State of Charge Estimation for Sodium-Ion Batteries Based on LSTM Network and Unscented Kalman Filter

State of Charge Estimation for Sodium-Ion Batteries Based on LSTM Network and Unscented Kalman Filter

With the increasing application of sodium-ion batteries in energy storage systems, accurate state of charge (SOC) estimation plays a vital role in ensuring both available battery capacity and operational safety. Traditional Kalman-filter-based methods often suffer from limited model expressiveness o...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangang Zuo, Xiaoheng Fu, Xu Han, Meng Sun, Yuqian Fan
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Batteries
Subjects:
SOC estimation
long short-term memory network
unscented Kalman filter
equivalent circuit model
Online Access:https://www.mdpi.com/2313-0105/11/7/274
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the increasing application of sodium-ion batteries in energy storage systems, accurate state of charge (SOC) estimation plays a vital role in ensuring both available battery capacity and operational safety. Traditional Kalman-filter-based methods often suffer from limited model expressiveness or oversimplified physical assumptions, making it difficult to balance accuracy and robustness under complex operating conditions, which may lead to unreliable estimation results. To address these challenges, this paper proposes a hybrid framework that combines an unscented Kalman filter (UKF) with a long short-term memory (LSTM) neural network for SOC estimation. Under various driving conditions, the UKF—based on a second-order equivalent circuit model with online parameter identification—provides physically interpretable estimates, while LSTM effectively captures complex temporal dependencies. Experimental results under CLTC, NEDC, and WLTC cycles demonstrate that the proposed LSTM-UKF approach reduces the mean absolute error (MAE) by an average of 2% and the root mean square error (RMSE) by an average of 3% compared to standalone methods. The proposed framework exhibits excellent adaptability across different scenarios, offering a precise, stable, and robust solution for SOC estimation in sodium-ion batteries.
ISSN:2313-0105

Similar Items