Is this project an undergraduate, graduate, or faculty project?

Undergraduate

individual

What campus are you from?

Daytona Beach

Authors' Class Standing

Annika Anderson, Senior

Lead Presenter's Name

Annika Anderson

Faculty Mentor Name

David Canales Garcia

Abstract

The sound a machine makes can be used to generate a profile of the machine. By analyzing the properties of the audio signal, it is possible to determine the expected behavior of the equipment, allowing for anomalies to be identified and diagnosed before they cause significant problems. By constantly monitoring the performance of assets, it is possible for maintenance to be proactive rather than reactive. As a preliminary investigation into the usage of spectral descriptors to predict mechanical failure, multiple pieces of equipment in the John Mica Engineering and Aerospace Innovation Complex were recorded. Trends were determined, and profiles of these machines were constructed. More than 24 hours of audio were recorded and analyzed, taken throughout the operation cycles of the machines. The da Vinci Super by XYZPrinting, a large format 3D printer, was monitored extensively; a failure to correctly print a part was successfully identified and predicted through audio signal processing before a visual inspection of the part confirmed the results of the algorithm.

Did this research project receive funding support from the Office of Undergraduate Research.

Yes, SURF

Share

COinS
 

Audio Signal Analysis as a Tool in Preventive Maintenance

The sound a machine makes can be used to generate a profile of the machine. By analyzing the properties of the audio signal, it is possible to determine the expected behavior of the equipment, allowing for anomalies to be identified and diagnosed before they cause significant problems. By constantly monitoring the performance of assets, it is possible for maintenance to be proactive rather than reactive. As a preliminary investigation into the usage of spectral descriptors to predict mechanical failure, multiple pieces of equipment in the John Mica Engineering and Aerospace Innovation Complex were recorded. Trends were determined, and profiles of these machines were constructed. More than 24 hours of audio were recorded and analyzed, taken throughout the operation cycles of the machines. The da Vinci Super by XYZPrinting, a large format 3D printer, was monitored extensively; a failure to correctly print a part was successfully identified and predicted through audio signal processing before a visual inspection of the part confirmed the results of the algorithm.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.