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{181893,
        author = {SASMITA PANI and Dr.Omkar Pattnaik and Sudeepta Pal and Prof Binod kumar pattanayak},
        title = {Scalable ML Solutions for Predictive Maintenance and Real-time Anomaly Detection in IIoT Systems: A Case Study Using the NASA C-MAPSS Dataset},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {393-397},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181893},
        abstract = {With the rise of the Industrial Internet of Things (IIoT), the need for efficient and scalable solutions for predictive maintenance (PdM) and anomaly detection (AD) has become more critical. These technologies help avoid costly downtimes and improve operational efficiency. In this paper we develop and implement a comprehensive Machine Learning (ML) framework for PdM and AD using the NASA CMAPSS dataset, which contains data related to turbofan engine degradation. We leverage supervised models like Gradient Boosting and Long Short-Term Memory (LSTM) networks for Remaining Useful Life (RUL) prediction and unsupervised models such as Isolation Forest and Autoencoders for anomaly detection. Further we investigate the scalability of the proposed solutions and deploy them using a hybrid cloud-edge architecture which allows real-time processing and efficient management of large sensor data. Our experiments show that our ML solutions improve the accuracy of RUL predictions and anomaly detection, offering practical insights for real-time IIoT applications},
        keywords = {},
        month = {July},
        }