Anomaly Detection in Electro-Mechanical Devices Using MFCC

This research introduces an innovative approach to detecting anomalies in electric motor-driven fan systems. Mel-Frequency Cepstral Coefficients (MFCCs) are employed for sound signal feature extraction. A specialized artificial neural network (ANN) model is trained using these extracted features to differentiate between normal and anomalous sound patterns based on their acoustic characteristics. The results demonstrate the efficacy of the proposed methodology in distinguishing normal sounds from defective sounds of electric motor-driven systems. This research contributes to the enhancement of maintenance practices and operational reliability within industrial settings, the field of electric motors, and anomaly detection using MFCCs.