Skip to Main Content
The shaft orbits and dynamic characteristics of the shaft centre orbit contain abundant information for the fault diagnosis of rotating machinery and reflect different faults of rotating machine. Therefore the shaft orbits recognition plays an important role in the fault diagnosis of steam turbine generator set. An automatic identification method of shaft orbit for steam turbine generator sets is proposed in this paper. The median morphological filter combining the open-closing with close-opening is used to eliminate the noise in the original X and Y vibration signals. Then the seven invariant moment feature are extracted from the shaft orbit reconstructed. Input the seven invariant moments to the trained BP neural network, the shaft orbit can be identified automatically. A case is verified this model. It is shown that this model is feasible and high precision for identify the shaft orbit in fault diagnosis.