Condition montoring of rotating machines supported by hydrostatic bearings

In this research work a neural network based technique to be applied on condition monitoring and diagnosis of rotating machines equipped with hydrostatic self levitating bearing system is presented. Based on fluid measured data, such pressures and temperature, vibration analysis based diagnosis is being carried out by determining the vibration characteristics of the rotating machines on the basis of signal processing tasks. Required signals are achieved by conversion of measured data (fluid temperature and pressures) into virtual data (vibration magnitudes) by means of neural network functional approximation techniques.