Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179974,
        author = {Aaryan Saraswat and Dev Peshawari and Satyasheel Ray and Rajesh Kumar Agarwal},
        title = {Predictive Maintenance of Automotive Engines Using Machine Learning and Deep Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {446-455},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179974},
        abstract = {The integration of intelligent diagnostics in e-mobility systems is vital for ensuring vehicle reliability and minimizing operational costs. This study presents a data-driven predictive maintenance framework for electric automotive engines, utilizing real-time sensor data—including engine RPM, oil temperature, and pressure—to preemptively identify potential faults. A robust preprocessing framework was applied to address data inconsistencies, incorporating normalization, skewness correction, and correlation analysis. Four classification models were evaluated: Logistic Regression, Random Forest, XGBoost, and an LSTM neural network. The LSTM model demonstrated superior performance, achieving 95.2% accuracy and a 0.968 ROC-AUC score by effectively capturing temporal dependencies in sensor data sequences. These results underscore the potential of deep learning techniques in enabling real-time fault prediction, offering a scalable solution for reducing unplanned downtime. The proposed system aligns with IoT-enabled vehicular ecosystems, providing automotive manufacturers and fleet operators with actionable insights to optimize maintenance workflows and enhance operational efficiency.},
        keywords = {Predictive Maintenance, Automotive Diagnostics, Machine Learning, Deep Learning, LSTM, Engine Health, XGBoost, Real-Time Monitoring},
        month = {May},
        }