Combined Framework for State of Charge Estimation of Lithium-Ion Batteries: Optimized LSTM Network Integrated with IAOA and AUKF
Mathematics · 13.08.2025 · 13 (16) · 2590
DOI: 10.3390/math13162590 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 13.08.2025. Verfasst von Jing Han und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China (NNSF), Hunan Natural Science Foundation.
Abstract (Originalsprache)
The State of Charge (SOC) is vital for battery system management. Enhancing SOC estimation boosts system performance. This paper presents a combined framework that improves SOC estimation’s accuracy and stability for electric vehicles. The framework combines a Long Short-Term Memory (LSTM) network with an Adaptive Unscented Kalman Filter (AUKF). An Improved Arithmetic Optimization Algorithm (IAOA) fine-tunes the LSTM’s hyperparameters. Its novelty lies in its adaptive iteration algorithm, which adjusts iterations based on a threshold, optimizing computational efficiency. It also integrates a genetic mutation strategy into the AOA to overcome local optima by mutating iterations. Additionally, the AUKF’s adaptive noise algorithm updates noise covariance in real-time, enhancing SOC estimation precision. The inputs of the proposed method include battery current, voltage, and temperature, then producing an accurate SOC output. The predictions of LSTM are refined through AUKF to obtain reliable SOC estimation. The proposed framework is firstly evaluated utilizing a public dataset and then applied to battery packs on actual engineering vehicles. Results indicate that the Root Mean Square Errors (RMSEs) of the SOC estimations in practical applications are below 0.6%, and the Maximum Errors (MAX) are under 3.3%, demonstrating the accuracy and robustness of the proposed combined framework.
Förderung
- National Natural Science Foundation of China (NNSF)
- Hunan Natural Science Foundation
Zitieren
APA
Han, J., Dong, Y., & Wang, W. (2025). Combined Framework for State of Charge Estimation of Lithium-Ion Batteries: Optimized LSTM Network Integrated with IAOA and AUKF. Mathematics, 13(16), 2590. https://doi.org/10.3390/math13162590
Vancouver
Han J, Dong Y, Wang W. Combined Framework for State of Charge Estimation of Lithium-Ion Batteries: Optimized LSTM Network Integrated with IAOA and AUKF. Mathematics. 2025;13(16):2590. doi:10.3390/math13162590
BibTeX
@article{Han2025,
author = {Han, Jing and Dong, Yaolin and Wang, Wei},
title = {Combined Framework for State of Charge Estimation of Lithium-Ion Batteries: Optimized LSTM Network Integrated with IAOA and AUKF},
journal = {Mathematics},
year = {2025},
volume = {13},
number = {16},
pages = {2590},
doi = {10.3390/math13162590}
}
EUVIMED