Intelligent condition diagnosis method for rotating machinery using Relative Ratio Symptom Parameter and Bayesian Network

In order to effectively identify faults of a rotating mechanics, a new kind of symptom parameter — Relative Ratio Symptom Parameter (RRSP) is proposed in this paper. Moreover, combined with Bayesian Network, the corresponding fault diagnosis system is built. In the paper, the vibration signals are monitored and measured and the relative ratio symptom parameter is calculated, of which the parameters whose identification index is bigger are chosen as the input of Bayesian Network, by observing and analyzing the output that is the probability of normal state and abnormal states, Bayesian Network in the mechanical fault diagnosis is proved to be effective by real date measured in each state of a rotating machine.