LAUSR

Induction motors are widely used in several industrial applications due to their factors of favouritism already consolidated, such as robustness, low cost and high reliability. Early detection and proper fault diagnosis reduce the maintenance cost and also increase process effectiveness. Therefore, this paper presents a method for fast classification of rotor faults in line-connected induction motors operating at steady state, under unbalanced voltages and load conditions. Hence, the amplitude of the stator’s current signal in the time domain is presented as input to intelligent computational models for the classification of rotor’s faults. After a proper discretization of the current signal, the points extraction technique is applied allowing a reduction in the classifier’s complexity. Results from 900 experimental tests are provided and compared to validate this study. The results indicate that this approach can be employed to proper classify rotor broken bars in induction motors operating under unbalanced voltage and different load conditions.