A deep learning-based method for estimating the state of charge and predicting the remaining life of energy storage batteries

Authors

  • Yuanjing Qian Southeast University image/svg+xml
  • Ning Zhao Shaanxi Water Development Huaze Zhihui Equipment Group Co., Ltd.
  • Zhenrong Yang North China Municipal Engineering Design & Research Institute image/svg+xml
  • Chang Liu Shaanxi Provincial Hospital of Traditional Chinese Medicine image/svg+xml

DOI:

https://doi.org/10.4108/ew.14866

Keywords:

Energy storage batteries, deep learning, state of charge, state of health, remaining useful life

Abstract

INTRODUCTION: In order to improve the precision of state estimation and forecast of long term deterioration tendency in complicated charging and discharging conditions.

OBJECTIVES: This paper adopted a collaborative modeling approach for state of charge (SOC), state of health (SOH), and Remaining Useful Life (RUL) for SOC estimation.

METHODS: By integrating the Huber loss and state continuity constraints, this method can capture both the local and long-term temporal dependencies; The SOH estimation uses multiscale convolutions, gated temporal coding, and residual regression to represent cross-cycle degradation characteristics, and generates future health trajectories using an encoder-decoder architecture, which enables RUL threshold search prediction.

RESULTS: The results show that the average absolute error of SOC is 0.63%, and the root mean square error is 0.86%, and the SOH estimate reaches a mean absolute error of 0.58%, and the RUL estimate reaches 13.8 cycles.

CONCLUSION: Under joint learning, the SOC root mean square error, SOH mean absolute error, and RUL mean absolute error are further reduced to 0.79%, 0.55%, and 12.9 cycles, respectively, confirming that shared degradation representation and task-coordinated optimization improve state estimation and lifetime prediction.

Downloads

Download data is not yet available.

References

[1] Kim S B, Lee S H. Application of deep learning techniques for the state of charge prediction of lithium-ion batteries[J]. Applied Sciences, 2024, 14(17): 8077.

[2] Schmitz M, Kowal J. A deep learning approach for online state of health estimation of lithium-ion batteries using partial constant current charging curves[J]. Batteries, 2024, 10(6): 206.

[3] Ezugwu E O, Bhattacharya I, Ayomide A I, et al. State of charge (soc) estimation with electrochemical impedance spectroscopy (eis) data using different ensemble machine learning algorithms[J]. Electronics, 2025, 14(22): 4423.

[4] Lanubile A, Bosoni P, Pozzato G, et al. Domain knowledge-guided machine learning framework for state of health estimation in Lithium-ion batteries[J]. Communications engineering, 2024, 3(1): 168.

[5] Sonthalia A, Josephin J S F, Varuvel E G, et al. A deep learning multi-feature based fusion model for predicting the state of health of lithium-ion batteries[J]. Energy, 2025, 317: 134569.

[6] Suh S, Mittal D A, Bello H, et al. Remaining useful life prediction of lithium-ion batteries using spatio-temporal multimodal attention networks[J]. Heliyon, 2024, 10(16): e36236.

[7] Reza M S, Hannan M A, Mansor M, et al. Towards enhanced remaining useful life prediction of lithium-ion batteries with uncertainty using optimized deep learning algorithm[J]. Journal of Energy Storage, 2024, 98: 113056.

[8] Onyenagubo C, Ismail Y, Belu R, et al. Forecasting the Remaining Useful Life of Lithium-Ion Batteries Using Machine Learning Models—A Web-Based Application[J]. Algorithms, 2025, 18(6): 303.

[9] Feng W, Sun Z, Han Y, et al. A multi-strategy attention regression network for joint prediction of state of health and remaining useful life of lithium-ion batteries using only charging data[J]. Journal of Power Sources, 2025, 636: 236507.

[10] Rastegarpanah A, Asif M E, Stolkin R. Hybrid neural networks for enhanced predictions of remaining useful life in lithium-ion batteries[J]. Batteries, 2024, 10(3): 106.

[11] Guirguis J, Ahmed R. Transformer-based deep learning models for state of charge and state of health estimation of li-ion batteries: A survey study[J]. Energies, 2024, 17(14): 3502.

[12] Babu P S, V I, B A, et al. Enhanced SOC estimation of lithium ion batteries with RealTime data using machine learning algorithms[J]. Scientific Reports, 2024, 14(1): 16036.

[13] Iftikhar M, Shoaib M, Altaf A, et al. A deep learning approach to optimize remaining useful life prediction for Li-ion batteries[J]. Scientific Reports, 2024, 14(1): 25838.

[14] Hasib S A, Islam S, Ali M F, et al. Enhancing prediction accuracy of Remaining Useful Life in lithium-ion batteries: A deep learning approach with Bat optimizer[J]. Future Batteries, 2024, 2: 100003.

[15] Oka K, Tanibata N, Takeda H, et al. Deep learning based emulator for predicting voltage behaviour in lithium ion batteries[J]. Scientific Reports, 2024, 14(1): 28905.

[16] Jang J, Jo J, Kim J, et al. State of health estimation of lithium-ion battery cell based on optical thermometry with physics-informed machine learning[J]. Engineering Applications of Artificial Intelligence, 2025, 140: 109704.

[17] Mu B Q, Doukhi O, Wang L, et al. State-of-charge estimation of commercial electric vehicles by using battery-aware transformer network algorithms[J]. Journal of Computational Design and Engineering, 2025, 12(6): 73-95.

[18] Bairwa B, Pareek K, Jadoun V K. Cycle based state of health estimation of lithium ion cells using deep learning architectures[J]. Scientific Reports, 2025, 15(1): 37078.

[19] Rout S, Samal S K, Gelmecha D J, et al. Estimation of state of health for lithium-ion batteries using advanced data-driven techniques[J]. Scientific Reports, 2025, 15(1): 30438.

[20] Ibrahim M, Ansari S, Ayob A, et al. Hybrid optimized remaining useful life prediction framework for lithium-ion batteries with limited data samples[J]. Scientific Reports, 2025, 15(1): 39126.

[21] Singh A, Singh S, Kamboj R K, et al. Explainable OptiCNN-SLSTM hybrid model for enhanced lithium-ion battery state of health prediction[J]. Scientific Reports, 2025, 15(1): 44364.

[22] Carrera R, Quiroz L, Guevara C, et al. State-of-charge estimation of medium-and high-voltage batteries using LSTM neural networks optimized with genetic algorithms[J]. Sensors, 2025, 25(15): 4632.

[23] Saneep K, Sundareswaran K, Nayak P S R, et al. State of charge estimation of lithium-ion batteries using PSO optimized random forest algorithm and performance analysis[J]. Journal of Energy Storage, 2025, 114: 115879.

[24] Yu T, Kumar S, Gupta A, et al. Gradient surgery for multi-task learning[J]. Advances in neural information processing systems, 2020, 33: 5824-5836.

[25] Al-Dulaimi A A, Guneser M T, Al-Shabandar R, et al. AE-BPNN: autoencoder and backpropagation neural network-based model for lithium-ion battery state of health estimation[J]. Scientific Reports, 2025, 15(1): 29193.

Downloads

Published

19-11-2026

Issue

Section

Digital Twin Technologies for Smart Energy Systems

How to Cite

1.
Qian Y, Zhao N, Yang Z, Liu C. A deep learning-based method for estimating the state of charge and predicting the remaining life of energy storage batteries. EAI Endorsed Trans Energy Web [Internet]. 2026 Nov. 19 [cited 2026 Nov. 19];13. Available from: https://publications.eai.eu/index.php/ew/article/view/14866

Most read articles by the same author(s)