Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer

Abstract Accurately predicting the State of Health (SOH) of new energy vehicle batteries is critical for ensuring their reliable operation and extending battery’s service life. To address the issue of low SOH prediction accuracy across different prediction lengths, this paper proposes a prediction m...

Full description

Saved in:
Bibliographic Details
Main Authors: Weijie Tang, Jiayan Chen, Dongjiao Chen
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-85492-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832594819886612480
author Weijie Tang
Jiayan Chen
Dongjiao Chen
author_facet Weijie Tang
Jiayan Chen
Dongjiao Chen
author_sort Weijie Tang
collection DOAJ
description Abstract Accurately predicting the State of Health (SOH) of new energy vehicle batteries is critical for ensuring their reliable operation and extending battery’s service life. To address the issue of low SOH prediction accuracy across different prediction lengths, this paper proposes a prediction method based on long-short-term battery degradation feature extraction and FEA-TimeMixer model. First, a novel automatic SOH extraction algorithm for offline charging data is introduced to label the battery SOH degradation data. Then, the autoencoder is utilized to fuse the features of long-term and short-term SOH degradation trends extracted by empirical degradation models and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise to improve the prediction accuracy over different prediction lengths. Finally, a Frequency Enhanced Attention (FEA) mechanism is introduced to improve the TimeMixer model, which integrates time-domain and frequency-domain information to overcome the limitations of the original model in capturing frequency-domain features. Experimental results show that the proposed method achieves a Mean Absolute Error of less than 0.0219 for short-term SOH predictions and less than 0.1007 for long-term SOH predictions, outperforming other deep learning models in prediction accuracy over multiple prediction lengths.
format Article
id doaj-art-3320f22fb67647e18c74f07ae0314c00
institution Kabale University
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-3320f22fb67647e18c74f07ae0314c002025-01-19T12:17:08ZengNature PortfolioScientific Reports2045-23222025-01-0115112210.1038/s41598-025-85492-3Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixerWeijie Tang0Jiayan Chen1Dongjiao Chen2College of Energy Environment and Safety Engineering and College of Carbon Metrology, China Jiliang UniversityCollege of Quality and Standardization, China Jiliang UniversityHangzhou Xiangce Electronic Technology Co.LtdAbstract Accurately predicting the State of Health (SOH) of new energy vehicle batteries is critical for ensuring their reliable operation and extending battery’s service life. To address the issue of low SOH prediction accuracy across different prediction lengths, this paper proposes a prediction method based on long-short-term battery degradation feature extraction and FEA-TimeMixer model. First, a novel automatic SOH extraction algorithm for offline charging data is introduced to label the battery SOH degradation data. Then, the autoencoder is utilized to fuse the features of long-term and short-term SOH degradation trends extracted by empirical degradation models and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise to improve the prediction accuracy over different prediction lengths. Finally, a Frequency Enhanced Attention (FEA) mechanism is introduced to improve the TimeMixer model, which integrates time-domain and frequency-domain information to overcome the limitations of the original model in capturing frequency-domain features. Experimental results show that the proposed method achieves a Mean Absolute Error of less than 0.0219 for short-term SOH predictions and less than 0.1007 for long-term SOH predictions, outperforming other deep learning models in prediction accuracy over multiple prediction lengths.https://doi.org/10.1038/s41598-025-85492-3BatteryState of healthAutoencoderCEEMDANSelf-attentionTimeMixer
spellingShingle Weijie Tang
Jiayan Chen
Dongjiao Chen
Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer
Scientific Reports
Battery
State of health
Autoencoder
CEEMDAN
Self-attention
TimeMixer
title Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer
title_full Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer
title_fullStr Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer
title_full_unstemmed Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer
title_short Predicting EV battery state of health using long short term degradation feature extraction and FEA TimeMixer
title_sort predicting ev battery state of health using long short term degradation feature extraction and fea timemixer
topic Battery
State of health
Autoencoder
CEEMDAN
Self-attention
TimeMixer
url https://doi.org/10.1038/s41598-025-85492-3
work_keys_str_mv AT weijietang predictingevbatterystateofhealthusinglongshorttermdegradationfeatureextractionandfeatimemixer
AT jiayanchen predictingevbatterystateofhealthusinglongshorttermdegradationfeatureextractionandfeatimemixer
AT dongjiaochen predictingevbatterystateofhealthusinglongshorttermdegradationfeatureextractionandfeatimemixer