Have a personal or library account? Click to login
Adaptive Hybrid LSTM-EKF Model for Reliable State of Charge Estimation in Lithium-Ion Batteries Under Noisy Conditions Cover

Adaptive Hybrid LSTM-EKF Model for Reliable State of Charge Estimation in Lithium-Ion Batteries Under Noisy Conditions

Acta Mechanica et Automatica
Volume 19 (2025): Issue 4 (December 2025)
By: Karim KHEMIRI and  Ridha DJEBALI  
Open Access
|Dec 2025

Figures & Tables

Fig. 1.

Hybrid LSTM-EKF architecture for SOC estimation
Hybrid LSTM-EKF architecture for SOC estimation

Fig. 2.

Experimental voltage, current, temperature and SoC profiles of a lithium-ion battery cell during the discharge process
Experimental voltage, current, temperature and SoC profiles of a lithium-ion battery cell during the discharge process

Fig. 3.

Training and validation loss for LSTM Model
Training and validation loss for LSTM Model

Fig. 4.

Evolution of the adaptive fusion factor (αk)
Evolution of the adaptive fusion factor (αk)

Fig. 5.

SoC Estimation results using LSTM, BiLSTM, LSTM-Attention, EKF and LSTM-EKF
SoC Estimation results using LSTM, BiLSTM, LSTM-Attention, EKF and LSTM-EKF

Fig. 6.

Comparison of RMSE and MAE for different SoC estimation methods
Comparison of RMSE and MAE for different SoC estimation methods

Comparative performance of SoC estimation methods

MethodRMSEMAERMSE Improvement(%)AME Improvement (%)
LSTM0.0210.0160.000.00
BiLSTM0.0230.018-7.37-9.78
LSTM-Attention0.0220.017-2.82-2.12
EKF0.0120.00943.9243.88
LSTM-EKF0.0060.00570.7770.80
DOI: https://doi.org/10.2478/ama-2025-0085 | Journal eISSN: 2300-5319 | Journal ISSN: 1898-4088
Journal RSS Feed
Language: English
Page range: 761 - 767
Submitted on: Jun 26, 2025
|
Accepted on: Nov 9, 2025
|
Published on: Dec 31, 2025
Published by: Bialystok University of Technology
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
lithiumion batteries,
state of charge estimation,
long short-term memory,
extended Kalman filter,
adaptive fusion,
hybrid modeling,
noisy environment
Related subjects:
Engineering,
Electrical engineering,
Electronics,
Mechanical engineering,
Mechanics,
Bioengineering and biomedical engineering,
Biomechanics,
Civil engineering,
Environmental engineering

© 2025 Karim KHEMIRI, Ridha DJEBALI, published by Bialystok University of Technology
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 19 (2025): Issue 4 (December 2025)Next article