AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Chinese Journal of Electrical Engineering Article
PDF (63.4 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

A Multitime-scale Deep Learning Model for Lithium-ion Battery Health Assessment Using Soft Parameter-sharing Mechanism

Lulu Wang1, Kun Zheng2, Yijing Li3, Zhipeng Yang4, Feifan Zhou4, Jia Guo5, Jinhao Meng3,4( )
North China Electric Power Test and Research Institute of China Datang Group Science and Technology Research Institute Co., Ltd., Beijing 100040, China
School of Future Technology, Xi’an Jiaotong University, Xi’an 710049, China
National Innovation Platform (Center) for Industry-Education Integration of Energy Storage Technology, Xi’an Jiaotong University, Xi’an 710049, China
School of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
Department of Mechanical Engineering, Imperial College London, London SW7 2AZ, UK
Show Author Information

Graphical Abstract

Efficient assessment of battery degradation is important to effectively utilize and maintain battery management systems. This study introduces an innovative residual convolutional network (RCN)-gated recurrent unit (GRU) model to accurately assess health of lithium-ion batteries on multiple time scales. The model employs a soft parameter-sharing mechanism to identify both short- and long-term degradation patterns. The continuously looped Q(V), T(V), dQ dV, and dT dV are extracted to form a four-channel image, from which the RCN can automatically extract the features and the GRU can capture the temporal features. By designing a soft parameter-sharing mechanism, the model can seamlessly predict the capacity and remaining useful life (RUL) on a dual time scale. The proposed method is validated on a large MIT-Stanford dataset comprising 124 cells, showing a high accuracy in terms of mean absolute errors of 0.00477 for capacity and 83 for RUL. Furthermore, studying the partial voltage fragment reveals the promising performance of the proposed method across various voltage ranges. Specifically, in the partial voltage segment of 2.8-3.2 V, root mean square errors of 0.0107 for capacity and 140 for RUL are achieved.

Abstract

Efficient assessment of battery degradation is important to effectively utilize and maintain battery management systems. This study introduces an innovative residual convolutional network (RCN)-gated recurrent unit (GRU) model to accurately assess health of lithium-ion batteries on multiple time scales. The model employs a soft parameter-sharing mechanism to identify both short- and long-term degradation patterns. The continuously looped Q(V), T(V), dQdV, and dTdV are extracted to form a four-channel image, from which the RCN can automatically extract the features and the GRU can capture the temporal features. By designing a soft parameter-sharing mechanism, the model can seamlessly predict the capacity and remaining useful life (RUL) on a dual time scale. The proposed method is validated on a large MIT-Stanford dataset comprising 124 cells, showing a high accuracy in terms of mean absolute errors of 0.00477 for capacity and 83 for RUL. Furthermore, studying the partial voltage fragment reveals the promising performance of the proposed method across various voltage ranges. Specifically, in the partial voltage segment of 2.8-3.2 V, root mean square errors of 0.0107 for capacity and 140 for RUL are achieved.

Keywords

Residual convolutional network-gated recurrent unitcapacity estimationsoft parameter sharingremaining useful life prediction

References

[1]

E T Sayed, A G Olabi, A H Alami, et al. Renewable energy and energy storage systems. Energies, 2023, 16(3): 1415.
Crossref Google Scholar
[2]

S Zhang, X Guo, X Zhang. Multi-objective decision analysis for data-driven based estimation of battery states: A case study of remaining useful life estimation. International Journal of Hydrogen Energy, 2020, 45(27): 14156-14173.
Crossref Google Scholar
[3]

S A Hasib, S Islam, R K Chakrabortty, et al. A comprehensive review of available battery datasets, RUL prediction approaches, and advanced battery management. IEEE Access, 2021, 9: 86166-86193.
Crossref Google Scholar
[4]

K Liu, Z Wei, C Zhang, et al. Towards long lifetime battery: AI-based manufacturing and management. IEEE/CAA Journal of Automatica Sinica, 2022, 9(7): 1139-1165.
Crossref Google Scholar
[5]

M F Ge, Y Liu, X Jiang, et al. A review on state of health estimations and remaining useful life prognostics of lithium-ion batteries. Measurement, 2021, 174: 109057.
Crossref Google Scholar
[6]

C R Birkl, M R Roberts, E McTurk, et al. Degradation diagnostics for lithium ion cells. Journal of Power Sources, 2017, 341: 373-386.
Crossref Google Scholar
[7]

A Tiane, C Okar, M Alzayed, et al. Comparing hybrid approaches of deep learning for remaining useful life prognostic of lithium-ion batteries. IEEE Access, 2024, 12: 70334-70344.
Crossref Google Scholar
[8]

Y Wang, Y Lei, N Li, et al. A multimodal dynamic parameterized bilinear factorized framework for remaining useful life prediction under variational data. Reliability Engineering & System Safety, 2024: 110025.
Crossref Google Scholar
[9]

Q Xu, M Wu, E Khoo, et al. A hybrid ensemble deep learning approach for early prediction of battery remaining useful life. IEEE/CAA Journal of Automatica Sinica, 2023, 10(1): 177-187.
Crossref Google Scholar
[10]

K Song, D Hu, Y Tong, et al. Remaining life prediction of lithium-ion batteries based on health management: A review. Journal of Energy Storage, 2023, 57: 106193.
Crossref Google Scholar
[11]

R Pan, D Yang, Y Wang, et al. Health degradation assessment of proton exchange membrane fuel cell based on an analytical equivalent circuit model. Energy, 2020, 207: 118185.
Crossref Google Scholar
[12]

Q Liu, J Zhang, K Li, et al. The remaining useful life prediction by using electrochemical model in the particle filter framework for lithium-ion batteries. IEEE Access, 2020, 8: 126661-126670.
Crossref Google Scholar
[13]

D I Stroe, M Swierczynski, A I Stroe, et al. Degradation behavior of lithium-ion batteries based on lifetime models and field measured frequency regulation mission profile. IEEE Transactions on Industry Applications, 2016, 52(6): 5009-5018.
Crossref Google Scholar
[14]

E Kim, M Kim, J Kim, et al. Data-driven methods for predicting the state of health, state of charge, and remaining useful life of Li-ion batteries: A comprehensive review. International Journal of Precision Engineering and Manufacturing, 2023, 24(7): 1281-1304.
Crossref Google Scholar
[15]

M Doyle, T F Fuller, J Newman. Modeling of galvanostatic charge and discharge of the lithium/polymer/insertion cell. Journal of the Electrochemical Society, 1993, 140(6): 1526.
Crossref Google Scholar
[16]

C Semeraro, M Caggiano, A G Olabi, et al. Battery monitoring and prognostics optimization techniques: Challenges and opportunities. Energy, 2022, 255: 124538.
Crossref Google Scholar
[17]

J Ben Ali, C Azizi, L Saidi, et al. Reliable state of health condition monitoring of Li-ion batteries based on incremental support vector regression with parameters optimization. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 2023, 237(4): 717-727.
Crossref Google Scholar
[18]

J Meng, L Cai, G Luo, et al. Lithium-ion battery state of health estimation with short-term current pulse test and support vector machine. Microelectronics Reliability, 2018, 88: 1216-1220.
Crossref Google Scholar
[19]

Z Hui, Z Shi, R Wang, et al. Health prediction of lithium-ion batteries by combining with empirical mode decomposition and PF-GPR algorithm. Materials Today Energy, 2024, 42: 101562.
Crossref Google Scholar
[20]

S Jafari, Y Byun. Optimizing battery RUL prediction of lithium-ion batteries based on Harris hawk optimization approach using random forest and LightGBM. IEEE Access, 2023, 11: 87034-87046.
Crossref Google Scholar
[21]

J Li, M Ye, Y Wang, et al. A hybrid framework for predicting the remaining useful life of battery using Gaussian process regression. Journal of Energy Storage, 2023, 66: 107513.
Crossref Google Scholar
[22]

K Liu, Y Li, X Hu, et al. Gaussian process regression with automatic relevance determination kernel for calendar aging prediction of lithium-ion batteries. IEEE Transactions on Industrial Informatics, 2019, 16(6): 3767-3777.
Crossref Google Scholar
[23]

W Xiong, G Xu, Y Li, et al. Early prediction of lithium-ion battery cycle life based on voltage-capacity discharge curves. Journal of Energy Storage, 2023, 62: 106790.
Crossref Google Scholar
[24]

Z Du, L Zuo, J Li, et al. Data-driven estimation of remaining useful lifetime and state of charge for lithium-ion battery. IEEE Transactions on Transportation Electrification, 2021, 8(1): 356-367.
Crossref Google Scholar
[25]

S Xiang, P Li, Y Huang, et al. Single gated RNN with differential weighted information storage mechanism and its application to machine RUL prediction. Reliability Engineering & System Safety, 2024, 242: 109741.
Crossref Google Scholar
[26]

M Lin, J Wu, J Meng, et al. State of health estimation with attentional long short-term memory network for lithium-ion batteries. Energy, 2023, 268: 126706.
Crossref Google Scholar
[27]

J Meng, Y You, M Lin, et al. Multi-scenarios transferable learning framework with few-shot for early lithium-ion battery lifespan trajectory prediction. Energy, 2024, 286: 129682.
Crossref Google Scholar
[28]

K Park, Y Choi, W J Choi, et al. LSTM-based battery remaining useful life prediction with multi-channel charging profiles. IEEE Access, 2020, 8: 20786-20798.
Crossref Google Scholar
[29]

J H Chou, F K Wang, S C Lo. Predicting future capacity of lithium-ion batteries using transfer learning method. Journal of Energy Storage, 2023, 71: 108120.
Crossref Google Scholar
[30]

M Wei, H Gu, M Ye, et al. Remaining useful life prediction of lithium-ion batteries based on Monte Carlo dropout and gated recurrent unit. Energy Reports, 2021, 7: 2862-2871.
Crossref Google Scholar
[31]

Y Liu, J Sun, Y Shang, et al. A novel remaining useful life prediction method for lithium-ion battery based on long short-term memory network optimized by improved sparrow search algorithm. Journal of Energy Storage, 2023, 61: 106645.
Crossref Google Scholar
[32]

M Catelani, L Ciani, R Fantacci, et al. Remaining useful life estimation for prognostics of lithium-ion batteries based on recurrent neural network. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-11.
Crossref Google Scholar
[33]

K Liu, Y Shang, Q Ouyang, et al. A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery. IEEE Transactions on Industrial Electronics, 2020, 68(4): 3170-3180.
Crossref Google Scholar
[34]

Y Ji, Z Chen, Y Shen, et al. An RUL prediction approach for lithium-ion battery based on SADE-MESN. Applied Soft Computing, 2021, 104: 107195.
Crossref Google Scholar
[35]

S Zhao, C Zhang, Y Wang. Lithium-ion battery capacity and remaining useful life prediction using board learning system and long short-term memory neural network. Journal of Energy Storage, 2022, 52: 104901.
Crossref Google Scholar
[36]

K A Severson, P M Attia, N Jin, et al. Data-driven prediction of battery cycle life before capacity degradation. Nature Energy, 2019, 4(5): 383-391.
Crossref Google Scholar
[37]
L Duong, T Cohn, S Bird, et al. Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (volume 2: short papers). 2015: 845-850.
Crossref
[38]
S Ruder. An overview of multi-task learning in deep neural networks. arXiv: 1706.05098, 2017. https://doi.org/10.48550/arXiv.1706.05098.
Chinese Journal of Electrical Engineering
Volume 10 Issue 3,
September 2024
Pages 1-11
DOI: 10.23919/CJEE.2024.000085
Cite this article:
Wang L, Zheng K, Li Y, et al. A Multitime-scale Deep Learning Model for Lithium-ion Battery Health Assessment Using Soft Parameter-sharing Mechanism. Chinese Journal of Electrical Engineering, 2024, 10(3): 1-11. https://doi.org/10.23919/CJEE.2024.000085

146

Views

8

Downloads

0

Crossref

0

Scopus

0

CSCD

Altmetrics
Received: 04 May 2024
Revised: 15 June 2024
Accepted: 25 June 2024
Published: 11 July 2024
© 2024 China Machinery Industry Information Institute
Return