FUZZY LOGIC BASED FAULT DETECTION IN INDUCTION MACHINES

Abstract

Three phase induction motors have been utilized in industrial applications, mainly due to their efficiency and reliability. These motors have good properties such as increased stability, robustness, durability, large power to weight ratio, low production costs and controllability easiness. All machines realise various stresses during operational conditions. These stresses might lead to some modes of failures or faults. Condition monitoring is necessary in order to prevent faults. These faults, are necessary to be identified and categorized, as soon as possible as they can end up in serious damages if not detected in due time. Different techniques of fault monitoring for induction motors are broadly classified as techniques based on model, signal processing, and soft computing. For model based techniques, exact models of the faulty machine are required for good fault diagnosis. Sometimes it is difficult to obtain exact models of the machines and also to apply model based techniques. The aim of this thesis is to present model based fault detection and diagnosis schemes for three phase induction motors relying on the fuzzy logic based induction motor health monitoring approach. The three-phase induction motor model has been developed instead of two phase model (d-q representation), which is very commonly used. This is because the two-phase model is driven under balance operation. The simulation results have been presented motor performance in healthy and faulty cases such as stator currents, torque, speed of the motor, symmetrical components of motor current and health monitoring index. The efficiency of the proposed scheme has been extended evaluated with simulation studies for the cases of a normal operation, turn to turn short in one phase winding, break in stator winding, unbalance in input voltage and one phase fault.