State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extraction
With the increasing demands for battery safety management, data-driven method becomes a promising solution for highly accurate battery state of health (SOH) estimation. However, the data-driven method faces problems of poor interpretability and high dependence on input features. This paper proposes...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-08-01
|
Series: | Frontiers in Energy Research |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1205165/full |
_version_ | 1797748299815452672 |
---|---|
author | Wentao Wang Gaoyuan Yang Muxi Li Zuoyi Yan Lisheng Zhang Hanqing Yu Kaiyi Yang Pengchang Jiang Wei Hua Yong Zhang Bosong Zou Kai Yang |
author_facet | Wentao Wang Gaoyuan Yang Muxi Li Zuoyi Yan Lisheng Zhang Hanqing Yu Kaiyi Yang Pengchang Jiang Wei Hua Yong Zhang Bosong Zou Kai Yang |
author_sort | Wentao Wang |
collection | DOAJ |
description | With the increasing demands for battery safety management, data-driven method becomes a promising solution for highly accurate battery state of health (SOH) estimation. However, the data-driven method faces problems of poor interpretability and high dependence on input features. This paper proposes a SOH estimation method that integrates data-driven model and signal analysis method. Specifically, the differential thermal voltammetry (DTV) analysis method is used to analyze aging characteristics to obtain features strongly related to battery aging and solve the problem of poor interpretability of data-driven methods. The use of local linear embedding method (LLE) for feature extraction has improved model efficiency. A data-driven model is constructed with the Bi-directional long short-term memory (Bi-LSTM) as the core, and the attention mechanism (AM) is added to focus on important parts of the sequence to further improve the accuracy of the model. The proposed method is validated based on the Oxford battery degradation dataset, and the results show that the proposed method achieves high accuracy and strong robustness in SOH estimation with a root mean square error (RMSE) maintained at about 0.4%. This method has the potential to be employed on cloud platforms or end-cloud collaboration systems for online implementation. |
first_indexed | 2024-03-12T16:03:55Z |
format | Article |
id | doaj.art-b414b1b30a324efe8e2bd9d6e52a5fe8 |
institution | Directory Open Access Journal |
issn | 2296-598X |
language | English |
last_indexed | 2024-03-12T16:03:55Z |
publishDate | 2023-08-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Energy Research |
spelling | doaj.art-b414b1b30a324efe8e2bd9d6e52a5fe82023-08-09T14:31:08ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-08-011110.3389/fenrg.2023.12051651205165State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extractionWentao Wang0Gaoyuan Yang1Muxi Li2Zuoyi Yan3Lisheng Zhang4Hanqing Yu5Kaiyi Yang6Pengchang Jiang7Wei Hua8Yong Zhang9Bosong Zou10Kai Yang11School of Transportation Science and Engineering, Beihang University, Beijing, ChinaSchool of Transportation Science and Engineering, Beihang University, Beijing, ChinaChina First Automobile Group Corporation, Beijing, ChinaSchool of Transportation Science and Engineering, Beihang University, Beijing, ChinaSchool of Transportation Science and Engineering, Beihang University, Beijing, ChinaSchool of Transportation Science and Engineering, Beihang University, Beijing, ChinaSchool of Transportation Science and Engineering, Beihang University, Beijing, ChinaSchool of Electrical Engineering, Southeast University, Nanjing, ChinaSchool of Electrical Engineering, Southeast University, Nanjing, ChinaCollege of Automobile and Traffic Engineering, Nanjing Forestry University, Nanjing, ChinaChina Software Testing Center, Beijing, ChinaDepartment of Electrical and Electronic Engineering, Advanced Technology Institute, University of Surrey, Guildford, United KingdomWith the increasing demands for battery safety management, data-driven method becomes a promising solution for highly accurate battery state of health (SOH) estimation. However, the data-driven method faces problems of poor interpretability and high dependence on input features. This paper proposes a SOH estimation method that integrates data-driven model and signal analysis method. Specifically, the differential thermal voltammetry (DTV) analysis method is used to analyze aging characteristics to obtain features strongly related to battery aging and solve the problem of poor interpretability of data-driven methods. The use of local linear embedding method (LLE) for feature extraction has improved model efficiency. A data-driven model is constructed with the Bi-directional long short-term memory (Bi-LSTM) as the core, and the attention mechanism (AM) is added to focus on important parts of the sequence to further improve the accuracy of the model. The proposed method is validated based on the Oxford battery degradation dataset, and the results show that the proposed method achieves high accuracy and strong robustness in SOH estimation with a root mean square error (RMSE) maintained at about 0.4%. This method has the potential to be employed on cloud platforms or end-cloud collaboration systems for online implementation.https://www.frontiersin.org/articles/10.3389/fenrg.2023.1205165/fullstate of healthdeep learningattention mechanismdifferential thermal voltammetrylocally linear embedding |
spellingShingle | Wentao Wang Gaoyuan Yang Muxi Li Zuoyi Yan Lisheng Zhang Hanqing Yu Kaiyi Yang Pengchang Jiang Wei Hua Yong Zhang Bosong Zou Kai Yang State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extraction Frontiers in Energy Research state of health deep learning attention mechanism differential thermal voltammetry locally linear embedding |
title | State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extraction |
title_full | State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extraction |
title_fullStr | State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extraction |
title_full_unstemmed | State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extraction |
title_short | State-of-health estimation for lithium-ion batteries based on Bi-LSTM-AM and LLE feature extraction |
title_sort | state of health estimation for lithium ion batteries based on bi lstm am and lle feature extraction |
topic | state of health deep learning attention mechanism differential thermal voltammetry locally linear embedding |
url | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1205165/full |
work_keys_str_mv | AT wentaowang stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT gaoyuanyang stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT muxili stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT zuoyiyan stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT lishengzhang stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT hanqingyu stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT kaiyiyang stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT pengchangjiang stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT weihua stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT yongzhang stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT bosongzou stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction AT kaiyang stateofhealthestimationforlithiumionbatteriesbasedonbilstmamandllefeatureextraction |