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{201070,
        author = {Mrs. M. Malarvizhi and Ashwin Kumar E and Kiruba P and Sethupathi M and Thangavel R},
        title = {AI-Based Universal Mechanical Noise Classifier for Fault Diagnosis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {309-314},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201070},
        abstract = {Mechanical systems such as motors, pumps, gearboxes, and compressors generate characteristic noise patterns during operation. Deviations in these acoustic signatures often indicate faults such as bearing wear, misalignment, or imbalance. Traditional fault diagnosis techniques rely on vibration sensors and expert analysis, which are costly, equipment-specific, and not scalable.
This project proposes an AI-based universal mechanical noise classifier that uses acoustic signals captured via microphones to automatically identify fault conditions. Audio signals are preprocessed, transformed into spectral features, and classified using machine learning/deep learning models. The system provides an affordable, scalable, and non-intrusive solution for early fault detection across multiple mechanical systems.},
        keywords = {Acoustic Fault Diagnosis, Machine Learning, Predictive Maintenance, MFCC Feature Extraction, Mechanical Condition Monitoring},
        month = {May},
        }