Fault Diagnosis of an Induction Motor based on Fuzzy Logic, Artificial Neural Network and Hybrid System

摘要

This paper presents the fault diagnosis of a three-phase induction motor using fuzzy logic, neural network and hybrid system. Detailed analysis during voltage unbalance, open phase, low voltage and overload motor fault using these strategies are presented. Stator currents were measured and their root mean square were derived. These values were used to train data. Each output of these diagnosis tools is used to determine the motor conditions whether it is in a healthy state or in a faulty one. A novel hybrid system is design and used in fault diagnosis. Simulation results show that hybrid systems give the best estimation of faults and can be therefore used in monitoring of induction motors with greater efficiency.