Acoustic-Based Detection Technique for Identifying Worn-Out Components in Large-Scale Industrial Machinery

This research addresses the challenge of monitoring large-scale machine halls, particularly in context iron making processes. We propose an acoustic sound-based condition (ASCM) system to detect potential faults and damages machinery. The study focuses on selecting suitable audio features, integrating physical insights regarding fault, determining optimal window lengths for feature extraction. Our fault detection method utilizes outlier with a Gaussian mixture model trained features extracted only from normal operating conditions. compare conventional physically motivated conduct length analysis. results demonstrate effectiveness our approach impact incorporating performance.