Copyright © 2026 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{198979,
        author = {Nayab Pasha and Shreeshanth Redddy and Sai Varun and Saravan Malempati and Ms. Umadevi and Dr. Siva Prasad},
        title = {An Ensemble Deep Learning Model for Vehicular Engine Health Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {13095-13099},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198979},
        abstract = {Vehicular engine failures impose direct risks on transportation safety, logistics continuity, and maintenance economics. Conventional manual diagnostic checks lack predictive capability, often resulting in sudden breakdowns and unplanned repair costs. To address these challenges, this paper proposes a predictive maintenance framework using an ensemble Artificial Intelligence model for vehicular engine health prediction. The system integrates a Random Forest classifier deployed through a Django-based web application, and benchmarks it against a dual-architecture ensemble deep learning model. A total of 12,350 simulated and Kaggle-based real-world engine parameter samples were used, each containing critical operational metrics such as RPM, fuel pressure, cooling temperature, and lubrication temperature. Experimental results reveal that the Random Forest model performs significantly better, achieving approximately 93% prediction accuracy compared to around 63% from the deep learning ensemble. The final deployed application enables users to upload engine data and receive real-time engine condition predictions, supporting proactive maintenance and reducing breakdown risks.},
        keywords = {RPM, Conventional manual diagnostic, Django, predictive capability},
        month = {April},
        }