Rotating machinery is widely used in today's industry and continuously the performance demand criteria is increasing. Machine failures can be catastrophic thus resulting in costly stop time. The safety, reliability, efficiency and performance of rotating machinery are major concerns in industry. An effective diagnosis may be able to make a reliable prediction of lead-time to detect failure. Therefore, conducting effective condition monitoring and fault diagnosis ought to be evaluated. The main aim of this research work is to design a reliable gearbox diagnostic system based on vibration data signatures from an industrial equipment and using neural network methods to diagnose the system. The analysis procedure was to perform a statistical features selection from the vibration data. An effective and efficient feature extraction techniques are critical for reliably diagnosing rotating machinery faults.
|State||Published - 1 Jan 2015|
|Event||44th International Congress and Exposition on Noise Control Engineering, INTER-NOISE 2015 - San Francisco, United States|
Duration: 9 Aug 2015 → 12 Aug 2015
|Conference||44th International Congress and Exposition on Noise Control Engineering, INTER-NOISE 2015|
|Period||9/08/15 → 12/08/15|
Bibliographical notePublisher Copyright:
© 2015 by ASME.