MACHINE LEARNING-BASED DRIVETRAIN FAULT CLASSIFICATION IN NEW ENERGY VEHICLES
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no2E.418Keywords:
New Energy Vehicles Drivetrain, Fault Classification, XGBoost, CatBoost, Random ForestAbstract
New Energy Vehicles (NEVs) represent an important direction in the development of sustainable transportation. The drivetrain of NEVs operates under changing electrical, mechanical, and environmental conditions, which can affect system stability and component integrity. Faults in the motor, inverter, and battery can interrupt power delivery, reduce operational continuity, and create risks for vehicle performance. This study presents an evaluation of machine learning methods for classifying drivetrain operating states using a structured dataset that contains measurements of voltage, current, motor speed, temperature, vibration, ambient temperature, and humidity. Three ensemble tree-based machine learning models, Random Forest, XGBoost, and CatBoost, are developed to classify four labeled states: normal condition, motor fault, inverter fault, and battery fault. Each model is trained and tested using common performance indicators, including accuracy, precision, recall, F1 score, and computation time. The experimental results demonstrate that ensemble learning models achieve high and stable classification performance across all drivetrain operating conditions, with XGBoost exhibiting the best balance between accuracy and computational efficiency. To enhance practical applicability, a real-time fault diagnosis demonstration is implemented, confirming the model's suitability for onboard systems. The findings indicate that machine learning can support automatic identification of drivetrain faults and contribute to diagnostic procedures, maintenance planning, and system reliability improvement in NEVs applications.
References
[1] M. S. Hossain et al., “AI-powered fault prediction and optimization in new energy vehicles (NEVs) for the US market,” J. Comput. Sci. Technol. Stud., vol. 7, no. 1, pp. 1–16, 2025, doi: https://doi.org/10.32996/jcsts.2025.7.1.1
[2] M. Z. Khaneghah, M. Alzayed, and H. Chaoui, “Fault detection and diagnosis of the electric motor drive and battery system of electric vehicles,” Machines, vol. 11, no. 7, p. 713, 2023, doi: https://doi.org/10.3390/machines11070713
[3] M. A. Islam, M. Z. H. Majumder, M. A. Hussein, K. M. Hossain, and M. S. Miah, "A review of machine learning and deep learning algorithms for Parkinson's disease detection using handwriting and voice datasets," Heliyon, vol. 10, no. 3, 2024. https://doi.org/10.1016/j.heliyon.2024.e25469
[4] A. A. Silva, A. M. Bazzi, and S. Gupta, “Fault diagnosis in electric drives using machine learning approaches,” in Proc. Int. Electr. Mach. Drives Conf. (IEMDC), Chicago, IL, USA, 2013, pp. 722–726, doi: https://doi.org/10.1109/IEMDC.2013.6556173
[5] H. El Hadraoui, E. Sabani, M. Zegrari, A. Chebak, and O. Laayati, “AI-driven diagnosis and health management of autonomous electric vehicle powertrains: An empirical data-driven approach,” Results Eng., vol. 27, Art. no. 106157, 2025, doi: https://doi.org/10.1016/j.rineng.2025.106157
[6] V. Kavana and M. Neethi, “Fault analysis and predictive maintenance of induction motor using machine learning,” in Proc. Int. Conf. Electr., Electron., Commun., Comput., Optim. Technol. (ICEECCOT), Mysuru, India, 2018, pp. 963–966, doi: https://doi.org/10.1109/ICEECCOT43722.2018.9001543
[7] J. W. Oliveira, D. Passos, D. Carvalho, J. F. Melo, E. G. Silva, and P. S. de Mattos Neto, “Improving electrical fault detection using multiple classifier systems,” Energies, vol. 17, no. 22, 2024, doi: https://doi.org/10.3390/en17225787
[8] D. Gonzalez-Jimenez, J. Del-Olmo, J. Poza, F. Garramiola, and P. Madina, “Data-driven fault diagnosis for electric drives: A review,” Sensors, vol. 21, no. 12, Art. no. 4024, 2021, doi: https://doi.org/10.3390/s21124024
[9] Ziya, “New Energy Vehicles Diagnosis,” Kaggle, [Online]. Available: https://www.kaggle.com/datasets/willianoliveiragibin/new-energy-vehicles?resource=download
[10] H. A. Salman, A. Kalakech, and A. Steiti, “Random forest algorithm overview,” Babylonian J. Mach. Learn., vol. 2024, pp. 69–79, 2024, doi: https://doi.org/10.58496/BJML/2024/007
[11] S. S. Azmi and S. Baliga, “An overview of boosting decision tree algorithms utilizing AdaBoost and XGBoost boosting strategies,” Int. Res. J. Eng. Technol., vol. 7, no. 5, pp. 6867–6870, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:235818978
[12] J. T. Hancock and T. M. Khoshgoftaar, “CatBoost for big data: An interdisciplinary review,” J. Big Data, vol. 7, no. 1, Art. no. 94, 2020, doi: https://doi.org/10.1186/s40537-020-00369-8.
