Application of wavecluster to fault diagnosis in aero-engine rotor system

For the typical fault characteristics of aero-engine rotor system, we apply wavecluster to the aero-engine rotor system fault diagnosis in this paper. In the process of quantizing feature space, the method combination of empirical formula and heuristic is used to solve the problem of optimal quantitative values. The calculation results show that this method can quickly determine the optimal quantitative values. By comparing to the properties of the usual wavelet basis function, and then combine with the features of the vibration signal of rotor system, we selected db2 wavelet for the wavelet transform. The final diagnosis result shows that the fault diagnosis method of aero-engine rotor system based on wavecluster is very effective, and the rotor faults data can be assigned to the corresponding rotor faults.