Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm

M. S. Hossain Lipu, M. A. Hannan, Aini Hussain, M. H.M. Saad, A. Ayob, M. N. Uddin

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

© 2018 IEEE This paper develops a state of charge (SOC) estimation model for a lithium-ion battery using an improved extreme learning machine (ELM) algorithm. ELM is suitable for SOC estimation since ELM algorithm has fast estimation speed, good generalization performance, and high accuracy. However, the performance of ELM is highly dependent on training accuracy and number of neurons in a hidden layer. Hence, gravitational search algorithm (GSA) is applied to improve the ELM computational intelligence by searching for the optimal value hidden layer neurons. The optimal ELM based GSA model does not require internal battery knowledge and mathematical model for SOC estimation. The model robustness is validated at different temperatures using different EV drive cycles. The performance of ELM-GSA model is verified with two popular neural network methods; back-propagation neural network (BPNN) and radial basis function neural network (RBFNN). The results are evaluatedusing different error rates and computation cost. The results demonstrate that the ELM-GSA model offers high accuracy and low SOC error rate than BPNN-GSA and RBFNN-GSA models. Furthermore, a detailed comparative study between the proposed model and existing SOC strategies is conducted which also demonstrates the superiority of the proposed model.
Original languageEnglish
DOIs
Publication statusPublished - 26 Nov 2018
Externally publishedYes
Event2018 IEEE Industry Applications Society Annual Meeting, IAS 2018 -
Duration: 26 Nov 2018 → …

Conference

Conference2018 IEEE Industry Applications Society Annual Meeting, IAS 2018
Period26/11/18 → …

Fingerprint

lithium
Learning systems
ion
Neural networks
back propagation
Backpropagation
Neurons
machine learning
battery
Lithium-ion batteries
Artificial intelligence
comparative study
Mathematical models
Costs
cost

All Science Journal Classification (ASJC) codes

  • Building and Construction
  • Energy(all)
  • Mechanical Engineering
  • Management, Monitoring, Policy and Law

Cite this

Hossain Lipu, M. S., Hannan, M. A., Hussain, A., Saad, M. H. M., Ayob, A., & Uddin, M. N. (2018). Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm. Paper presented at 2018 IEEE Industry Applications Society Annual Meeting, IAS 2018, . https://doi.org/10.1109/IAS.2018.8544607
Hossain Lipu, M. S. ; Hannan, M. A. ; Hussain, Aini ; Saad, M. H.M. ; Ayob, A. ; Uddin, M. N. / Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm. Paper presented at 2018 IEEE Industry Applications Society Annual Meeting, IAS 2018, .
@conference{44b6abe5a1b740bdbd8ffa3fb688328a,
title = "Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm",
abstract = "{\circledC} 2018 IEEE This paper develops a state of charge (SOC) estimation model for a lithium-ion battery using an improved extreme learning machine (ELM) algorithm. ELM is suitable for SOC estimation since ELM algorithm has fast estimation speed, good generalization performance, and high accuracy. However, the performance of ELM is highly dependent on training accuracy and number of neurons in a hidden layer. Hence, gravitational search algorithm (GSA) is applied to improve the ELM computational intelligence by searching for the optimal value hidden layer neurons. The optimal ELM based GSA model does not require internal battery knowledge and mathematical model for SOC estimation. The model robustness is validated at different temperatures using different EV drive cycles. The performance of ELM-GSA model is verified with two popular neural network methods; back-propagation neural network (BPNN) and radial basis function neural network (RBFNN). The results are evaluatedusing different error rates and computation cost. The results demonstrate that the ELM-GSA model offers high accuracy and low SOC error rate than BPNN-GSA and RBFNN-GSA models. Furthermore, a detailed comparative study between the proposed model and existing SOC strategies is conducted which also demonstrates the superiority of the proposed model.",
author = "{Hossain Lipu}, {M. S.} and Hannan, {M. A.} and Aini Hussain and Saad, {M. H.M.} and A. Ayob and Uddin, {M. N.}",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/IAS.2018.8544607",
language = "English",
note = "2018 IEEE Industry Applications Society Annual Meeting, IAS 2018 ; Conference date: 26-11-2018",

}

Hossain Lipu, MS, Hannan, MA, Hussain, A, Saad, MHM, Ayob, A & Uddin, MN 2018, 'Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm', Paper presented at 2018 IEEE Industry Applications Society Annual Meeting, IAS 2018, 26/11/18. https://doi.org/10.1109/IAS.2018.8544607

Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm. / Hossain Lipu, M. S.; Hannan, M. A.; Hussain, Aini; Saad, M. H.M.; Ayob, A.; Uddin, M. N.

2018. Paper presented at 2018 IEEE Industry Applications Society Annual Meeting, IAS 2018, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm

AU - Hossain Lipu, M. S.

AU - Hannan, M. A.

AU - Hussain, Aini

AU - Saad, M. H.M.

AU - Ayob, A.

AU - Uddin, M. N.

PY - 2018/11/26

Y1 - 2018/11/26

N2 - © 2018 IEEE This paper develops a state of charge (SOC) estimation model for a lithium-ion battery using an improved extreme learning machine (ELM) algorithm. ELM is suitable for SOC estimation since ELM algorithm has fast estimation speed, good generalization performance, and high accuracy. However, the performance of ELM is highly dependent on training accuracy and number of neurons in a hidden layer. Hence, gravitational search algorithm (GSA) is applied to improve the ELM computational intelligence by searching for the optimal value hidden layer neurons. The optimal ELM based GSA model does not require internal battery knowledge and mathematical model for SOC estimation. The model robustness is validated at different temperatures using different EV drive cycles. The performance of ELM-GSA model is verified with two popular neural network methods; back-propagation neural network (BPNN) and radial basis function neural network (RBFNN). The results are evaluatedusing different error rates and computation cost. The results demonstrate that the ELM-GSA model offers high accuracy and low SOC error rate than BPNN-GSA and RBFNN-GSA models. Furthermore, a detailed comparative study between the proposed model and existing SOC strategies is conducted which also demonstrates the superiority of the proposed model.

AB - © 2018 IEEE This paper develops a state of charge (SOC) estimation model for a lithium-ion battery using an improved extreme learning machine (ELM) algorithm. ELM is suitable for SOC estimation since ELM algorithm has fast estimation speed, good generalization performance, and high accuracy. However, the performance of ELM is highly dependent on training accuracy and number of neurons in a hidden layer. Hence, gravitational search algorithm (GSA) is applied to improve the ELM computational intelligence by searching for the optimal value hidden layer neurons. The optimal ELM based GSA model does not require internal battery knowledge and mathematical model for SOC estimation. The model robustness is validated at different temperatures using different EV drive cycles. The performance of ELM-GSA model is verified with two popular neural network methods; back-propagation neural network (BPNN) and radial basis function neural network (RBFNN). The results are evaluatedusing different error rates and computation cost. The results demonstrate that the ELM-GSA model offers high accuracy and low SOC error rate than BPNN-GSA and RBFNN-GSA models. Furthermore, a detailed comparative study between the proposed model and existing SOC strategies is conducted which also demonstrates the superiority of the proposed model.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85059944034&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85059944034&origin=inward

U2 - 10.1109/IAS.2018.8544607

DO - 10.1109/IAS.2018.8544607

M3 - Paper

ER -

Hossain Lipu MS, Hannan MA, Hussain A, Saad MHM, Ayob A, Uddin MN. Extreme learning machine for SOC estimation of lithium-ion battery using gravitational search algorithm. 2018. Paper presented at 2018 IEEE Industry Applications Society Annual Meeting, IAS 2018, . https://doi.org/10.1109/IAS.2018.8544607