1D-CNN Vibration Signal Bearing Fault Diagnosis

Bearing fault diagnosis has been a challenge in the monitoring activities of rotating machinery, and it's receiving more and more attention. The conventional fault diagnosis methods usually extract features from the waveforms or spectrums of vibration signals in order to correctly classify faults.

CWRU-dataset

Case Western Reserve University Bearing Fault Dataset

https://csegroups.case.edu/bearingdatacenter/pages/download-data-file

Data presented here were collected for -

1. normal bearings,
2. single-point drive end and
3. fan end defects.

Data collected at 12,000 samples/second and at 48,000 samples/second for drive end bearing experiments.
All fan end bearing data was collected at 12,000 samples/second.

Data files are in Matlab format.
Each file contains -

1. Fan end
2. Drive end vibration data as well as
3. motor rotational speed.

For all files, the following item in the variable name indicates:
  
DE - drive end accelerometer data

FE - fan end accelerometer data

BA - base accelerometer data

time - time series data

RPM- rpm during testing

Stargazers over time