A Motor Fault Diagnosis System Based on Cerebellar Model Articulation Controller

The purpose of this paper is to construct a smart induction motor fault diagnosis system with cerebellar model articulation controller (CMAC). First, we divide induction motor faults in three kinds, rotor mandrel fault, bearing fault and electrical fault. Then, we subdivide them into ten types, in each of which the vibration signal spectra of induction motors were measured and sorted for establishing the individual fault types. From the information on motor faults, we identify representative characteristic frequency spectra for the faults to further establish the correlations between each of the fault types and its corresponding characteristic frequency spectrum as the basis for the development of a motor fault diagnosis system. In this paper, the theoretic basis is CMAC, and the data of vibration signal spectrum measured against the motor faults are used to train the fault diagnosis system. We then conducted fault diagnoses with the data of actual motor run. The test results demonstrated that the proposed induction motor fault diagnosis system is capable of fast algorithm, requires less data to train with, as well as has excellent power of identification.