Induction motor fault diagnosis using ANFIS based on vibration signal spectrum analysis

In this work, vibration signals of a faulty induction motor are analyzed to establish an intelligent fault diagnosis system using Adaptive Neuro-Fuzzy Inference System (ANFIS). Firstly, signal spectra of individual motor fault models are obtained. Subsequently, representative characteristic frequency spectra are identified, and the correlation between the motor fault types and their corresponding characteristic frequency spectra are established. Finally, the test results confirm that the proposed fault diagnosis system is robust, and requires less complication than former proposed methods.