Neural network approach for estimating state of charge of lithium-ion battery using backtracking search algorithm

Hannan M A, Molla S.Hossain Lipu, Aini Hussain, Mohamad Hanif Md Saad, Afida Ayob

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

The state of charge (SOC) is a critical evaluation index of battery residual capacity. The significance of an accurate SOC estimation is great for a lithium-ion battery to ensure its safe operation and to prevent from over-charging or over-discharging. However, to estimate an accurate capacity of SOC of the lithium-ion battery has become a major concern for the electric vehicle (EV) industry. Therefore, numerous researches are being conducted to address the challenges and to enhance the battery performance. The main objective of this paper is to develop an accurate SOC estimation approach for a lithium-ion battery by improving back-propagation neural network (BPNN) capability using backtracking search algorithm (BSA). BSA optimization is utilized to improve the accuracy and robustness of BPNN model by finding the optimal value of hidden layer neurons and learning rate. In this paper, Dynamic Stress Test and Federal Urban Driving Schedule drive profiles are applied for testing the model at three different temperatures. The obtained results of the BPNN based BSA model are compared with the radial basis function neural network, generalized regression neural network and extreme learning machine model using statistical error values of root mean square error, mean absolute error, mean absolute percentage error, and SOC error to check and validate the model performance. The obtained results show that the BPNN based BSA model outperforms other neural network models in estimating SOC with high accuracy under different EV profiles and temperatures.

Original languageEnglish
Pages (from-to)10069-10079
Number of pages11
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 24 Jan 2018

Fingerprint

Neural networks
Backpropagation
Electric vehicles
Lithium-ion batteries
Mean square error
Neurons
Learning systems
Temperature
Testing
Industry

Keywords

  • Back propagation neural network
  • Backtracking search algorithm
  • Electric vehicle
  • Lithium-ion battery
  • The state of charge

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Neural network approach for estimating state of charge of lithium-ion battery using backtracking search algorithm. / M A, Hannan; Lipu, Molla S.Hossain; Hussain, Aini; Md Saad, Mohamad Hanif; Ayob, Afida.

In: IEEE Access, Vol. 6, 24.01.2018, p. 10069-10079.

Research output: Contribution to journalArticle

@article{5383163392b345deac11eb4052b40dc0,
title = "Neural network approach for estimating state of charge of lithium-ion battery using backtracking search algorithm",
abstract = "The state of charge (SOC) is a critical evaluation index of battery residual capacity. The significance of an accurate SOC estimation is great for a lithium-ion battery to ensure its safe operation and to prevent from over-charging or over-discharging. However, to estimate an accurate capacity of SOC of the lithium-ion battery has become a major concern for the electric vehicle (EV) industry. Therefore, numerous researches are being conducted to address the challenges and to enhance the battery performance. The main objective of this paper is to develop an accurate SOC estimation approach for a lithium-ion battery by improving back-propagation neural network (BPNN) capability using backtracking search algorithm (BSA). BSA optimization is utilized to improve the accuracy and robustness of BPNN model by finding the optimal value of hidden layer neurons and learning rate. In this paper, Dynamic Stress Test and Federal Urban Driving Schedule drive profiles are applied for testing the model at three different temperatures. The obtained results of the BPNN based BSA model are compared with the radial basis function neural network, generalized regression neural network and extreme learning machine model using statistical error values of root mean square error, mean absolute error, mean absolute percentage error, and SOC error to check and validate the model performance. The obtained results show that the BPNN based BSA model outperforms other neural network models in estimating SOC with high accuracy under different EV profiles and temperatures.",
keywords = "Back propagation neural network, Backtracking search algorithm, Electric vehicle, Lithium-ion battery, The state of charge",
author = "{M A}, Hannan and Lipu, {Molla S.Hossain} and Aini Hussain and {Md Saad}, {Mohamad Hanif} and Afida Ayob",
year = "2018",
month = "1",
day = "24",
doi = "10.1109/ACCESS.2018.2797976",
language = "English",
volume = "6",
pages = "10069--10079",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Neural network approach for estimating state of charge of lithium-ion battery using backtracking search algorithm

AU - M A, Hannan

AU - Lipu, Molla S.Hossain

AU - Hussain, Aini

AU - Md Saad, Mohamad Hanif

AU - Ayob, Afida

PY - 2018/1/24

Y1 - 2018/1/24

N2 - The state of charge (SOC) is a critical evaluation index of battery residual capacity. The significance of an accurate SOC estimation is great for a lithium-ion battery to ensure its safe operation and to prevent from over-charging or over-discharging. However, to estimate an accurate capacity of SOC of the lithium-ion battery has become a major concern for the electric vehicle (EV) industry. Therefore, numerous researches are being conducted to address the challenges and to enhance the battery performance. The main objective of this paper is to develop an accurate SOC estimation approach for a lithium-ion battery by improving back-propagation neural network (BPNN) capability using backtracking search algorithm (BSA). BSA optimization is utilized to improve the accuracy and robustness of BPNN model by finding the optimal value of hidden layer neurons and learning rate. In this paper, Dynamic Stress Test and Federal Urban Driving Schedule drive profiles are applied for testing the model at three different temperatures. The obtained results of the BPNN based BSA model are compared with the radial basis function neural network, generalized regression neural network and extreme learning machine model using statistical error values of root mean square error, mean absolute error, mean absolute percentage error, and SOC error to check and validate the model performance. The obtained results show that the BPNN based BSA model outperforms other neural network models in estimating SOC with high accuracy under different EV profiles and temperatures.

AB - The state of charge (SOC) is a critical evaluation index of battery residual capacity. The significance of an accurate SOC estimation is great for a lithium-ion battery to ensure its safe operation and to prevent from over-charging or over-discharging. However, to estimate an accurate capacity of SOC of the lithium-ion battery has become a major concern for the electric vehicle (EV) industry. Therefore, numerous researches are being conducted to address the challenges and to enhance the battery performance. The main objective of this paper is to develop an accurate SOC estimation approach for a lithium-ion battery by improving back-propagation neural network (BPNN) capability using backtracking search algorithm (BSA). BSA optimization is utilized to improve the accuracy and robustness of BPNN model by finding the optimal value of hidden layer neurons and learning rate. In this paper, Dynamic Stress Test and Federal Urban Driving Schedule drive profiles are applied for testing the model at three different temperatures. The obtained results of the BPNN based BSA model are compared with the radial basis function neural network, generalized regression neural network and extreme learning machine model using statistical error values of root mean square error, mean absolute error, mean absolute percentage error, and SOC error to check and validate the model performance. The obtained results show that the BPNN based BSA model outperforms other neural network models in estimating SOC with high accuracy under different EV profiles and temperatures.

KW - Back propagation neural network

KW - Backtracking search algorithm

KW - Electric vehicle

KW - Lithium-ion battery

KW - The state of charge

UR - http://www.scopus.com/inward/record.url?scp=85040974639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040974639&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2797976

DO - 10.1109/ACCESS.2018.2797976

M3 - Article

AN - SCOPUS:85040974639

VL - 6

SP - 10069

EP - 10079

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -