Abstract
The fault diagnosis by vibration signals on rotary machineries is more difficult than independent mechanical elements, because almost complex machines are composed of great number of structural bodies and mechanical elements. Rotary machineries find it hard to identifi of fault elements to exist a number of noise sources within the engine. This paper proposes a new condition monitoring method on rotary machineries by multiplex elements Auto Regressive model and cross correlation of close two point signals generated by diagnosed machines. Artificially assumed fault conditions in rotary machineries are concerning a rotor and gear unbalance, a wear of gear. Identification of above the fault conditions has been carried out based on the proposed method at diagnosed location within the rotary machine. It is possible to diagnose above fault condition by the proposal SN ratio improvement method.
