A Dual-Head Mixer-BiLSTM Architecture for Battery State of Charge Prediction
Source abstract
Abstract
State of charge (SOC) estimation is a key research topic for electric vehicles, with accurate SOC estimation being important for both range and safety. In this study, we present the Dual-Head Depth Directional Mixer (DH-DW-M) model for SOC estimation. The model is tested using the BMW i3 dataset and its performance is evaluated using standard error measures from multiple perspectives. Furthermore, the results are compared with those of previous studies; specifically, DH-DW-M is compared with the Trend Flow-Mixer model, which has achieved the best results on this dataset in the literature to date. Notably, the proposed DH-DW-M model achieves the lowest overall estimation error value of 0.21%. Compared with the Trend Flow-Mixer model, DH-DW-M showed an 82% lower Root Mean Square Error (RMSE) when using the same input features. The model is also compared with well-known methods, with RMSE approximately 97%, 96%, and 95% lower when compared to those of Long Short-Term Memory (LSTM), Convolutional Neural Network–LSTM (CNN-LSTM), and Bidirectional LSTM with Attention (BiLSTM-AT) models, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Electric Vehicles and Infrastructure · Electric and Hybrid Vehicle Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Faculty of Engineering, Düzce University, 81620 Düzce, Türkiye
References (33)
Show source-provided references
1. (2025, December 10). Electric Vehicle Battery Market Size, Segments, Regional Outlook (NA, EU, APAC, LA, MEA) & Competitive Landscape, 2025–2034. Available online: https://www.towardsautomotive.com/insights/electric-vehicle-battery-market-sizing.
2. State-of-the-Art and Energy Management System of Lithium-Ion Batteries in Electric Vehicle Applications: Issues and Recommendations10.1109/ACCESS.2018.2817655 ↗
3. Critical Review on the Battery State of Charge Estimation Methods for Electric Vehicles10.1109/ACCESS.2017.2780258 ↗
4. Manthopoulos, A., and Wang, X. (2020, January 18–21). A Review and Comparison of Lithium-Ion Battery SOC Estimation Methods for Electric Vehicles. Proceedings of the IECON 2020 (Industrial Electronics Conference), Singapore.10.1109/IECON43393.2020.9254918 ↗
5. Movassagh, K., Raihan, A., Balasingam, B., and Pattipati, K. (2021). A Critical Look at Coulomb Counting Approach for State of Charge Estimation in Batteries. Energies, 14.10.3390/en14144074 ↗
6. Review on Technological Advancement of Lithium-Ion Battery States Estimation Methods for Electric Vehicle Applications10.1016/j.est.2023.107159 ↗
7. Correlation between the Model Accuracy and Mod-el-Based SOC Estimation10.1016/j.electacta.2017.01.057 ↗
8. A Review on Data-Driven SOC Estimation with Li-Ion Batteries: Implementation Methods & Future Aspirations10.1016/j.est.2023.108420 ↗
9. Data-Driven State of Charge Estimation of Lithium-Ion Batteries: Algorithms, Im-plementation Factors, Limitations and Future Trends10.1016/j.jclepro.2020.124110 ↗
10. A Survey on Long Short-Term Memory Networks for Time Series Prediction10.1016/j.procir.2021.03.088 ↗
11. Rahimi-Eichi, H., and Chow, M.Y. (November, January 29). Big-Data Framework for Electric Vehicle Range Estimation. Proceedings of the IECON 2014 (Industrial Electronics Conference), Dallas, TX, USA.10.1109/IECON.2014.7049362 ↗
12. A Novel Hybrid Deep Learning Model for Accurate State of Charge Estimation of Li-Ion Batteries for Electric Vehicles under High and Low Temperature10.1016/j.energy.2024.130584 ↗
13. Machine Learning-Based Lithium-Ion Battery Capacity Estimation Ex-ploiting Multi-Channel Charging Profiles10.1109/ACCESS.2019.2920932 ↗
14. Mohanty, P.K., Jena, P., and Padhy, N.P. (2022, January 14–17). Electric Vehicle State-of-Charge Prediction Using Deep LSTM Network Model. Proceedings of the 10th IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES 2022), Jaipur, India.10.1109/PEDES56012.2022.10080466 ↗
15. Improved Anti-Noise Adaptive Long Short-Term Memory Neural Network Modeling for the Robust Remaining Useful Life Prediction of Lithium-Ion Batteries10.1016/j.ress.2022.108920 ↗
16. Improved Singular Filtering–Gaussian Process Regression–Long Short-Term Memory Model for Whole-Life-Cycle Remaining Capacity Estimation of Lithium-Ion Batteries Adaptive to Fast Aging and Multi-Current Variations10.1016/j.energy.2023.128677 ↗
17. State of Charge Estimation of Lithium-Ion Batteries Based on PSO–TCN–Attention Neural Network10.1016/j.est.2024.110806 ↗
18. State-of-Charge Estimation of LiFePO4 Batteries in Electric Vehicles: A Deep-Learning Enabled Approach10.1016/j.apenergy.2021.116812 ↗
19. Hybrid Deep Learning Model for Efficient State of Charge Estimation of Li-Ion Batteries in Electric Vehicles10.1016/j.energy.2023.128317 ↗
20. Deep Learning-Based State of Charge Estimation for Electric Vehicle Batteries: Overcoming Tech-nological Bottlenecks10.1016/j.heliyon.2024.e35780 ↗
21. Chandran, V., Patil, C.K., Karthick, A., Ganeshaperumal, D., Rahim, R., and Ghosh, A. (2021). State of Charge Estimation of Lithium-Ion Battery for Electric Vehicles Using Machine Learning Algorithms. World Electr. Veh. J., 12.10.3390/wevj12010038 ↗
22. On Equivalent Circuit Model-Based State-of-Charge Estimation for Lithium-Ion Batteries in Electric Vehicles10.1109/ACCESS.2025.3560065 ↗
23. Multi-Model Deep Learning-Based State of Charge Estimation for Shipboard Lithium Batteries with Feature Extraction and Spatio-Temporal Dependency10.1016/j.jpowsour.2024.235983 ↗
24. Battery State of Health Estimation under Fast Charging via Deep Transfer Learning10.1016/j.isci.2025.112235 ↗
25. IEEE DataPort (2025, December 10). Battery and Heating Data in Real Driving Cycles. Available online: https://ieee-dataport.org/open-access/battery-and-heating-data-real-driving-cycles.
26. Long Short-Term Memory10.1162/neco.1997.9.8.1735 ↗
27. Long Short-Term Memory Recurrent Neural Network for Automatic Speech Recognition10.1109/ACCESS.2022.3159339 ↗
28. Bidirectional Recurrent Neural Networks10.1109/78.650093 ↗
29. Pau, D.P., and Aniballi, A. (2024). Tiny Machine Learning Battery State-of-Charge Estimation Hardware Accelerated. Appl. Sci., 14.10.3390/app14146240 ↗
30. A Real-World Battery State of Charge Prediction Method Based on a Lightweight Mixer Architecture10.1016/j.energy.2024.133434 ↗
31. Real Driving Cycle Based SoC and Battery Temperature Prediction for Electric Vehicle Using AI Models10.22201/icat.24486736e.2024.22.3.2453 ↗
32. State of Charge Estimation of Lithium-Ion Batteries in an Electric Vehicle Using Hybrid Metaheuristic–Deep Neural Networks Models10.1016/j.enss.2025.01.002 ↗
33. Ariche, S., Boulghasoul, Z., El Ouardi, A., Elbacha, A., Tajer, A., and Espié, S. (2024). A Comparative Study of Electric Vehicles Battery State of Charge Estimation Based on Machine Learning and Real Driving Data. J. Low Power Electron. Appl., 14.10.3390/jlpea14040059 ↗