A general scheme for induction motor condition monitoring

This work proposes a general scheme to detect induction motor faults by monitoring the motor current. The scheme is based on signal processing (predictive filters), soft computing techniques (fuzzy logic), the analytical studies of induction motor under fault conditions and the analysis of data generated by finite element method (FEM). The predictive filter is used in order to separate the fundamental component from the harmonic components. Fuzzy logic is used to identify the motor state and FEM is utilized to generate virtual data. A simple and reliable method for the detection of stator failures based on the phase current amplitudes is implemented and tested. The layout has been proved in MATLAB/SIMULINK, with both data from FEM motor simulation program and real measurements. The proposed method is simple and has the ability to work with variable speed drives. This work, on one hand, shows the feasibility of spotting broken bars and inter-turn short-circuit by monitoring the motor currents. On the other hand, it shows that the detection of eccentricity and bearing fault by monitoring the motor current is a difficult task.