Bearing Fault Classification using Acoustic Features and Artificial Neural Network

Bearing fault diagnosis is essential to ensure the machine's operational safety and economic efficiency. Condition monitoring of the bearings can be done using data from different sensors. Despite the recent advancement in machine learning and deep learning methods, only vibration data has been widely used for fault detection. In this work, the acoustic signal acquired from a bearing rig is used for fault detection by extracting the audio features from the acoustic signal. A simple Artificial Neural Network is used for the classification of faults