Hybrid Machine Learning-Based Prediction of RUL & Capacity Fade in EV Lithium-Ion Batteries
Keywords:
(EV) Electric vehicle, Hybrid machine learning, Lithium-ion battery, (LSTM) Long short-term memory, (MAE) Mean absolute error, (MSE) Mean squared error, Random forest, (RMSE) Root mean squared error, (RUL) Remaining use life, (SOH) State of healthAbstract
Lithium-ion batteries power electric vehicles (EVs), but it remains a mystery how to accurately estimate the remaining useful life (RUL) and state of health (SOH) of these batteries due to the complex degradation mechanisms involved. This work presented with hybrid LSTM, a simple neural network, as well as a random forest to predict SOH and RUL accurately. The data were obtained from Kaggle, and then its exploratory data analysis, standard scaling, and 80-20 train-test splitting were done. Some performance assessment indicators such as mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and R² score were used to build and test the individual models. This work showed that the hybrids of the two model systems produced better accuracy and stability than single-mode schemes. SOH (%) and RUL predictions were done using Streamlit to facilitate developed web applications. Through this framework, battery life cycle strategies are improved as well as strategic choices of electric vehicle producers and of consumers interested in safety, cost effectiveness, and sustainability.
References
G. R. Sylvestrin et al., “State of the art in electric batteries’ state-of-health (SoH) estimation with machine learning: A review,” Energies, vol. 18, no. 3, p. 746, Feb. 2025, doi: https://doi.org/10.3390/en18030746
J. Ranninger, S. J. Wachs, J. Möller, K. J. J. Mayrhofer, and B. B. Berkes, “On-line monitoring of dissolution processes in nonaqueous electrolytes – A case study with platinum,” Electrochemistry Communications, vol. 114, pp. 106702–106702, Mar. 2020, doi: https://doi.org/10.1016/j.elecom.2020.106702
X.-Q. Zhang et al., “Crosstalk shielding of transition metal ions for long cycling lithium–metal batteries,” Journal of Materials Chemistry A, vol. 8, no. 8, pp. 4283–4289, Dec. 2019, doi: https://doi.org/10.1039/c9ta12269a
D. Roman, S. Saxena, V. Robu, M. Pecht, and D. Flynn, “Machine learning pipeline for battery state-of-health estimation,” Nature Machine Intelligence, vol. 3, no. 5, pp. 447–456, Apr. 2021, doi: https://doi.org/10.1038/s42256-021-00312-3
W. Song, D. Wu, W. Shen, and B. Boulet, “A remaining useful life prediction method for lithium-ion battery based on temporal transformer network,” Procedia Computer Science, vol. 217, pp. 1830–1838, Jan. 2023, doi: https://doi.org/10.1016/j.procs.2022.12.383
D. Yuanchang, P. Xiaoqiong, J. Jianfang, S. Yuanhao, W. Jie, and L. Xiao, “Remaining useful life prediction of lithium-ion batteries based on SVD-SAE-GPR,” Energy Storage Science and Technology, vol. 12, no. 4, pp. 1257-1267, 2023. Available: https://doi.org/10.19799/j.cnki.2095-4239.2022.0767
S. Zhao, C. Zhang, and Y. Wang, “Lithium-ion battery capacity and remaining useful life prediction using board learning system and long short-term memory neural network,” Journal of Energy Storage, vol. 52, no. B, p. 104901, Aug. 2022, doi: https://doi.org/10.1016/j.est.2022.104901
W. Hu, C. Zhang, L. Luo, and S. Jiang, “Integrated method of future capacity and RUL prediction for lithium‐ion batteries based on CEEMD‐transformer‐LSTM model,” Energy Science & Engineering, vol. 12, no. 11, pp. 5272–5286, Nov. 2024, doi: https://doi.org/10.1002/ese3.1952
C. Zhang, S. Zhao, Zhong, and Y. Chen, “A reliable data-driven state-of-health estimation model for lithium-ion batteries in electric vehicles,” Frontiers in Energy Research, vol. 10, Sep. 2022, doi: https://doi.org/10.3389/fenrg.2022.1013800
Shehzar Shahzad Sheikh, Fawad Ali Shah, Syed Owais Athar, and Hassan Abdullah Khalid, “A data-driven comparative analysis of lithium-ion battery state of health and capacity estimation,” Electric Power Components and Systems, vol. 51, no. 1, pp. 1–11, Jan. 2023, doi: https://doi.org/10.1080/15325008.2022.2145389
M. Khalid, S. S. Sheikh, A. K. Janjua and H. A. Khalid, “Performance validation of electric vehicle’s battery management system under state of charge estimation for lithium-ion Battery,” 2018 International Conference on Computing, Electronic and Electrical Engineering (ICE Cube), Quetta, Pakistan, 2018, pp. 1-5, doi: https://doi.org/10.1109/ICECUBE.2018.8610969
S. S. Sheikh et al., “A battery health monitoring method using machine learning: A data-driven approach,” Energies, vol. 13, no. 14, p. 3658, Jul. 2020, doi: https://doi.org/10.3390/en13143658
G. dos Reis, C. Strange, M. Yadav, and S. Li, “Lithium-ion battery data and where to find it,” Energy and AI, vol. 5, p. 100081, Sep. 2021, doi: https://doi.org/10.1016/j.egyai.2021.100081
S. Wang, S. Jin, D. Deng, and C. Fernandez, “A critical review of online battery remaining useful lifetime prediction methods,” Frontiers in Mechanical Engineering, vol. 7, Aug. 2021, doi: https://doi.org/10.3389/fmech.2021.719718
Y. Li, H. Sheng, Y. Cheng, Daniel-Ioan Stroe, and R. Teodorescu, “State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis,” Applied Energy, vol. 277, pp. 115504–115504, Nov. 2020, doi: https://doi.org/10.1016/j.apenergy.2020.115504
Y. Che, X. Hu, X. Lin, J. Guo, and R. Teodorescu, “Health prognostics for lithium-ion batteries: mechanisms, methods, and prospects,” Energy & Environmental Science, vol. 16, no. 2, pp. 338–371, 2023, doi: https://doi.org/10.1039/D2EE03019E
S. Mishra, A. Choubey, B. A. Reddy, and R. Misra, “Enhancing EV lithium-ion battery management: automated machine learning for early remaining useful life prediction with innovative multi-health indicators,” The Journal of Supercomputing, vol. 80, no. 14, pp. 20813–20860, Jun. 2024, doi: https://doi.org/10.1007/s11227-024-06264-w
R. Zhong et al., “Lithium-ion battery remaining useful life prediction: A federated learning-based approach,” Energy Ecology and Environment, vol. 9, no. 5, pp. 549–562, Apr. 2024, doi: https://doi.org/10.1007/s40974-024-00323-x
