Author Description

Machinery plays a key role for manufacturing and production companies. Most of the machines of a production company are subject to vibration signatures of one form or another. Vibration Signatures are quite often used to diagnose the health of the machines, i.e., detect problems in the machines before catastrophic failure takes place. In this thesis, first vibration data is generated using a machinery fault simulator (MFS). The piezoelectric transducers are mounted at various locations on the vibration fault simulating system to collect the data. The primary goal of this thesis deals with the data analytics to identify the source of a problem in the machine. National Instruments Laboratory Virtual Instrumentation Engineering Workbench (LabVIEW) for acquiring the data and KNIME for the statistical regression analysis are the main tools used to identify the faults which occur in the MFS.