Loading…
This event has ended. Visit the official site or create your own event on Sched.
Welcome to ICSV26!
Back To Schedule
Wednesday, July 10 • 15:30 - 18:00
MONITORING OF COMPRESSOR OPERATIONS – A MACHINE LEARNING APPROACH

Log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Compressors are backbone components of many industrial branches. Failures of compressors can be very costly. Operational and maintenance cost could be saved with proper monitoring technologies. Acoustical methods play a key role for monitoring and trend analyses. In addition to acoustics and vibration measurements at lower frequencies, the sensor and signal processing methodologies have been extended towards higher frequencies. This results in advantages for the earlier prediction of operational states and lifetime of compressor components due to its sensitivity to small scale vibrations and turbulences caused by vibration effects. An increase of friction and micro-shocks, often an indicator for inappropriate operation, does not provide intense vibration. The methodology will be explained by means of a case study of screw type compressors. The combined use of vibration and ultrasound together with advanced data technology has been demonstrated for different operational states and classes of faults. It could be concluded that the combination of vibration and ultrasound provides a promising tool for condition monitoring and fault diagnosis of compressors. Data processing based on machine learning techniques such as deep neural networks enables improved trend analyses.


Wednesday July 10, 2019 15:30 - 18:00 EDT
St-Laurent 3, Board 06-A
  T10 Sig. Proc. & nonlin. mthds., RS02 Fault diagnosis & progn