Predicting Battery Health for Electric Vehicles using Machine Learning Approach


Abstract views: 24 / PDF downloads: 7

Authors

  • Abdelmounaim Bensabeur İstanbul Okan Üniversitesi
  • Belfun Arslan Mutlu Battery
  • Cem Hakan Yılmaz Mutlu Battery
  • Doç. Dr. Ömer Cihan Kıvanç İstanbul Okan Üniversitesi
  • Prof. Dr. Ramazan Nejat Tuncay İstanbul Okan Üniversitesi

Keywords:

Lithium Li-Ion Batteries, State Of Health, State Of Charge, Battery Management System

Abstract

Research utilized data-driven models to investigate SoH estimation methodologies for lithium
ion batteries, particularly focusing on their effectiveness in capturing degradation trends. The study
evaluated four different deep learning approaches-DNN, CNN, RNN, and LSTM-using various metrics,
including MAE, RMSE, R², and validation loss. Results reveal that the LSTM model outperforms the
others, achieving the lowest MAE (0.1293), RMSE (0.1680), and validation loss (0.0282), with an R² of
0.9790, making it the most reliable predictor of battery SoH. The study highlights a strong linear
correlation between SoH and parameters such as capacity and charge voltage, affirming their role as
critical indicators of battery health. Conversely, temperature exhibited negligible impact on SoH within
the narrow range studied, necessitating further research under diverse environmental conditions.
Anomalies in terminal current during charge-discharge cycles suggest potential operational irregularities
requiring deeper analysis. The study underscores the limitations of CNN in modeling temporal
dependencies, advocating for hybrid architectures like CNN-LSTM for enhanced predictive accuracy as
well as narrow temperature range of 25oc. Findings also demonstrate consistent SoC transitions across
cycles, emphasizing the stability of the battery's charge-discharge behavior and its implications for long
term durability.

Downloads

Download data is not yet available.

Author Biographies

Abdelmounaim Bensabeur , İstanbul Okan Üniversitesi

Department of Mechatronics Engineering, Turkey

Belfun Arslan, Mutlu Battery

Department of Research and Development, Turkey

Cem Hakan Yılmaz, Mutlu Battery

Department of Research and Development, Turkey

Doç. Dr. Ömer Cihan Kıvanç, İstanbul Okan Üniversitesi

Department of Electrical and Electronics Engineering, Turkey

Prof. Dr. Ramazan Nejat Tuncay, İstanbul Okan Üniversitesi

Department of Electrical and Electronics Engineering,Turkey

References

Marinaro, M., Bresser, D., Beyer, E., Faguy, P., Hosoi, K., Li, H., ... & Passerini, S. (2020). Bringing forward the development of battery cells for automotive applications: Perspective of R&D activities in China, Japan, the EU and the USA. Journal of Power Sources, 459, 228073.

Howey, D. A., Roberts, S. A., Viswanathan, V., Mistry, A., Beuse, M., Khoo, E., ... & Sulzer, V. (2020). Free radicals: making a case for battery modeling. The Electrochemical Society Interface, 29(4), 30.

Liu, K., Hu, X., Zhou, H., Tong, L., Widanage, W. D., & Marco, J. (2021). Feature analyses and modeling of lithium-ion battery manufacturing based on random forest classification. IEEE/ASME Transactions on Mechatronics, 26(6), 2944-2955.

Burzyński, D., & Kasprzyk, L. (2021). A novel method for the modeling of the state of health of lithium-ion cells using machine learning for practical applications. Knowledge-Based Systems, 219, 106900.

Liu, P., Wu, Y., She, C., Wang, Z., & Zhang, Z. (2022). Comparative study of incremental capacity curve determination methods for lithium-ion batteries considering the real-world situation. IEEE Transactions on Power Electronics, 37(10), 12563-12576.

Cahyani, D. E., Setyawan, F. F., Hariadi, A. D., Gumilar, L., & Junoh, A. K. (2023, September). Comparison of Regression Methods for Estimation of State-of-Health in Lithium-Ion Batteries. In 2023 International Conference on Electrical and Information Technology (IEIT) (pp. 202-206). IEEE.

Poh, W. Q. T., Xu, Y., & Tan, R. T. P. (2023, July). Data-Driven Estimation of Li-Ion Battery Health using a Truncated Time-based Indicator and LSTM. In 2023 IEEE Power & Energy Society General Meeting (PESGM) (pp. 1-5). IEEE.

Dos Reis, G., Strange, C., Yadav, M., & Li, S. (2021). Lithium-ion battery data and where to find it. Energy and AI, 5, 100081.

Gur TJIEA, France. Global EV outlook 2020 entering the decade of electric drive. 2020.

Meshram P, Mishra A, Abhilash Sahu R. Environmental impact of spent lithium ion batteries and green recycling perspectives by organic acids - a review. Chemosphere 2020;242:125291.

Xiao J, Li J, Xu Z. Challenges to future development of spent lithium ion batteries recovery from environmental and techno-logical perspectives. Environ Sci Technol 2020;54:9–25.

Fujita T, Chen H, Wang K-t, He C-l, Wang Y-b, Dodbiba G, et al. Reduction, reuse and recycle of spent Li-ion batteries for automobiles: a review. Int J Miner Metall Mater 2021;28:179–92.

Pradhan S, Nayak R, Mishra S. A review on the recovery of metal values from spent nickel metal hydride and lithium-ion batteries. Int J Environ Sci Technol 2022;19:4537–54.

Tran, M. K., DaCosta, A., Mevawalla, A., Panchal, S., & Fowler, M. (2021). Comparative study of equivalent circuit models performance in four common lithium-ion batteries: LFP, NMC, LMO, NCA. Batteries, 7(3), 51.

China Industrial Association of Power (CIAP) Sources: China’s top 20 power lithium-ion battery companies in terms of in-stalled capacity in 2020: http://www.ciaps.org. cn/news/show-htm-itemid-37907.html.

Baum ZJ, Bird RE, Yu X, Ma J. Lithium-ion battery Recycling─Overview of techniques and trends. ACS Energy Lett 2022:712–9.

Chen S-P, Lv D, Chen J, Zhang Y-H, Shi F-N. Review on defects and modification methods of LiFePO4 cathode material for lithium-ion batteries. Energy & Fuels; 2022.

Wang, M., Liu, K., Dutta, S., Alessi, D. S., Rinklebe, J., Ok, Y. S., & Tsang, D. C. (2022). Recycling of lithium iron phosphate batteries: Status, technologies, challenges, and prospects. Renewable and Sustainable Energy Reviews, 163, 112515.

Zhao, T., Li, W., Traversy, M., Choi, Y., Ghahreman, A., Zhao, Z., ... & Song, Y. (2024). A review on the recycling of spent lithium iron phosphate batteries. Journal of Environmental Management, 351, 119670.

Yang, X. G., Liu, T., & Wang, C. Y. (2021). Thermally modulated lithium iron phosphate batteries for mass-market electric vehicles. Nature Energy, 6(2), 176-185.

Torregrosa, A. J., Broatch, A., Olmeda, P., & Agizza, L. (2023). A generalized equivalent circuit model for lithium-iron phosphate batteries. Energy, 284, 129316.

Lagnoni, M., Scarpelli, C., Lutzemberger, G., & Bertei, A. (2024). Critical comparison of equivalent circuit and physics-based models for lithium-ion batteries: A graphite/lithium-iron-phosphate case study. Journal of Energy Storage, 94, 112326.

Thelen, A., Lui, Y. H., Shen, S., Laflamme, S., Hu, S., Ye, H., & Hu, C. (2022). Integrating physics-based modeling and machine learning for degradation diagnostics of lithium-ion batteries. Energy Storage Materials, 50, 668-695.

How, D. N., Hannan, M. A., Lipu, M. S. H., Sahari, K. S., Ker, P. J., & Muttaqi, K. M. (2020). State-of-charge estimation of li-ion battery in electric vehicles: A deep neural network approach. IEEE Transactions on Industry Applications, 56(5), 5565-5574.

Tian, J., Xiong, R., Shen, W., & Lu, J. (2021). State-of-charge estimation of LiFePO4 batteries in electric vehicles: A deep-learning enabled approach. Applied Energy, 291, 116812.

Kara, A. (2021). A data-driven approach based on deep neural networks for lithium-ion battery prognostics. Neural Com-puting and Applications, 33(20), 13525-13538.

Wang, S., Ren, P., Takyi-Aninakwa, P., Jin, S., & Fernandez, C. (2022). A critical review of improved deep convolutional neural network for multi-timescale state prediction of lithium-ion batteries. Energies, 15(14), 5053.

Gu, X., See, K. W., Li, P., Shan, K., Wang, Y., Zhao, L., ... & Zhang, N. (2023). A novel state-of-health estimation for the lithium-ion battery using a convolutional neural network and transformer model. Energy, 262, 125501.

Buchanan, S., & Crawford, C. (2024). Probabilistic lithium-ion battery state-of-health prediction using convolutional neural networks and Gaussian process regression. Journal of Energy Storage, 76, 109799.

Chemali, E., Kollmeyer, P. J., Preindl, M., Fahmy, Y., & Emadi, A. (2022). A convolutional neural network approach for estimation of li-ion battery state of health from charge profiles. Energies, 15(3), 1185.

Zraibi, B., Okar, C., Chaoui, H., & Mansouri, M. (2021). Remaining useful life assessment for lithium-ion batteries using CNN-LSTM-DNN hybrid method. IEEE Transactions on Vehicular Technology, 70(5), 4252-4261.

Wang, Z., Zhao, X., Zhen, D., Pombo, J., Yang, W., Gu, F., & Ball, A. (2024). Adaptable capacity estimation of lithium-ion battery based on short-duration random constant-current charging voltages and convolutional neural networks. Energy, 306, 132541.

Schmitt, J., Horstkötter, I., & Bäker, B. (2023). Electrical lithium-ion battery models based on recurrent neural networks: A holistic approach. Journal of Energy Storage, 58, 106461.

Chen, J., Feng, X., Jiang, L., & Zhu, Q. (2021). State of charge estimation of lithium-ion battery using denoising autoencoder and gated recurrent unit recurrent neural network. Energy, 227, 120451.

Feng, X., Chen, J., Zhang, Z., Miao, S., & Zhu, Q. (2021). State-of-charge estimation of lithium-ion battery based on clockwork recurrent neural network. Energy, 236, 121360.

Liu, Y., Sun, J., Shang, Y., Zhang, X., Ren, S., & Wang, D. (2023). A novel remaining useful life prediction method for lithi-um-ion battery based on long short-term memory network optimized by improved sparrow search algorithm. Journal of Energy Storage, 61, 106645.

Pang, Y., Dong, A., Wang, Y., & Niu, Z. (2024). Deep learning from three-dimensional Lithium-ion battery multiphysics model Part II: Convolutional neural network and long short-term memory integration. Energy and AI, 17, 100398.

Gong, Y., Zhang, X., Gao, D., Li, H., Yan, L., Peng, J., & Huang, Z. (2022). State-of-health estimation of lithium-ion batteries based on improved long short-term memory algorithm. Journal of Energy Storage, 53, 105046.

Ang, E. Y., & Paw, Y. C. (2022). Linear model for online state of health estimation of lithium-ion batteries using segmented discharge profiles. IEEE Transactions on Transportation Electrification, 9(2), 2464-2471.

Athappan, V., Piriyadharshini, D., Suganthi, S., Abimanyu, A., Ranganathan, S., Saravanabalaji, M., & Muthuramalingam, E. (2023, June). Health Monitoring of E-Vehicle Battery Using Machine Learning. In 2023 2nd International Conference on Ad-vancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA) (pp. 1-6). IEEE.

Allirani, S., Pooja, K., Soundarya, E., & Nair, S. S. (2023, July). Li-ion Battery Life Estimation using K-Nearest Neighbor Al-gorithm. In 2023 2nd International Conference on Edge Computing and Applications (ICECAA) (pp. 1606-1610). IEEE.

Vilsen, S. B., & Stroe, D. I. (2024). Dataset of lithium-ion battery degradation based on a forklift mission profile for state-of-health estimation and lifetime prediction. Data in Brief, 52, 109861.

Sheikhani, A., & Agic, E. (2024). Lithium-Ion Battery SOH Forecasting With Deep Learning Augmented By Explainable Machine Learning.

Safavi, V., Mohammadi Vaniar, A., Bazmohammadi, N., Vasquez, J. C., & Guerrero, J. M. (2024). Battery Remaining Useful Life Prediction Using Machine Learning Models: A Comparative Study. Information, 15(3), 124.

Oyucu, S., Doğan, F., Aksöz, A., & Biçer, E. (2024). Comparative Analysis of Commonly Used Machine Learning Approaches for Li-Ion Battery Performance Prediction and Management in Electric Vehicles. Applied Sciences, 14(6), 2306.

Zhang, Y. (2023). Data-driven battery aging diagnostics and prognostics (Master's thesis, Chalmers Tekniska Hogskola (Sweden).

Luo, K., Chen, X., Zheng, H., & Shi, Z. (2022). A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries. Journal of Energy Chemistry, 74, 159-173.

Guo, Y., Huang, K., & Hu, X. (2021). A state-of-health estimation method of lithium-ion batteries based on multi-feature extracted from constant current charging curve. Journal of Energy Storage, 36, 102372.

Mocera, F., Somà, A., & Clerici, D. (2020, September). Study of aging mechanisms in lithium-ion batteries for working vehicle applications. In 2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER) (pp. 1-8). IEEE.

Seok, J., Lee, W., Lee, H., Park, S., Chung, C., Hwang, S., & Yoon, W. S. (2024). Aging Mechanisms of Lithium-ion Batteries. J. Electrochem. Sci. Technol, 15, 51-66.

Yang, S., Zhang, C., Jiang, J., Zhang, W., Zhang, L., & Wang, Y. (2021). Review on state-of-health of lithium-ion batteries: Characterizations, estimations and applications. Journal of Cleaner Production, 314, 128015.

Zhu, J., Xu, W., Knapp, M., Darma, M. S. D., Mereacre, L., Su, P., ... & Ehrenberg, H. (2023). A method to prolong lithium-ion battery life during the full life cycle. Cell Reports Physical Science, 4(7).

Sharma, S. K., Sharma, G., Gaur, A., Arya, A., Mirsafi, F. S., Abolhassani, R., ... & Mishra, Y. K. (2022). Progress in electrode and electrolyte materials: path to all-solid-state Li-ion batteries. Energy Advances, 1(8), 457-510.

Zhang, Y. (2023). Data-driven battery aging diagnostics and prognostics (Master's thesis, Chalmers Tekniska Hogskola (Sweden)).

Thelen, A. C. (2023). Machine learning-based aging models for estimating battery state of health and predicting future deg-radation (Doctoral dissertation, Iowa State University).

Liu, H., Li, C., Hu, X., Li, J., Zhang, K., Xie, Y., ... & Song, Z. (2025). Multi-modal framework for battery state of health evaluation using open-source electric vehicle data. Nature Communications, 16(1), 1137.

Li, K., & Chen, X. (2025). Machine Learning-Based Lithium Battery State of Health Prediction Research. Applied Sciences, 15(2), 516.

Downloads

Published

2025-07-01

How to Cite

Bensabeur , A., Arslan, B., Yılmaz, C. H., Kıvanç, D. D. Ömer C., & Tuncay, P. D. R. N. (2025). Predicting Battery Health for Electric Vehicles using Machine Learning Approach. International Journal of Advanced Natural Sciences and Engineering Researches, 9(6), 321–339. Retrieved from https://as-proceeding.com/index.php/ijanser/article/view/2724

Issue

Section

Articles