With the target of some common vibration failure in turbine, Putting forward the architecture of condition-based diagnosis system, The concept of subordinate degree of fuzzy theory is introduced to describe the tendency of the steam turbine vibration fault by analyzing the uncertainty in turbine vibration fault diagnosis. and the dynamic fuzzy clustering analysis method is applied to analyze the vibration causes of the unit. The fault diagnosis based on Bayesian network is studied by analyzing the uncertainty in turbine vibration fault diagnosis. A Bayesian Network architecture available to such fault diagnosis is proposed. The unique advantages of fault diagnosis expert system based On Bayesian Network are illustrated by modeling process and diagnosis results. |