Crack Fault Diagnosis and Location Method for a Dual-disks Hollow Shaft Rotor System Based on the Radial Basis Function Network and Pattern Recognition Neural Network

Abstract

In recent years, the crack fault is one of the most common faults in the rotor system, and its fault diagnosis has been paid close attention by researchers. However, the traditional fault diagnosis methods based on various signal processing algorithms can only be adopted to determine whether there is a crack fault in the rotor system, but the dynamic response of the rotor system can hardly be used to calculate the depth and position of the crack. In this paper, a new crack fault diagnosis and location method for a dual-disks hollow shaft rotor system based on the Radial basis function (RBF) network and Pattern recognition neural network (PRNN) is presented. Firstly, a rotor system model with a breathing crack suitable for a short-thick hollow shaft rotor is established based on the finite element method and Timoshenko beam theory. Then the dynamic response is calculated by the harmonic balance method and the analysis results show that the first critical whirl speed, the first subcritical speed, the first critical speed amplitude, and the super-harmonic resonance peak at 1/2 first critical whirl speed of the rotor system are closely related to the depth and position of the crack, which can be used for crack fault diagnosis. Finally, the RBF network and PRNN are adopted to determine the depth and approximate location of the crack by taking the above dynamic response characteristics as input, respectively. The test results show that this method has high fault diagnosis accuracy.