Proceedings of TUSUR University / Archive / Issue of Journal № 4, t. 28, 2025 / Neural network-based prediction of the state of charge of Lithium-ion battery

Neural network-based prediction of the state of charge of Lithium-ion battery

DOI: 10.21293/1818-0442-2025-28-4-155-161

Download article in PDF format

JATS xml

Abstract: The problem of predicting the state of charge (SOC) of lithium-ion batteries (LIB) for energy storage systems of technological equipment and mobile objects is considered. A neural network-based approach is proposed to overcome the limitations of tra-ditional mathematical models that require prior knowledge of battery parameters. Three types of architectures are examined-multilayer perceptrons (MLP), recurrent neural networks (RNN), and gated recurrent units (GRU) – to analyze their ef-fectiveness in SOC prediction. A methodology is developed for training these neural network models on experimental data, in-cluding time series of voltage, current and temperature under dynamic discharge conditions. Differences in accuracy and computational costs are confirmed: MLP networks train faster but fail to capture temporal dependencies, while RNN and GRU networks demonstrate lower test errors but demand higher com-putational resources. The practical applicability of the results is validated through the optimization of SOC estimation algo-rithms under real-world conditions.

Keywords: Lithium-ion battery, state of charge, neural networks, neural network architectures: MLP, RNN, GRU

For citation:
Bukreev V. G., Hoang F. N. Neural network-based prediction of the state of charge of Lithium-ion battery. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2025, vol. 28, no. 4, pp. 155–161. DOI: 10.21293/1818-0442-2025-28-4-155-161

Authors and copyright holders:

Bukreev V. G. , National Research Tomsk Polytechnic University (Tomsk, Russia)
Hoang F. N. , National Research Tomsk Polytechnic University (Tomsk, Russia)

1. Tian N., Wang Y., Chen J., Fang H. On Parameter Identification of an Equivalent Circuit Model for Lithium-Ion Batteries. 2017 Conference on Control Technology and Applications (CCTA), Hawai'i, USA, 2017, pp. 187–192.
2. Ng K.S., Moo C.-S., Chen Y.-P., Hsieh Y.-C. Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries. Appl Energy, 2009, vol. 86, pp. 1506–1511.
3. You H.W., Bae J.I., Cho S.J., Lee J.M., Kim S.-H. Analysis of equivalent circuit models in lithium-ion batteries. AIP Advances, 2018, vol. 8, no. 12, pp. 125101.
4. Plett G.L. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs Part 1: Background. Journal of Power Sources, 2004, vol. 134, pp. 252–261.
5. Lee J., Nam O., Cho B.H. Li-ion battery SOC estimation method based on the reduced order extended Kalman filtering. Journal of Power Sources, 2007, vol. 174, pp. 9–15.
6. Plett G.L. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs Part 2: Modeling and identification. Journal of Power Sources, 2004, vol. 134, pp. 262–276.
7. He W., Williard N., Chen C., Pecht M. State of charge estimation for Li-ion batteries using neural network modeling and unscented Kalman filter-based error cancellation. Electrical Power and Energy Systems, 2014, vol. 62, pp. 783–791.
8. Kazakov F.A., Shnaider A.V. [Using neural networks with time series of data to analyze data flows]. Modern High Technologies, 2021, no. 6, pp. 260–264 (in Russ.).
9. Feofilov S.V., Khapkin D.L. [Application of recurrent neural networks in closed tracking systems with nonlinear objects]. Izvestiya Tula State University, 2021, vol. 11, pp. 72–80 (in Russ.).
10. Haykin S. *Neironnye seti: polnyi kurs, 2-e izdanie* [Neural Networks: A Comprehensive Foundation, 2nd ed], translated from English. Moscow: Williams Publishing House, 2006, 1104 p. (in Russ.).
11. Garbin C., X. Zhu, O. Marques. Dropout vs. Batch Normalization: An Empirical Study of Their Impact to Deep Learning. Multimedia Tools and Applications, 2020, vol. 79, pp. 12777–12815.
12. Jagtap A.D., Karniadakis G.E. How important are activation functions in regression and classification? A survey, performance comparison, and future directions. Journal of Machine Learning for Modeling and Computing, 2023, vol. 4, no. 1, pp. 21–75.
13. Chaoui H., Ibe-Ekeocha C.C. State of Charge and State of Health Estimation for Lithium Batteries Using Recurrent Neural Networks. IEEE Trans. Veh. Technol, 2017, vol. 66, pp. 8773–8783.
14. Novikov A.A., Budzinskaya E.O., Kaneva O.N. Analiz metodov prognozirovaniya vremennykh ryadov [Analysis of Time Series Forecasting Methods]. International Youth Scientific and Practical Conference with Elements of Scientific School, Omsk, OmSTU, 2020, vol. 4, no. 1, pp. 37–43 (in Russ.).
15. Perepelkin V. [Using recurrent neural networks for time series forecasting]. Modern Science: actual problems of theory and practice. Series: Natural and Technical Sciences, 2023, no. 7, pp. 80–82 (in Russ.).
16. Yang F. State-of-charge estimation of lithium-ion batteries based on gated recurrent neural network. Energy, 2019, vol. 175, pp. 66–75.
17. Pashshoev B., Petrusevich D.A. Neural network analysis in time series forecasting. Russ. Technol. J, 2024, vol 12, no. 4, pp. 106−116.
18. Pecht M. Battery Data Set. CALCE, CALCE Battery Research Group, Maryland, MD; 2017. Available at: https://web.calce.umd.edu/batteries/data.htm.
19. Starovoitov V.V., Golub Y.I. [Data normalization in machine learning]. Informatics, 2021, vol. 18, no. 3, pp. 83−96 (in Russ.).