TCN method development for SOC prediction of Li-ion batteries
DOI:
https://doi.org/10.61173/r7mzap95Keywords:
component, lithium battery, state of charge estimation, temporal convolutional network, attention mechanism, transfer learning, battery management sys-tem, optimization algorithmAbstract
Lithium battery state-of-charge (SOC) estimation is a core function of battery management system, which directly affects the safety and range performance of electric vehicles. Aiming at the nonlinear modelling limitations of traditional methods under dynamic operating conditions and battery aging scenarios, temporal convolutional networks (TCNs) have become a research hotspot in the field of SOC estimation. This paper reviews the recent progress of TCN methods: through the introduction of attention mechanism, migration learning and hybrid architecture, it effectively solves the challenges of data missing sensitivity and poor cross-cell generalisation; combined with genetic algorithm, grey wolf optimisation and other strategies, it further optimises the network structure and hyperparameters.
References
[1] X. Song, F. Yang, D. Wang and K. -L. Tsui, “Combined CNN-LSTM Network for State-of-Charge Estimation of Lithium-Ion Batteries,” in IEEE Access, vol. 7, pp. 88894- 88902, 2019, doi: 10.1109/ACCESS.2019.2926517.
[2] Duan, W.; Song, C.; Peng, S.; Xiao, F.; Shao, Y.; Song, S. An Improved Gated Recurrent Unit Network Model for State-of- Charge Estimation of Lithium-Ion Battery. Energies 2020, 13, 6366.
[3] Chung, DW., Ko, JH. & Yoon, KY. State-of-Charge Estimation of Lithium-ion Batteries Using LSTM Deep Learning Method. J. Electr. Eng. Technol. 17, 1931–1945 (2022).
[4] Gao Zhennan, Zhai Ronggang, Yang Wei, et al. Research on improved battery SOC algorithm based on ampere-time integration method[J]. Journal of Heze College,2021,43(05):39-44.DOI:10.16393/j.cnki.37-1436/ z.2021.05.009.
[5] XU Liyou, MA Ke, YANG Qingxia, et al. SOC estimation of power battery based on Kalman filter[J]. Journal of Jiangsu University (Natural Science Edition),2024,45(01):24-29.
[6] WANG Hengde, XU Yonghong, ZHANG Hongguang, et al. A review on the progress of SOC estimation technology for lithium-ion power batteries[J]. Times Automotive,2023,(22):120-122.
[7] Ma Chenbin,Wang Yi. Current status and outlook of new energy vehicle battery SOC development[J]. Auto Electric,2024,(03):8-11.DOI:10.13273/j.cnki.qcdq.2024.03.001.
[8] D. Yahia, L. Degaa, D. Sara, N. S. Allah, L. M. Mourad and N. Rizoug, “A Temporal Convolution Network to Electric vehicle Battery State-of-Charge Estimation,” 2023 9th International Conference on Control, Decision and Information Technologies (CoDIT), Rome, Italy, 2023, pp. 2740-2744, doi: 10.1109/ CoDIT58514.2023.10284143.
[9] Y. Hu, X. Hu and Y. Yao, “Research on State of Charge Estimation of Power Battery Based on Neural Network under the Background of New Energy Electric Vehicle,” 2023 4th International Conference on Advanced Electrical and Energy Systems (AEES), Shanghai, China, 2023, pp. 628-633, doi: 10.1109/AEES59800.2023.10468713.
[10] K. Zhao, Y. Liu, Y. Zhou, W. Ming and J. Wu, “Digital Twin-Supported Battery State Estimation Based on TCN-LSTM Neural Networks and Transfer Learning,” in CSEE Journal of Power and Energy Systems, vol. 11, no. 2, pp. 567-579, March 2025, doi: 10.17775/CSEEJPES.2024.00900.
[11] Y. Liu, J. Li, G. Zhang, B. Hua and N. Xiong, “State of Charge Estimation of Lithium-Ion Batteries Based on Temporal Convolutional Network and Transfer Learning,” in IEEE Access, vol. 9, pp. 34177-34187, 2021, doi: 10.1109/ ACCESS.2021.3057371.
[12] J. Wang, Y. Ye, M. Wu, F. Zhang, Y. Cao and Z. Zhang, “Temporal Convolutional Recombinant Network: A Novel Method for SOC Estimation and Prediction in Electric Vehicles,” in IEEE Access, vol. 12, pp. 128326-128337, 2024, doi: 10.1109/ ACCESS.2024.3434557.
[13] R. Zhou, X. Dai, F. Lin, J. Zhang and H. Ma, “TGT: Battery State of Charge Estimation with Robustness to Missing Data,” 2024 CPSS & IEEE International Symposium on Energy Storage and Conversion (ISESC), Xi’an, China, 2024, pp. 431-436, doi: 10.1109/ISESC63657.2024.10785457.
[14] H.B. Wang. Estimation of charge state of automotive lithium battery based on CGOA-MAM-TCN algorithm[J]. Automotive Engine,2024,(05):78-85.
[15] C. Huang, Y. Wei and C. Zhou, “State of Charge Estimation of Lithium-Ion Batteries Based on Temporal Convolution Network and Unscented Kalman Filter,” 2024 7th International Conference on Advanced Algorithms and Control Engineering (ICAACE), Shanghai, China, 2024, pp. 1113-1119, doi: 10.1109/ ICAACE61206.2024.10549416.
[16] LI Haolei, ZHAO Sheng, XIE Xilong, et al. Research on lithium battery charge state estimation based on GWO- LSTM-TCN hybrid model[J]. Power Supply Technolo gy,2024,48(11):2195-2200.
[17] Feng Li, Wei Zuo, Kun Zhou, Qingqing Li, Yuhan Huang,State of charge estimation of lithium-ion batteries based on PSO-TCN-Attention neural network,Journal of Energy Storage,Volume 84, Part A,2024,110806,ISSN 2352-152X,
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
