Vibration Based Condition Monitoring of Rotating Machines: A Future Possibility?

Abstract

Adopted conventional practice is to use number of vibration sensors at a bearing pedestal of a rotating machine for the vibration based condition monitoring. Number of bearings in a machine, say, a Turbo-Generator (TG) set is likely to be very high, hence increasing the number of sensors to large number. Therefore data acquisition results in huge data sets to analyze to track any fault/faults which often depend on the experience and the engineering judgment. The effort of the present study is to reduce the number of sensors per bearing pedestal based on the higher order spectra (HOS) and data fusion so that the vibration data is managed efficiently and is able to detect fault uniquely. The preliminary results of the suggested approach have been discussed here.