F.A.I.R. open dataset of brushed DC motor faults for testing of AI algorithms

Practical research in AI often lacks of available and reliable datasets so the practitioners can try different algorithms. The field of predictive maintenance is particularly challenging in this aspect as many researchers don't have access to full-size industrial equipment or there is not available datasets representing a rich information content in different evolutions of faults.

This dataset presents the evolution of typical faults (commutator, winding and brush wear) in inexpensive DC motors under extensive monitoring (vibration, temperature, voltage, current and noise). These motors exhibit a particularly short useful life when operating out of nominal conditions (from 30 minutes to 6 hours) which make them very interesting to test different signal processing algorithms and introduce students and researchers into signal processing, fault detection and predictive maintenance.

The data-set comprises two main elements:

A spreadsheet with the processing of each raw data file

4 folders with raw data files in HDF5 format

The spread sheet contains the following columns

filename of the raw data file

timestamp of the raw data file

speed of the motor in rpm

speed of the motor in Hz

Current of the moter (A)

Voltage supply (V)

surface motor temperature (ºC)

ambient temperature (ºC)

For each measured signal (Vibration, current, voltage) the vibration of the main harmonic (at the speed of the motor) and it's first 10 multiple.

For each measured signal (Vibration, current, voltage) the vibration in 4 bands: 0-4kHz, 4kHz-8kHz, 8kHz-16kHz, 16kHz-26kHz

The raw data files in HDF5 format contains the instantaneous measured vibration (g), current (A) and voltage (volts) of the DC motor at 51.200 Hz.