State of Charge Estimation for Lithium-Ion Battery Using Recurrent NARX Neural Network Model Based Lighting Search Algorithm

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

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

State of charge (SOC) is one of the crucial parameters in a lithium-ion battery. The accurate estimation of SOC guarantees the safe and efficient operation of a specific application. However, SOC estimation with high accuracy is a serious concern to the automobile engineer due to the battery nonlinear characteristics and complex electrochemical reactions. This paper presents an improved nonlinear autoregressive with exogenous input (NARX)-based neural network (NARXNN) algorithm for an accurate and robust SOC estimation of lithium-ion battery which is effective and computationally rich for controlling dynamic system and predicting time series. However, the accuracy of recurrent NARXNN depends on the amount of input order, output order, and hidden layer neurons. The unique contribution of the improved recurrent NARXNN-based SOC estimation is developed using lighting search algorithm (LSA) for finding the best value of input delays, feedback delays, and hidden layer neurons. The contributions are summarized as: 1) the computational capability of NARXNN model which does not require battery model and parameters rather only needs current, voltage, and temperature sensors; 2) the effectiveness of LSA which is verified with particle swarm optimization; 3) the adaptability, efficiency, and robustness of the model which are evaluated using FUDS and US06 drive cycles at varying temperatures conditions; and 4) the performance of the proposed model which is compared with back propagation neural network and radial basis function neural network optimized by LSA using different error statistical terms and computational time. Furthermore, a comparative analysis of SOC estimation in proposed method and existing techniques is presented for validation of NARXNN performance. The results prove that the proposed NARXNN model achieves higher accuracy with less computational time than other existing SOC algorithms under different temperature conditions and electric vehicle drive cycles.

Original languageEnglish
Pages (from-to)28150-28161
Number of pages12
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 16 May 2018

Fingerprint

Recurrent neural networks
Lighting
Neural networks
Neurons
Lithium-ion batteries
Temperature sensors
Network performance
Electric vehicles
Backpropagation
Particle swarm optimization (PSO)
Automobiles
Time series
Dynamical systems
Feedback
Engineers
Temperature
Electric potential

Keywords

  • lighting search algorithm
  • lithium-ion battery
  • NARX neural network
  • State of charge

ASJC Scopus subject areas

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

Cite this

State of Charge Estimation for Lithium-Ion Battery Using Recurrent NARX Neural Network Model Based Lighting Search Algorithm. / Lipu, Molla S.Hossain; M A, Hannan; Hussain, Aini; Md Saad, Mohamad Hanif; Ayob, Afida; Blaabjerg, Frede.

In: IEEE Access, Vol. 6, 16.05.2018, p. 28150-28161.

Research output: Contribution to journalArticle

@article{c8a5ff2ed8a346ed9579f037cae32d48,
title = "State of Charge Estimation for Lithium-Ion Battery Using Recurrent NARX Neural Network Model Based Lighting Search Algorithm",
abstract = "State of charge (SOC) is one of the crucial parameters in a lithium-ion battery. The accurate estimation of SOC guarantees the safe and efficient operation of a specific application. However, SOC estimation with high accuracy is a serious concern to the automobile engineer due to the battery nonlinear characteristics and complex electrochemical reactions. This paper presents an improved nonlinear autoregressive with exogenous input (NARX)-based neural network (NARXNN) algorithm for an accurate and robust SOC estimation of lithium-ion battery which is effective and computationally rich for controlling dynamic system and predicting time series. However, the accuracy of recurrent NARXNN depends on the amount of input order, output order, and hidden layer neurons. The unique contribution of the improved recurrent NARXNN-based SOC estimation is developed using lighting search algorithm (LSA) for finding the best value of input delays, feedback delays, and hidden layer neurons. The contributions are summarized as: 1) the computational capability of NARXNN model which does not require battery model and parameters rather only needs current, voltage, and temperature sensors; 2) the effectiveness of LSA which is verified with particle swarm optimization; 3) the adaptability, efficiency, and robustness of the model which are evaluated using FUDS and US06 drive cycles at varying temperatures conditions; and 4) the performance of the proposed model which is compared with back propagation neural network and radial basis function neural network optimized by LSA using different error statistical terms and computational time. Furthermore, a comparative analysis of SOC estimation in proposed method and existing techniques is presented for validation of NARXNN performance. The results prove that the proposed NARXNN model achieves higher accuracy with less computational time than other existing SOC algorithms under different temperature conditions and electric vehicle drive cycles.",
keywords = "lighting search algorithm, lithium-ion battery, NARX neural network, State of charge",
author = "Lipu, {Molla S.Hossain} and {M A}, Hannan and Aini Hussain and {Md Saad}, {Mohamad Hanif} and Afida Ayob and Frede Blaabjerg",
year = "2018",
month = "5",
day = "16",
doi = "10.1109/ACCESS.2018.2837156",
language = "English",
volume = "6",
pages = "28150--28161",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - State of Charge Estimation for Lithium-Ion Battery Using Recurrent NARX Neural Network Model Based Lighting Search Algorithm

AU - Lipu, Molla S.Hossain

AU - M A, Hannan

AU - Hussain, Aini

AU - Md Saad, Mohamad Hanif

AU - Ayob, Afida

AU - Blaabjerg, Frede

PY - 2018/5/16

Y1 - 2018/5/16

N2 - State of charge (SOC) is one of the crucial parameters in a lithium-ion battery. The accurate estimation of SOC guarantees the safe and efficient operation of a specific application. However, SOC estimation with high accuracy is a serious concern to the automobile engineer due to the battery nonlinear characteristics and complex electrochemical reactions. This paper presents an improved nonlinear autoregressive with exogenous input (NARX)-based neural network (NARXNN) algorithm for an accurate and robust SOC estimation of lithium-ion battery which is effective and computationally rich for controlling dynamic system and predicting time series. However, the accuracy of recurrent NARXNN depends on the amount of input order, output order, and hidden layer neurons. The unique contribution of the improved recurrent NARXNN-based SOC estimation is developed using lighting search algorithm (LSA) for finding the best value of input delays, feedback delays, and hidden layer neurons. The contributions are summarized as: 1) the computational capability of NARXNN model which does not require battery model and parameters rather only needs current, voltage, and temperature sensors; 2) the effectiveness of LSA which is verified with particle swarm optimization; 3) the adaptability, efficiency, and robustness of the model which are evaluated using FUDS and US06 drive cycles at varying temperatures conditions; and 4) the performance of the proposed model which is compared with back propagation neural network and radial basis function neural network optimized by LSA using different error statistical terms and computational time. Furthermore, a comparative analysis of SOC estimation in proposed method and existing techniques is presented for validation of NARXNN performance. The results prove that the proposed NARXNN model achieves higher accuracy with less computational time than other existing SOC algorithms under different temperature conditions and electric vehicle drive cycles.

AB - State of charge (SOC) is one of the crucial parameters in a lithium-ion battery. The accurate estimation of SOC guarantees the safe and efficient operation of a specific application. However, SOC estimation with high accuracy is a serious concern to the automobile engineer due to the battery nonlinear characteristics and complex electrochemical reactions. This paper presents an improved nonlinear autoregressive with exogenous input (NARX)-based neural network (NARXNN) algorithm for an accurate and robust SOC estimation of lithium-ion battery which is effective and computationally rich for controlling dynamic system and predicting time series. However, the accuracy of recurrent NARXNN depends on the amount of input order, output order, and hidden layer neurons. The unique contribution of the improved recurrent NARXNN-based SOC estimation is developed using lighting search algorithm (LSA) for finding the best value of input delays, feedback delays, and hidden layer neurons. The contributions are summarized as: 1) the computational capability of NARXNN model which does not require battery model and parameters rather only needs current, voltage, and temperature sensors; 2) the effectiveness of LSA which is verified with particle swarm optimization; 3) the adaptability, efficiency, and robustness of the model which are evaluated using FUDS and US06 drive cycles at varying temperatures conditions; and 4) the performance of the proposed model which is compared with back propagation neural network and radial basis function neural network optimized by LSA using different error statistical terms and computational time. Furthermore, a comparative analysis of SOC estimation in proposed method and existing techniques is presented for validation of NARXNN performance. The results prove that the proposed NARXNN model achieves higher accuracy with less computational time than other existing SOC algorithms under different temperature conditions and electric vehicle drive cycles.

KW - lighting search algorithm

KW - lithium-ion battery

KW - NARX neural network

KW - State of charge

UR - http://www.scopus.com/inward/record.url?scp=85046997280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046997280&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2837156

DO - 10.1109/ACCESS.2018.2837156

M3 - Article

AN - SCOPUS:85046997280

VL - 6

SP - 28150

EP - 28161

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -