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{197518,
        author = {Om Jambukar and Nikhil Bhavar and Ritesh Nemade and Vitthal Kamble},
        title = {AI-Driven Predictive Maintenance Framework Using IoT Sensors and Cloud Analytics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {6108-6123},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197518},
        abstract = {Ensuring uninterrupted operation of industrial and electronic equipment remains a persistent challenge in modern manufacturing and process industries. This paper introduces an intelligent IoT-based predictive maintenance (PdM) framework—designated the AI-Driven Predictive Maintenance Framework (ADPMF)—that leverages real-time multi-sensor data, cloud-hosted analytics, and machine learning classification to deliver proactive equipment health assessment. The framework acquires temperature, vibration, and electrical current measurements through an ESP32 microcontroller, transmitting structured sensor payloads to a Firebase Realtime Database at five-second intervals. A Python inference engine applies a Random Forest classifier to assign each device a health risk level—LOW, MEDIUM, or HIGH—based on a nine-dimensional engineered feature vector. The system achieves a macro-average F1-score of 94.3% and furnishes maintenance personnel with an 18.4-second early-warning lead time ahead of HIGH-risk fault transitions. Systematic benchmarking against five contemporary PdM frameworks validates the framework’s competitive predictive accuracy and cost-efficient deployment profile. Rigorous mathematical formulations, algorithmic pseudocode, a comparative benchmarking study, system design justification, advanced model selection analysis, explainable AI integration, and an Industry 4.0 deployment roadmap are additionally contributed.},
        keywords = {Predictive Maintenance; Internet of Things; ESP32; Random Forest; Firebase; Machine Learning; Cloud Analytics; Industry 4.0; Fault Detection; IIoT; Explainable AI; Feature Engineering.},
        month = {April},
        }