Deep Hybrid Temporal Modeling with TCN-GRU-Transformer for Lithium-Polymer Battery State-of-Charge Estimation
Omar LAMMAMRI, Brahim ZRAIBI, Mohamed MANSOURI, Abdelghani EZZAHI, Adam AFADISS
Abstract. Accurate state-of-charge (SOC) estimation is critical for safe and efficient battery operation in electric vehicles and stationary energy storage systems. This study proposes a hybrid deep learning model that combines a Temporal Convolutional Network (TCN) for local temporal feature extraction, a Gated Recurrent Unit (GRU) for sequential dynamics, and a Transformer block to capture longer-range dependencies in battery signals. The model is trained and validated using experimentally measured lithium-Polymer battery data and is benchmarked against standalone TCN, GRU, and Transformer baselines under the same data splits and evaluation protocol. On the test set, the proposed hybrid architecture achieves a mean absolute error (MAE) of 0.66%, a root mean square error (RMSE) of 0.88%, and a coefficient of determination (R²) of 0.9992, consistently outperforming the individual models. The results indicate that integrating complementary temporal modeling mechanisms improves estimation accuracy and robustness, supporting real-time SOC prediction in practical battery management systems.
Keywords
State of Charge, Lithium Polymer Battery, Deep Learning, TCN, GRU, Hybrid Model
Published online 4/25/2026, 7 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Omar LAMMAMRI, Brahim ZRAIBI, Mohamed MANSOURI, Abdelghani EZZAHI, Adam AFADISS, Deep Hybrid Temporal Modeling with TCN-GRU-Transformer for Lithium-Polymer Battery State-of-Charge Estimation, Materials Research Proceedings, Vol. 64, pp 164-170, 2026
DOI: https://doi.org/10.21741/9781644904091-20
The article was published as article 20 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] G. Kostenko, A. Zaporozhets, Transition from Electric Vehicles to Energy Storage: Review on Targeted Lithium-Ion Battery Diagnostics, Energies 17 (2024) 5132. https://doi.org/10.3390/en17205132
[2] G.G. Njema, R.B.O. Ouma, J.K. Kibet, A Review on the Recent Advances in Battery Development and Energy Storage Technologies, J. Renew. Energy 2024 (2024) 2329261. https://doi.org/10.1155/2024/2329261
[3] M.A. Pisani Orta, D. García Elvira, H. Valderrama Blaví, Review of State-of-Charge Estimation Methods for Electric Vehicle Batteries, World Electr. Veh. J. 16 (2025) 87. https://doi.org/10.3390/wevj16020087
[4] K. Yang, Y. Tang, S. Zhang, Z. Zhang, A Deep Learning Approach to State of Charge Estimation of Lithium-Ion Batteries Based on Dual-Stage Attention Mechanism, Energy 244 (2022) 123233. https://doi.org/10.1016/j.energy.2022.123233
[5] J.-H. Lee, I.-S. Lee, Hybrid Estimation Method for the State of Charge of Lithium Batteries Using a Temporal Convolutional Network and XGBoost, Batteries 9 (2023) 544. https://doi.org/10.3390/batteries9110544
[6] M.S. Nazim, M.M. Rahman, R.B. Mofidul, M.M.B. Rimu, Y.M. Jang, Robust State of Charge Estimation for Lithium-Ion Batteries Using a Fully Entangled Temporal Convolutional Network with Particle Swarm Optimization, J. Power Sources (2025) 237020. https://doi.org/10.1016/j.jpowsour.2025.237020
[7] S. Guo, L. Ma, A Comparative Study of Different Deep Learning Algorithms for Lithium-Ion Batteries on State-of-Charge Estimation, Energy 263 (2023) 125872. https://doi.org/10.1016/j.energy.2022.125872
[8] G. Taş, A. Uysal, C. Bal, A New Lithium Polymer Battery Dataset with Different Discharge Levels: SOC Estimation of Lithium Polymer Batteries with Different Convolutional Neural Network Models, Arab. J. Sci. Eng. 48 (2023) 6873–6888. https://doi.org/10.1007/s13369-022-07586-8
[9] B. Zraibi, M. Mansouri, C. Okar, Comparing Single and Hybrid Methods of Deep Learning for Remaining Useful Life Prediction of Lithium-Ion Batteries, E3S Web Conf. 297 (2021) 01043. https://doi.org/10.1051/e3sconf/202129701043
[10] Y. Liu, J. Li, G. Zhang, B. Hua, N. Xiong, State of Charge Estimation of Lithium-Ion Batteries Based on Temporal Convolutional Network and Transfer Learning, IEEE Access 9 (2021) 34177–34187. https://doi.org/10.1109/ACCESS.2021.3057371
[11] J. Chen, X. Feng, L. Jiang, Q. Zhu, State of Charge Estimation of Lithium-Ion Battery Using Denoising Autoencoder and Gated Recurrent Unit Recurrent Neural Network, Energy 227 (2021) 120451. https://doi.org/10.1016/j.energy.2021.120451
[12] M.A. Hannan, D.N.T. How, M.S.H. Lipu, M. Mansor, P.J. Ker, Z.Y. Dong, K.S.M. Sahari, S.K. Tiong, K.M. Muttaqi, T.M.I. Mahlia, F. Blaabjerg, Deep Learning Approach Towards Accurate State of Charge Estimation for Lithium-Ion Batteries Using Self-Supervised Transformer Model, Sci. Rep. 11 (2021) 19541. https://doi.org/10.1038/s41598-021-98915-8
