View in EDS

Electric vehicle parameter identification and state of charge estimation of Li-ion​ batteries: Hybrid WSO-HDLNN method.

Saved in:
Bibliographic Details
Title: Electric vehicle parameter identification and state of charge estimation of Li-ion​ batteries: Hybrid WSO-HDLNN method.
Authors: Varatharajalu, Kandasamy1 (AUTHOR) kandasamy.v.eee@kct.ac.in, Manoharan, Mathankumar2 (AUTHOR) mathankumarbit@gmail.com, Palanichamy, Thamil Selvi C3 (AUTHOR) cpthamil.selvi72@gmail.com, Subramani, Sivaranjani4 (AUTHOR) sivaranjanis@skcet.ac.in
Source: ISA Transactions. Nov2023, Vol. 142, p347-359. 13p.
Subjects: Parameter identification, Electric batteries, Optimization algorithms, Storage batteries, Electric vehicles
Abstract: This manuscript proposes a hybrid method for measuring the battery's dynamic electrical response as it is compressed by an external-force. The proposed hybrid technique is the wrapper of the War Strategy Optimization algorithm and Hierarchical Deep Learning Neural Network, commonly called as WSO-HDLNN technique. The main aim of the proposed method is to lessen the battery-voltage error. The War Strategy Optimization method detects the parameters of the battery method. The Hierarchical Deep Learning Neural Network is used to predict the dynamic-electrical-response of the battery when it deforms during external-force. By using the proposed method, the estimated voltage and measured voltage error are reduced, and identifies the parameter effectively. Finally, the proposed method is done in the MATLAB platform and it is compared with different existing approaches. The error of the proposed method is 4 mV, the Jellyfish Search Optimizer method error is 6 mV, the Heap-based Optimizer method error is 12 mV, and the Grey Wolf Optimizer method error is 14 mV. The proposed method time is 0.7 s The proposed method shows better results in all methods, like Jellyfish Search Optimizer, Heap-based Optimizer, and Grey Wolf Optimizer, The proposed method provides less computation time and error than the existing one is proved from the simulation outcome. • This manuscript proposes a hybrid technique for measuring the battery's dynamic electrical response. • The proposed hybrid technique is the wrapper of WSO and HDLNN. • The main aim of the proposed method is to lessen the battery-voltage error. • WSO is detects the parameters of battery; HDLNN is predict the electrical response of battery. • The estimated voltage and measured voltage error is reduced and identifies the parameter effectively. [ABSTRACT FROM AUTHOR]
Copyright of ISA Transactions is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:This manuscript proposes a hybrid method for measuring the battery's dynamic electrical response as it is compressed by an external-force. The proposed hybrid technique is the wrapper of the War Strategy Optimization algorithm and Hierarchical Deep Learning Neural Network, commonly called as WSO-HDLNN technique. The main aim of the proposed method is to lessen the battery-voltage error. The War Strategy Optimization method detects the parameters of the battery method. The Hierarchical Deep Learning Neural Network is used to predict the dynamic-electrical-response of the battery when it deforms during external-force. By using the proposed method, the estimated voltage and measured voltage error are reduced, and identifies the parameter effectively. Finally, the proposed method is done in the MATLAB platform and it is compared with different existing approaches. The error of the proposed method is 4 mV, the Jellyfish Search Optimizer method error is 6 mV, the Heap-based Optimizer method error is 12 mV, and the Grey Wolf Optimizer method error is 14 mV. The proposed method time is 0.7 s The proposed method shows better results in all methods, like Jellyfish Search Optimizer, Heap-based Optimizer, and Grey Wolf Optimizer, The proposed method provides less computation time and error than the existing one is proved from the simulation outcome. • This manuscript proposes a hybrid technique for measuring the battery's dynamic electrical response. • The proposed hybrid technique is the wrapper of WSO and HDLNN. • The main aim of the proposed method is to lessen the battery-voltage error. • WSO is detects the parameters of battery; HDLNN is predict the electrical response of battery. • The estimated voltage and measured voltage error is reduced and identifies the parameter effectively. [ABSTRACT FROM AUTHOR]
ISSN:00190578
DOI:10.1016/j.isatra.2023.07.029