Bearing Fault Diagnosis based on 2D-Acoustic Imaging and Convolutional Neural Networks

Bearing faults are the common mode of failure in rotating machinery. Various techniques have been proposed for bearing fault diagnosis based on vibration signals. However, vibration-based fault diagnosis is restrained in some cases since they are limited by surface characteristics such as temperature. Acoustic-based fault diagnosis has the edge of non-contact measurement over vibration-based fault diagnosis. Convolutional neural networks have been used widely in condition monitoring to learn features naturally from the raw data, which does not require exhaustive domain knowledge and expertise. In the present study, 1D-acoustic signals are converted into 2D images and a Convolutional Neural Networks algorithm is applied to classify the bearing health conditions. The proposed method shows promising results on experimental data conducted on an in-house test rig.