITECIndia2019-1

@inproceedings{57877732a9f148cd9097759fe4df93c3,

title = "An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates",

abstract = "State of charge (SOC) prediction for Li-ion batteries is an essential feature of a battery management system (BMS). This paper proposes two Autoregressive Integrated Moving Average (ARIMA) models to independently forecast cell current and voltage, respectively and a Nonlinear Autoregressive neural network (NARX-net) model. The battery parameters corresponding to an unknown higher C-rate are forecasted using the parameters corresponding to known C-rates obtained experimentally using a 3.7V, 3.5Ah Li-ion battery. Four algorithms are then used to train a NARX-net to predict SOC for an unknown higher C-rate, performances of which are compared with the experimentally obtained SOC for C/10. The resulting proposed model combining ARIMA and NARX-net predicts SOC with very low error values.",

keywords = "ARIMA, NARX, battery analyzer, state of charge prediction",

author = "Asadullah Khalid and Aditya Sundararajan and Sarwat, \{Arif I.\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Transportation Electrification Conference, ITEC-India 2019 ; Conference date: 17-12-2019 Through 19-12-2019",

year = "2019",

month = dec,

doi = "10.1109/ITEC-India48457.2019.ITECIndia2019-1",

language = "English",

series = "2019 IEEE Transportation Electrification Conference, ITEC-India 2019",

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

booktitle = "2019 IEEE Transportation Electrification Conference, ITEC-India 2019",

}

Khalid, A, Sundararajan, A & Sarwat, AI 2019, An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates. in 2019 IEEE Transportation Electrification Conference, ITEC-India 2019., 9080860, 2019 IEEE Transportation Electrification Conference, ITEC-India 2019, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE Transportation Electrification Conference, ITEC-India 2019, Bengaluru, India, 12/17/19. https://doi.org/10.1109/ITEC-India48457.2019.ITECIndia2019-1

An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates. / Khalid, Asadullah; Sundararajan, Aditya; Sarwat, Arif I.
2019 IEEE Transportation Electrification Conference, ITEC-India 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9080860 (2019 IEEE Transportation Electrification Conference, ITEC-India 2019).

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

TY - GEN

T1 - An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates

AU - Khalid, Asadullah

AU - Sundararajan, Aditya

AU - Sarwat, Arif I.

PY - 2019/12

Y1 - 2019/12

N2 - State of charge (SOC) prediction for Li-ion batteries is an essential feature of a battery management system (BMS). This paper proposes two Autoregressive Integrated Moving Average (ARIMA) models to independently forecast cell current and voltage, respectively and a Nonlinear Autoregressive neural network (NARX-net) model. The battery parameters corresponding to an unknown higher C-rate are forecasted using the parameters corresponding to known C-rates obtained experimentally using a 3.7V, 3.5Ah Li-ion battery. Four algorithms are then used to train a NARX-net to predict SOC for an unknown higher C-rate, performances of which are compared with the experimentally obtained SOC for C/10. The resulting proposed model combining ARIMA and NARX-net predicts SOC with very low error values.

AB - State of charge (SOC) prediction for Li-ion batteries is an essential feature of a battery management system (BMS). This paper proposes two Autoregressive Integrated Moving Average (ARIMA) models to independently forecast cell current and voltage, respectively and a Nonlinear Autoregressive neural network (NARX-net) model. The battery parameters corresponding to an unknown higher C-rate are forecasted using the parameters corresponding to known C-rates obtained experimentally using a 3.7V, 3.5Ah Li-ion battery. Four algorithms are then used to train a NARX-net to predict SOC for an unknown higher C-rate, performances of which are compared with the experimentally obtained SOC for C/10. The resulting proposed model combining ARIMA and NARX-net predicts SOC with very low error values.

KW - ARIMA

KW - NARX

KW - battery analyzer

KW - state of charge prediction

UR - https://www.scopus.com/pages/publications/85085166776

U2 - 10.1109/ITEC-India48457.2019.ITECIndia2019-1

DO - 10.1109/ITEC-India48457.2019.ITECIndia2019-1

M3 - Conference contribution

AN - SCOPUS:85085166776

T3 - 2019 IEEE Transportation Electrification Conference, ITEC-India 2019

BT - 2019 IEEE Transportation Electrification Conference, ITEC-India 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE Transportation Electrification Conference, ITEC-India 2019

Y2 - 17 December 2019 through 19 December 2019

ER -

Khalid A, Sundararajan A, Sarwat AI. An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates. In 2019 IEEE Transportation Electrification Conference, ITEC-India 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9080860. (2019 IEEE Transportation Electrification Conference, ITEC-India 2019). doi: 10.1109/ITEC-India48457.2019.ITECIndia2019-1

An ARIMA-NARX Model to Predict Li-Ion State of Charge for Unknown Charge/Discharge Rates

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this