Prediksi Degradasi Kesehatan Baterai Kendaraan Listrik Berbasis Machine Learning pada Pengisian Cepat DC
DOI:
https://doi.org/10.29407/ays90r20Keywords:
Machine Learning, Prediksi Degradasi, Fast Charging DCAbstract
Perkembangan kendaraan listrik mendorong penerapan sistem pengisian cepat untuk meningkatkan kenyamanan pengguna. Namun, pengisian cepat dengan arus dan daya tinggi berpotensi mempercepat degradasi kesehatan baterai (State of Health / SoH), yang berdampak pada umur pakai dan keandalan baterai kendaraan listrik. Oleh karena itu, diperlukan pendekatan prediktif yang mampu mengidentifikasi degradasi kesehatan baterai secara akurat sejak dini. Penelitian ini mengusulkan pendekatan machine learning berbasis Random Forest Regressor untuk memprediksi degradasi kesehatan baterai kendaraan listrik pada proses pengisian cepat DC. Dataset diperoleh dari hasil simulasi pengisian cepat yang mempertimbangkan parameter arus pengisian, tegangan DC, suhu baterai, dan State of Charge (SoC). Model dilatih untuk mempelajari hubungan nonlinier antara parameter pengisian cepat dan degradasi kesehatan baterai yang dinyatakan sebagai ΔSoH. Kinerja model dievaluasi menggunakan metrik Mean Absolute Error (MAE), Root Mean Square Error (RMSE), dan koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa model Random Forest mampu memprediksi degradasi kesehatan baterai dengan nilai MAE sebesar 0.00000009, RMSE sebesar 0.00000015, serta nilai R² sebesar 0.999998, yang menunjukkan tingkat akurasi prediksi yang sangat tinggi. Pendekatan ini berpotensi digunakan sebagai dasar pengambilan keputusan dalam pengelolaan sistem pengisian cepat DC yang lebih aman dan berkelanjutan, serta mendukung pengembangan sistem pengisian kendaraan listrik yang cerdas dan berorientasi pada umur pakai baterai.
Downloads
References
K. T. Chau, C. C. Chan, S. Niu, W. Liu, and T. Liu, “Graduate Degree in Electric Vehicles—A Timely Programme for Modern Society,” World Electric Vehicle Journal, vol. 16, no. 1, p. 31, Jan. 2025, doi: 10.3390/wevj16010031.
[2] F. Alanazi, “Electric Vehicles: Benefits, Challenges, and Potential Solutions for Widespread Adaptation,” Applied Sciences, vol. 13, no. 10, p. 6016, May 2023, doi: 10.3390/app13106016.
[3] R. R. Kumar, C. Bharatiraja, K. Udhayakumar, S. Devakirubakaran, K. S. Sekar, and L. Mihet-Popa, “Advances in Batteries, Battery Modeling, Battery Management System, Battery Thermal Management, SOC, SOH, and Charge/Discharge Characteristics in EV Applications,” IEEE Access, vol. 11, pp. 105761–105809, 2023, doi: 10.1109/ACCESS.2023.3318121.
[4] P. Dini, A. Colicelli, and S. Saponara, “Review on Modeling and SOC/SOH Estimation of Batteries for Automotive Applications,” Batteries, vol. 10, no. 1, p. 34, Jan. 2024, doi: 10.3390/batteries10010034.
[5] B. Babu, P. Simon, A. Balducci, B. Babu, A. Balducci, and P. Simon, “Fast Charging Materials for High Power Applications,” 2020, doi: 10.1002/aenm.202001128.
[6] “A Quick Guide to Fast Charging 1.”
[7] A. Tomaszewska et al., “Lithium-ion battery fast charging: A review,” eTransportation, vol. 1, p. 100011, Aug. 2019, doi: 10.1016/j.etran.2019.100011.
[8] C. Miller, M. Goutham, X. Chen, and S. Stockar, “DC Fast Charging Optimization for Capacity Fade Minimization,” 2022.
[9] S. Samsurizal, A. N. Afandi, and M. R. Faiz, “A Comparative Analysis of Fast Charging Performance and Battery Life Against Charging Current Variations,” ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA, vol. 11, no. 52, pp. 81–86, 2025, doi: 10.5935/jetia.v11i52.1536.
[10] A. N. Afandi and Y. Sulistyorini, “Transformation of Thunderstorm Mechanisms into Computational Intelligence Applied to the Load Dispatch,” in 2019 International Conference on Information and Communications Technology (ICOIACT), IEEE, Jul. 2019, pp. 773–778. doi: 10.1109/ICOIACT46704.2019.8938531.
[11] J. G. Qu, Z. Y. Jiang, and J. F. Zhang, “Investigation on lithium-ion battery degradation induced by combined effect of current rate and operating temperature during fast charging,” J Energy Storage, vol. 52, p. 104811, Aug. 2022, doi: 10.1016/J.EST.2022.104811.
[12] P. Makeen, H. A. Ghali, and S. Memon, “A Review of Various Fast Charging Power and Thermal Protocols for Electric Vehicles Represented by Lithium-Ion Battery Systems,” Mar. 01, 2022, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/futuretransp2010015.
[13] H. Rathore, H. K. Meena, and P. Jain, “Prediction of EV Energy consumption Using Random Forest And XGBoost,” in 2023 International Conference on Power Electronics and Energy (ICPEE), IEEE, Jan. 2023, pp. 1–6. doi: 10.1109/ICPEE54198.2023.10060798.
[14] H. A. Salman, A. Kalakech, and A. Steiti, “Random Forest Algorithm Overview,” Babylonian Journal of Machine Learning, vol. 2024, pp. 69–79, Jun. 2024, doi: 10.58496/BJML/2024/007.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zulham Kentji, Samsurizal Samsurizal, Septiannissa Azzahra, Dwi Listiawati, Dody Dody, Kartika Tresya Mauriraya
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
