Deep learning framework designed for high-performance lithium-ion batteries state monitoring

Accurate state of charge (SOC) estimation is crucial for ensuring the safety of batteries, especially in real-time battery management system (BMS) applications. Deep learning methods have become increasingly popular, driving significant advancements in battery research across various fields. However...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Renewable & sustainable energy reviews Ročník 218; s. 115803
Hlavní autoři:	Takyi-Aninakwa, Paul, Wang, Shunli, Liu, Guangchen, Fernandez, Carlos, Kang, Wenbin, Song, Yingze
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.08.2025
Témata:	Deep-stacked denoising autoencoder Lithium-ion batteries Long short-term memory Secondary scale feature extraction State of charge estimation Lithium-ion batteries Long short-term memory State of charge estimation Deep-stacked denoising autoencoder Secondary scale feature extraction
ISSN:	1364-0321
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Accurate state of charge (SOC) estimation is crucial for ensuring the safety of batteries, especially in real-time battery management system (BMS) applications. Deep learning methods have become increasingly popular, driving significant advancements in battery research across various fields. However, their accuracy is limited due to the nonlinear adverse driving conditions batteries experience during operation and an over-reliance on raw battery information. In this work, a deep-stacked denoising autoencoder is established for a long short-term memory model that incorporates a transfer learning mechanism to estimate and study the SOC from an electrochemical perspective. More importantly, this proposed model is designed to extract and optimize the electrochemical features from the training data on a secondary scale, improving noise reduction and the precision of initial weights. This adaptation allows for accurate SOC estimation of batteries while minimizing interference and divergence. For large-scale applicability, the proposed model is tested with high-performance lithium-ion batteries featuring different morphologies under a range of complex loads and driving conditions. The experimental results highlight the distinct behaviors of the tested batteries. Moreover, the performance of the proposed model demonstrates its effectiveness and outperforms existing models, achieving a mean absolute error of 0.04721% and a coefficient of determination of 98.99%, facilitating more precise state monitoring of batteries through secondary feature extraction. •A DSDA-LSTM model enhances state monitoring for lithium-ion batteries in real-time.•The model optimizes secondary electrochemical feature extraction for accuracy improvement.•The challenges of noise and inaccurate initial weights in SOC estimation are solved.•Transfer learning boosts model performance across battery types and driving conditions.•Achieves superior state estimation accuracy with MAE of 0.04721 % and R2 of 98.99 %.
ISSN:	1364-0321
DOI:	10.1016/j.rser.2025.115803