A hybrid LSTM-transformer model for accurate

With the widespread application of lithium-ion batteries in electric vehicles and energy storage systems, health monitoring and remaining useful life prediction have become critical components of battery management systems. To address the challenges posed by the high nonlinearity and long-term depen...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianren Zhao, Yanhui Zhang, Minghao Wang, Wei Feng, Shengxian Cao, Gong Wang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Electronics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/felec.2025.1654344/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849231519993823232
author Tianren Zhao
Yanhui Zhang
Minghao Wang
Wei Feng
Shengxian Cao
Gong Wang
author_facet Tianren Zhao
Yanhui Zhang
Minghao Wang
Wei Feng
Shengxian Cao
Gong Wang
author_sort Tianren Zhao
collection DOAJ
description With the widespread application of lithium-ion batteries in electric vehicles and energy storage systems, health monitoring and remaining useful life prediction have become critical components of battery management systems. To address the challenges posed by the high nonlinearity and long-term dependency in battery degradation modeling, this paper proposes a deep hybrid architecture that integrates Long Short-Term Memory networks with Transformer mechanisms, aiming to improve the accuracy and robustness of RUL prediction. Firstly, time-series samples are constructed from raw battery data, and physically consistent temperature-derived features—including average temperature, temperature range, and temperature fluctuation—are engineered. Data preprocessing is performed using standardization and Yeo-Johnson transformation. The model employs LSTM modules to capture local temporal patterns, while the Transformer modules extract global dependencies through multi-head self-attention mechanisms. These complementary features are fused to enable joint modeling of battery health states. The regression task is optimized using the Mean Squared Error loss function and trained with the Adam optimizer. Experimental results on the MIT battery dataset demonstrate the proposed model achieves excellent performance in a 7-step multi-point prediction task, with a Root Mean Square Error of 0.0085, Mean Absolute Percentage Error of 0.0200, and a coefficient of determination of 0.9902. Compared with alternative models such as MC-LSTM and XGBoost-LSTM, the proposed model exhibits superior accuracy and stability. Residual analysis and visualization further confirm the model’s unbiased and stable predictive capability. This study shows that the LSTM-Transformer hybrid architecture offers significant potential in modeling complex battery degradation processes and enhancing RUL prediction accuracy, providing effective technical support for the development of intelligent battery health management systems.
format Article
id doaj-art-9dc47da02e604688808e8300abaac47d
institution Kabale University
issn 2673-5857
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Electronics
spelling doaj-art-9dc47da02e604688808e8300abaac47d2025-08-21T05:27:39ZengFrontiers Media S.A.Frontiers in Electronics2673-58572025-08-01610.3389/felec.2025.16543441654344A hybrid LSTM-transformer model for accurateTianren Zhao0Yanhui Zhang1Minghao Wang2Wei Feng3Shengxian Cao4Gong Wang5Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaUniversity of Macau, Taipa, Macao SAR, ChinaShenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaNortheast Electric Power University, Jilin, ChinaNortheast Electric Power University, Jilin, ChinaWith the widespread application of lithium-ion batteries in electric vehicles and energy storage systems, health monitoring and remaining useful life prediction have become critical components of battery management systems. To address the challenges posed by the high nonlinearity and long-term dependency in battery degradation modeling, this paper proposes a deep hybrid architecture that integrates Long Short-Term Memory networks with Transformer mechanisms, aiming to improve the accuracy and robustness of RUL prediction. Firstly, time-series samples are constructed from raw battery data, and physically consistent temperature-derived features—including average temperature, temperature range, and temperature fluctuation—are engineered. Data preprocessing is performed using standardization and Yeo-Johnson transformation. The model employs LSTM modules to capture local temporal patterns, while the Transformer modules extract global dependencies through multi-head self-attention mechanisms. These complementary features are fused to enable joint modeling of battery health states. The regression task is optimized using the Mean Squared Error loss function and trained with the Adam optimizer. Experimental results on the MIT battery dataset demonstrate the proposed model achieves excellent performance in a 7-step multi-point prediction task, with a Root Mean Square Error of 0.0085, Mean Absolute Percentage Error of 0.0200, and a coefficient of determination of 0.9902. Compared with alternative models such as MC-LSTM and XGBoost-LSTM, the proposed model exhibits superior accuracy and stability. Residual analysis and visualization further confirm the model’s unbiased and stable predictive capability. This study shows that the LSTM-Transformer hybrid architecture offers significant potential in modeling complex battery degradation processes and enhancing RUL prediction accuracy, providing effective technical support for the development of intelligent battery health management systems.https://www.frontiersin.org/articles/10.3389/felec.2025.1654344/fulllithium-ion batteryremaining useful lifeLSTMtransformertime-series prediction
spellingShingle Tianren Zhao
Yanhui Zhang
Minghao Wang
Wei Feng
Shengxian Cao
Gong Wang
A hybrid LSTM-transformer model for accurate
Frontiers in Electronics
lithium-ion battery
remaining useful life
LSTM
transformer
time-series prediction
title A hybrid LSTM-transformer model for accurate
title_full A hybrid LSTM-transformer model for accurate
title_fullStr A hybrid LSTM-transformer model for accurate
title_full_unstemmed A hybrid LSTM-transformer model for accurate
title_short A hybrid LSTM-transformer model for accurate
title_sort hybrid lstm transformer model for accurate
topic lithium-ion battery
remaining useful life
LSTM
transformer
time-series prediction
url https://www.frontiersin.org/articles/10.3389/felec.2025.1654344/full
work_keys_str_mv AT tianrenzhao ahybridlstmtransformermodelforaccurate
AT yanhuizhang ahybridlstmtransformermodelforaccurate
AT minghaowang ahybridlstmtransformermodelforaccurate
AT weifeng ahybridlstmtransformermodelforaccurate
AT shengxiancao ahybridlstmtransformermodelforaccurate
AT gongwang ahybridlstmtransformermodelforaccurate
AT tianrenzhao hybridlstmtransformermodelforaccurate
AT yanhuizhang hybridlstmtransformermodelforaccurate
AT minghaowang hybridlstmtransformermodelforaccurate
AT weifeng hybridlstmtransformermodelforaccurate
AT shengxiancao hybridlstmtransformermodelforaccurate
AT gongwang hybridlstmtransformermodelforaccurate