Publication:
Differential Search Optimized Random Forest Regression Algorithm for State of Charge Estimation in Electric Vehicle Batteries

Simple item page
dc.contributor.authorHossain Lipu M.S.en_US
dc.contributor.authorHannan M.A.en_US
dc.contributor.authorHussain A.en_US
dc.contributor.authorAnsari S.en_US
dc.contributor.authorAyob A.en_US
dc.contributor.authorSaad M.H.M.en_US
dc.contributor.authorMuttaqi K.M.en_US
dc.contributor.authorid36518949700en_US
dc.contributor.authorid7103014445en_US
dc.contributor.authorid57208481391en_US
dc.contributor.authorid57218906707en_US
dc.contributor.authorid26666566900en_US
dc.contributor.authorid7202075525en_US
dc.contributor.authorid55582332500en_US
dc.date.accessioned2023-05-29T09:09:51Z
dc.date.available2023-05-29T09:09:51Z
dc.date.issued2021
dc.descriptionBattery management systems; Charging (batteries); Data handling; Decision trees; Digital storage; Electric vehicles; Learning algorithms; Lithium-ion batteries; Machine learning; Differential search algorithm; Electric vehicle batteries; Lithium ions; Lithiumion battery; Random forest regression; Random forests; Regression algorithms; Search Algorithms; State-of-charge estimation; States of charges; Regression analysisen_US
dc.description.abstractThis paper presents an improved machine learning approach for the accurate and robust state of charge (SOC) in electric vehicle (EV) batteries using differential search optimized random forest regression (RFR) algorithm. The precise SOC estimation confirms the safety and reliability of EV. Nevertheless, SOC is influenced by numerous factors which cannot be measured directly. RFR is suitable for SOC estimation due to its robustness to noise, overfitting issues and capacity to work with huge datasets. However, proper selection of RFR architecture and hyper-parameters combination remains a key issue to be explored. Hence, a differential search algorithm (DSA) is employed to search for the optimal values of trees and leaves in RFR algorithm. DSA optimized RFR eliminates the utilization of the filter in data pre-processing steps and does not require a detailed understanding and knowledge about battery chemistry, rather only needs sensors to monitor battery voltage and current. The developed approach is validated at room temperature using two types of lithium-ion batteries under a pulse discharge test. In addition, the proposed model is verified under varying temperature settings under EV drive cycles. The experimental results demonstrate that the DSA optimized RFR algorithm is superior to other optimized machine learning approaches in achieving a lower error rate which illustrates the suitability of the proposed model in the online battery management system. � 2021 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1109/IAS48185.2021.9677106
dc.identifier.scopus2-s2.0-85124686814
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85124686814&doi=10.1109%2fIAS48185.2021.9677106&partnerID=40&md5=bd61a95ea787f25d8391c48fe4842f83
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/26390
dc.identifier.volume2021-October
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.sourceScopus
dc.sourcetitleConference Record - IAS Annual Meeting (IEEE Industry Applications Society)
dc.titleDifferential Search Optimized Random Forest Regression Algorithm for State of Charge Estimation in Electric Vehicle Batteriesen_US
dc.typeConference Paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS