I would like to take a data driven approach for fatigue or wear estimation detection of a small spherical plain bearings in an oscillating conveyor assembly.
What are the appropriate measurements to make which can be used for later feature extraction and training of a detection model?
Attached in a example video of when the bearing has completely failed as well as a simple layout of the oscillating conveyor assembly. (Small end bearing is the one we are interested in)
Recommendations of appropriate sensor type for acoustic, acoustic emission, acceleration etc. would be greatly appreciated.
Hello Matthew Dabin
For diagnostics and monitoring of rolling bearings, there are two main approaches:
Acoustic Emission and Vibration analysis. Therefore the instrumentation you use will depend on the type of monitoring. Also take into account that in order to get a good data interpretation, additional to taking measurements, you would need further signal processing, including filtering, synchronized rotation vector and profile monitoring, averaging, envelope calculation, calculation of amplitudes of selected frequency components, cepstrum calculations, , etc.
You may find the type of sensors used in diagnosis and monitoring of bearings as well as other interesting practical information in the following white paper:
https://www.emerson.com/documents/automation/white-paper-measurement-types-in-machinery-monitoring-ams-en-39660.pdf
Hope this helps!
- Badges
- Science topic