Deep learning-driven estimation and multi-objective optimization of lithium-ion battery parameters for enhanced EV/HEV performance

Nima Khosravi and Adel Oubelaid

Energy, 2025, vol. 320, issue C

Abstract: Accurate parameter identification of lithium-ion batteries (LIBs) is critical for the performance and safety of electric vehicles (EVs). This study introduces a hybrid approach to efficiently identify and forecast LIB parameters under dynamic operating conditions. The hybrid method combines the hierarchical deep learning neural network (HDLNN) with the walrus optimization (WO) technique. While HDLNN predicts the battery (BAT) components and greatly reduces the error between estimated and measured voltage, the WO method is used to determine optimal settings. The suggested method improves BAT modeling accuracy and ensures optimal performance under different load scenarios. Three complementary algorithms, the genetic algorithm (GA), the black hole algorithm (BHA), and harmony search (HS) have been used for comparison in order to confirm the efficacy of the WO approach. Results indicate the superiority of the WO method, achieving a faster computation time of 0.17 s and reducing voltage error by 4.65 mV, outperforming the alternative algorithms. The results demonstrate how the WO-HDLNN hybrid technique can reliably and steadily detect BAT characteristics in LIB applications for both EVs and hybrid EVs.

Keywords: Battery management; Electric vehicle; Lithium-ion battery (LIB); LIB component identification (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225007893
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:320:y:2025:i:c:s0360544225007893

DOI: 10.1016/j.energy.2025.135147

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().