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{199476,
        author = {Kunal Ovhal and Abhinav Edake and Ms. Archana Suryawanshi and Ms. Kajal Kamable},
        title = {Impact of AI for Enhancing Predictive Maintenance in Electric Vehicles Using Real-Time Sensor Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12922-12927},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199476},
        abstract = {Electric vehicles (EVs) are gaining popularity as an alternative to traditional internal combustion engine vehicles for sustainable transportation due to growing awareness of environmental pollution, greenhouse gas emissions and depleting fossil fuel reserves. Governments and industries worldwide are encouraging the use of EVs through incentives and technological development. However, even with the benefits, EVs are still facing challenges in maintaining the operation health, efficiency, and reliability of core components, such as batteries, electric motors and power electronics. Conventional maintenance methods, such as periodic maintenance and visual inspections, are not adequate for detecting early- stage fault conditions, resulting in unscheduled failures, increased downtime, and higher maintenance costs.
This study presents an Artificial Intelligence (AI)-based electric vehicle health monitoring and predictive maintenance system to address these limitations. The system continuously collects critical operational parameters such as battery state of health, temperature changes, charge and discharge cycles, voltage changes, current changes, and energy consumption patterns under various driving conditions. Advanced machine learning techniques convert these parameters into hidden patterns, anomalies, and failure prediction with high accuracy beforehand.
Additionally, the proposed system implements a graphical interface that is intuitive and interactive with real-time display data using visual dashboards such as bar charts and performance graphs. Furthermore, real-time data could also be accessed remotely via the cloud that enables the vehicle system to be monitored by operators, technicians, and fleets for optimal performance and in a timely manner that aids in better decision-making and faster diagnostics.
Switching from reactive and predetermined time-based maintenance to condition-based predictive maintenance using the proposed system increase operational efficiency and minimize unnecessary servicing. Experimental results indicate that the system leads to higher fault detection accuracy and timely maintenance actions which reduce vehicle downtime and operational costs.
Moreover, this system enhances the safety, reliability, and overall performance of electric vehicles and increases the durability of critical components. The system is scalable and flexible, and it is a viable candidate for incorporation into contemporary intelligent transportation systems and smart mobility ecosystems.},
        keywords = {Electric Vehicles, Artificial Intelligence, Predictive Maintenance, Battery Monitoring, Machine Learning, EV Performance Monitoring.},
        month = {April},
        }